https://www.na-mic.org/w/api.php?action=feedcontributions&user=Polina&feedformat=atomNAMIC Wiki - User contributions [en]2024-03-28T11:58:52ZUser contributionsMediaWiki 1.33.0https://www.na-mic.org/w/index.php?title=2016_Winter_Project_Week&diff=906232016 Winter Project Week2015-12-02T15:07:17Z<p>Polina: /* Logistics */</p>
<hr />
<div>__NOTOC__<br />
<br />
[[image:PW-MIT2016.png|300px|left]]<br />
<br><br><br><br><br><br><br><br><br><br><br><br><br />
'''Dates:''' January 4-8, 2016<br />
<br />
'''Location:''' MIT, Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)<br />
<br><br />
<br />
== Introduction ==<br />
Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week. <br />
<br />
[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws 80-120 researchers. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event. <br />
<br />
Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.<br />
<br />
Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO]. <br />
<br />
A summary of all previous Project Events is available [[Project_Events#Past|here]].<br />
<br />
This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.<br />
<br />
Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]<br />
<br />
==Agenda==<br />
<br />
Tentative Agenda<br />
<br />
{|border="1"<br />
|-style="background:#b0d5e6;color:#02186f" <br />
!style="width:10%" |Time<br />
!style="width:18%" |Monday, January 4<br />
!style="width:18%" |Tuesday, January 5<br />
!style="width:18%" |Wednesday, January 6<br />
!style="width:18%" |Thursday, January 7<br />
!style="width:18%" |Friday, January 8<br />
|-<br />
|<br />
|bgcolor="#dbdbdb"|'''Project Presentations''' <br />
|bgcolor="#6494ec"|<br />
|<br />
|bgcolor="#88aaae"|'''IGT Day'''<br />
|bgcolor="#faedb6"|'''Reporting Day'''<br />
|-<br />
|bgcolor="#ffffdd"|'''8:30am'''<br />
|<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast <br />
|-<br />
|bgcolor="#ffffdd"|'''9am-12pm'''<br />
|'''10:30am-12pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 1 by Sarang Joshi)<br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].<br />
|'''10-11:30am:''' <font color="#503020">Breakout Session: New Slicer Extensions'''</font><br><br />
|<br />
'''10-11:30am:''' <font color="#503020">Breakout Session: [[2015_Winter_Project_Week:SlicerROSIntegration| Slicer for Medical Robotics Research]] </font><br />
<br><br />
|'''9:00-10:30am''' TBD <br><br />
<br>----------------------------------------<br><br />
'''10am-12pm: <font color="#4020ff">Breakout Session:'''</font><br>TBD <br><br />
|'''10am-12pm:''' [[#Projects|Project Progress Updates]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''12pm''' [[Events:TutorialContestJune2014|Tutorial Contest Winner Announcement]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
|-<br />
|bgcolor="#ffffdd"|'''12pm-1pm'''<br />
|bgcolor="#ffffaa"|Lunch <br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch boxes; Adjourn by 1:30pm<br />
|-<br />
|bgcolor="#ffffdd"|'''1pm-5:30pm'''<br />
|'''1-1:05pm: <font color="#503020">Welcome</font>'''<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''1:05-2:30pm:''' [[#Projects|Project Introductions]] (all Project Leads)<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''2:45-4pm:''' [[Breakout Session: Ultrasound]]<br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
<br />
'''4:00pm-5:30pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 2 by Sarang Joshi) <br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].<br />
|'''1-3pm:''' <font color="#503020"> [[Breakout Session: What's Planned for Slicer Core]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]] <br />
|'''1-2:30pm:''' <font color="#503020">Breakout Session:'''</font><br>[[Breakout Session: Diffusion MRI]]<br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]] <br />
|<br />
|<br />
|-<br />
|bgcolor="#ffffdd"|'''5:30pm'''<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|<br />
|}<br />
<br />
<googlecalendar>kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com</googlecalendar><br />
<br />
='''Projects'''=<br />
* [[2016_Project_Week_Template | Template for project pages]]<br />
<br />
<br />
* [[2015_Winter_Project_Week:SlicerROSIntegration | 3D Slicer + ROS Integration]] (Junichi Tokuda, Axel Krieger, Simon Leonard)<br />
* [[2016_Winter_Project_Week:TrackedUltrasoundStandardization | Tracked ultrasound standardization]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Steve Pieper, Adam Rankin)<br />
*Integration of CustusX with PLUS on BK System (Christian A, Adam Rankin)<br />
*Integration of ImFusion MR-US registration with BWH AMIGO neurosurgery setup (Christian A, Tina Kapur, Steve Pieper, Sandy Wells, Andras Lasso)<br />
*Digital Pathology Nuclear Segmentation (Erich Bremer, Nicole Aucoin)<br />
*Chest Imaging Platform: COPD and other pulmonary diseases (Raúl San José, Jorge Onieva)<br />
*Upgrade the namic wiki (JC, Mike Halle)<br />
* [[2016_Winter_Project_Week:BatchImageAnalysis | Batch Clinical Image Analysis]] (Kalli Retzepi, Yangming Ou, Matt Toews, Steve Pieper, Sandy Wells, Randy Gollub)<br />
<br />
==Infrastructure==<br />
* [[2016_Winter_Project_Week:SlicerProjectName | Project Name]] (List of people working on this project)<br />
* [[2016_Winter_Project_Week:CommonGL | CommonGL]] (Steve Pieper, Jim Miller)<br />
* [[2016_Winter_Project_Week:WebTechnologies | Web Technologies and Slicer]] (Steve Pieper, Hans Meine)<br />
* [[2016_Winter_Project_Week:CLIModules Backgrounding in MeVisLab | Running CLI Modules in MeVisLab asynchronously]] (Hans Meine)<br />
* [[2016_Winter_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with BRAINSFit (or other interesting CLIs) in MeVisLab]] (Hans Meine, Steve Pieper)<br />
* [[2016_Winter_Project_Week:CLI_Dashboard | Kibana dashboard for browsing all available CLI modules]] (Hans Meine, JC?)<br />
* [[2016_Winter_Project_Week:SegmentationEditorWidget | Editor widget using Segmentations]] (Csaba Pinter, Andras Lasso, Steve Pieper?)<br />
<br />
= '''Logistics''' =<br />
<br />
*'''Dates:''' January 4-8, 2016<br />
*'''Location:''' MIT, Kiva Conference room; 4th floor of Building 32.<br />
*'''REGISTRATION:''' Register [https://www.regonline.com/namic16 here].<br />
*'''Registration Fee:''' $300.<br />
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.<br />
*'''Room sharing''': If interested, add your name to the list [[2016_Winter_Project_Week/RoomSharing|here]]<br />
<br />
= '''Registrants''' =<br />
<br />
Do not add your name to this list - it is maintained by the organizers based on your paid registration.</div>Polinahttps://www.na-mic.org/w/index.php?title=2016_Winter_Project_Week&diff=906222016 Winter Project Week2015-12-02T15:05:43Z<p>Polina: </p>
<hr />
<div>__NOTOC__<br />
<br />
[[image:PW-MIT2016.png|300px|left]]<br />
<br><br><br><br><br><br><br><br><br><br><br><br><br />
'''Dates:''' January 4-8, 2016<br />
<br />
'''Location:''' MIT, Cambridge, MA. (Rooms: [[MIT_Project_Week_Rooms#Kiva|Kiva]], R&D)<br />
<br><br />
<br />
== Introduction ==<br />
Founded in 2005, the National Alliance for Medical Image Computing (NAMIC), was chartered with building a computational infrastructure to support biomedical research as part of the NIH funded [http://www.ncbcs.org/ NCBC] program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform [http://www.slicer.org 3D Slicer], built using [http://www.vtk.org VTK], [http://www.itk.org ITK], [http://www.cmake.org CMake], and [http://www.cdash.org CDash], and the creation of a community of algorithm researchers, biomedical scientists and software engineers who are committed to open science. This community meets twice a year in an event called Project Week. <br />
<br />
[[Engineering:Programming_Events|Project Week]] is a semi-annual event which draws 80-120 researchers. As of August 2014, it is a MICCAI endorsed event. The participants work collaboratively on open-science solutions for problems that lie on the interfaces of the fields of computer science, mechanical engineering, biomedical engineering, and medicine. In contrast to conventional conferences and workshops the primary focus of the Project Weeks is to make progress in projects (as opposed to reporting about progress). The objective of the Project Weeks is to provide a venue for this community of medical open source software creators. Project Weeks are open to all, are publicly advertised, and are funded through fees paid by the attendees. Participants are encouraged to stay for the entire event. <br />
<br />
Project Week activities: Everyone shows up with a project. Some people are working on the platform. Some people are developing algorithms. Some people are applying the tools to their research problems. We begin the week by introducing projects and connecting teams. We end the week by reporting progress. In addition to the ongoing working sessions, breakout sessions are organized ad-hoc on a variety of special topics. These topics include: discussions of software architecture, presentations of new features and approaches and topics such as Image-Guided Therapy.<br />
<br />
Several funded projects use the Project Week as a place to convene and collaborate. These include [http://nac.spl.harvard.edu/ NAC], [http://www.ncigt.org/ NCIGT], [http://qiicr.org/ QIICR], and [http://ocairo.technainstitute.com/open-source-software-platforms-and-databases-for-the-adaptive-process/ OCAIRO]. <br />
<br />
A summary of all previous Project Events is available [[Project_Events#Past|here]].<br />
<br />
This project week is an event [[Post-NCBC-2014|endorsed]] by the MICCAI society.<br />
<br />
Please make sure that you are on the [http://public.kitware.com/mailman/listinfo/na-mic-project-week na-mic-project-week mailing list]<br />
<br />
==Agenda==<br />
<br />
Tentative Agenda<br />
<br />
{|border="1"<br />
|-style="background:#b0d5e6;color:#02186f" <br />
!style="width:10%" |Time<br />
!style="width:18%" |Monday, January 4<br />
!style="width:18%" |Tuesday, January 5<br />
!style="width:18%" |Wednesday, January 6<br />
!style="width:18%" |Thursday, January 7<br />
!style="width:18%" |Friday, January 8<br />
|-<br />
|<br />
|bgcolor="#dbdbdb"|'''Project Presentations''' <br />
|bgcolor="#6494ec"|<br />
|<br />
|bgcolor="#88aaae"|'''IGT Day'''<br />
|bgcolor="#faedb6"|'''Reporting Day'''<br />
|-<br />
|bgcolor="#ffffdd"|'''8:30am'''<br />
|<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast<br />
|bgcolor="#ffffaa"|Breakfast <br />
|-<br />
|bgcolor="#ffffdd"|'''9am-12pm'''<br />
|'''10:30am-12pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 1 by Sarang Joshi)<br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].<br />
|'''10-11:30am:''' <font color="#503020">Breakout Session: New Slicer Extensions'''</font><br><br />
|<br />
'''10-11:30am:''' <font color="#503020">Breakout Session: [[2015_Winter_Project_Week:SlicerROSIntegration| Slicer for Medical Robotics Research]] </font><br />
<br><br />
|'''9:00-10:30am''' TBD <br><br />
<br>----------------------------------------<br><br />
'''10am-12pm: <font color="#4020ff">Breakout Session:'''</font><br>TBD <br><br />
|'''10am-12pm:''' [[#Projects|Project Progress Updates]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''12pm''' [[Events:TutorialContestJune2014|Tutorial Contest Winner Announcement]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
|-<br />
|bgcolor="#ffffdd"|'''12pm-1pm'''<br />
|bgcolor="#ffffaa"|Lunch <br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch<br />
|bgcolor="#ffffaa"|Lunch boxes; Adjourn by 1:30pm<br />
|-<br />
|bgcolor="#ffffdd"|'''1pm-5:30pm'''<br />
|'''1-1:05pm: <font color="#503020">Welcome</font>'''<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''1:05-2:30pm:''' [[#Projects|Project Introductions]] (all Project Leads)<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
'''2:45-4pm:''' [[Breakout Session: Ultrasound]]<br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]]<br />
<br>----------------------------------------<br><br />
<br />
'''4:00pm-5:30pm:''' '''Diffeomorphic registration and the more recent geodesic shooting methods for diffeomorphic registration.''' (Tutorial Part 2 by Sarang Joshi) <br> Room: [http://www.csail.mit.edu/resources/maps/5D/D507.gif 32-D507].<br />
|'''1-3pm:''' <font color="#503020"> [[Breakout Session: What's Planned for Slicer Core]]<br><br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]] <br />
|'''1-2:30pm:''' <font color="#503020">Breakout Session:'''</font><br>[[Breakout Session: Diffusion MRI]]<br />
[[MIT_Project_Week_Rooms#Kiva|Kiva]] <br />
|<br />
|<br />
|-<br />
|bgcolor="#ffffdd"|'''5:30pm'''<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|bgcolor="#f0e68b"|Adjourn for the day<br />
|<br />
|}<br />
<br />
<googlecalendar>kitware.com_sb07i171olac9aavh46ir495c4@group.calendar.google.com</googlecalendar><br />
<br />
='''Projects'''=<br />
* [[2016_Project_Week_Template | Template for project pages]]<br />
<br />
<br />
* [[2015_Winter_Project_Week:SlicerROSIntegration | 3D Slicer + ROS Integration]] (Junichi Tokuda, Axel Krieger, Simon Leonard)<br />
* [[2016_Winter_Project_Week:TrackedUltrasoundStandardization | Tracked ultrasound standardization]] (Andras Lasso, Christian Askeland, Simon Drouin, Junichi Tokuda, Steve Pieper, Adam Rankin)<br />
*Integration of CustusX with PLUS on BK System (Christian A, Adam Rankin)<br />
*Integration of ImFusion MR-US registration with BWH AMIGO neurosurgery setup (Christian A, Tina Kapur, Steve Pieper, Sandy Wells, Andras Lasso)<br />
*Digital Pathology Nuclear Segmentation (Erich Bremer, Nicole Aucoin)<br />
*Chest Imaging Platform: COPD and other pulmonary diseases (Raúl San José, Jorge Onieva)<br />
*Upgrade the namic wiki (JC, Mike Halle)<br />
* [[2016_Winter_Project_Week:BatchImageAnalysis | Batch Clinical Image Analysis]] (Kalli Retzepi, Yangming Ou, Matt Toews, Steve Pieper, Sandy Wells, Randy Gollub)<br />
<br />
==Infrastructure==<br />
* [[2016_Winter_Project_Week:SlicerProjectName | Project Name]] (List of people working on this project)<br />
* [[2016_Winter_Project_Week:CommonGL | CommonGL]] (Steve Pieper, Jim Miller)<br />
* [[2016_Winter_Project_Week:WebTechnologies | Web Technologies and Slicer]] (Steve Pieper, Hans Meine)<br />
* [[2016_Winter_Project_Week:CLIModules Backgrounding in MeVisLab | Running CLI Modules in MeVisLab asynchronously]] (Hans Meine)<br />
* [[2016_Winter_Project_Week:BRAINSFit_in_MeVisLab | Interoperability tests with BRAINSFit (or other interesting CLIs) in MeVisLab]] (Hans Meine, Steve Pieper)<br />
* [[2016_Winter_Project_Week:CLI_Dashboard | Kibana dashboard for browsing all available CLI modules]] (Hans Meine, JC?)<br />
* [[2016_Winter_Project_Week:SegmentationEditorWidget | Editor widget using Segmentations]] (Csaba Pinter, Andras Lasso, Steve Pieper?)<br />
<br />
= '''Logistics''' =<br />
<br />
*'''Dates:''' January 4-8, 2016<br />
*'''Location:''' MIT<br />
*'''REGISTRATION:''' Register [https://www.regonline.com/namic16 here].<br />
*'''Registration Fee:''' $300.<br />
*'''Hotel:''' Similar to previous years, no rooms have been blocked in a particular hotel.<br />
*'''Room sharing''': If interested, add your name to the list [[2016_Winter_Project_Week/RoomSharing|here]]<br />
<br />
= '''Registrants''' =<br />
<br />
Do not add your name to this list - it is maintained by the organizers based on your paid registration.</div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2014.pptx&diff=84676File:NAMIC-AHM-MIT-2014.pptx2014-01-09T04:47:16Z<p>Polina: </p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=AHM_2014_alg_core_presentations&diff=84675AHM 2014 alg core presentations2014-01-09T04:44:09Z<p>Polina: </p>
<hr />
<div>== Alg core presentations ==<br />
<br />
* Utah 1, Ross Whitaker<br />
* [[media:NAMIC-AHM-MIT-2014.pptx | MIT, Polina Golland]]<br />
* Utah 2, Guido Gerig<br />
* [[media:UNC_AHM2014.pptx | UNC, Martin Styner ]]<br />
* Stony Brook, Allen Tannenbaum</div>Polinahttps://www.na-mic.org/w/index.php?title=2014_How_about_the_Future&diff=841992014 How about the Future2013-12-26T17:04:03Z<p>Polina: </p>
<hr />
<div> [[AHM_2014#Agenda|Back to AHM_2014 Agenda]]<br />
<br />
[[image:Slicer-country-stats-2013-11-16.png|right|thumb|500px|Slicer downloads by country and region]]<br />
=Introduction=<br />
This page contains talking points for the opening session of the NA-MIC AHM 2014 (the last one).<br />
<br />
=What we have accomplished=<br />
*Created an outstanding scientific and engineering community in the field of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (MIC).<br />
*Investigated novel algorithmic approaches: Particle systems, registration algorithms, segmentation algorithms,<br />
*Created the NA-MIC kit, a free open source platform for MIC.<br />
*Turned 3D Slicer into a platform with worldwide impact.<br />
<br />
=Where we are today=<br />
*Many algorithm papers, prototypes, and tools<br />
*Slicer 4 is a high performance FOSS and will be available for several years<br />
<br />
=Highlights=<br />
* Robust algorithms for segmentation in the face of anatomical variability: label fusion<br />
* A novel framework for modeling brain connectivity networks<br />
* Robust pipeline for processing clinical brain images<br />
<br />
=Where we go from here=<br />
*Funding:<br />
**NIH mandated sunset for NA-MIC in June 2014. <br />
**[http://projectreporter.nih.gov/project_info_description.cfm?aid=8415024&icde=18711051&ddparam=&ddvalue=&ddsub=&cr=8&csb=default&cs=ASC NAC] funded through 2018. <br />
**[http://projectreporter.nih.gov/project_info_description.cfm?aid=8606944&icde=18711051&ddparam=&ddvalue=&ddsub=&cr=1&csb=default&cs=ASC QIICR] funded through 2018.<br />
**Several other grants are being worked on<br />
*** U54 for further development of statsitical methods, computational platform and visualization tools<br />
*** R01 jointly with MGH Stroke Center to develop and maintain a pipeline for multimodal stroke image analysis across sites<br />
*Project weeks will continue, as long as there is continued interest by the community.<br />
*Slicer 4 will be maintained as a stable platform.<br />
*The remaining months of NA-MIC funding will be used to simplify the submission of extensions.</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:SlicerModules&diff=83414Algorithm:SlicerModules2013-10-13T00:07:36Z<p>Polina: /* Algorithms Core: Slicer Modules Under Development */</p>
<hr />
<div>= Algorithms Core: Slicer Modules Under Development = <br />
These modules will become (or are already) available as extensions in the Slicer Extension Manager as part of the NAMIC Algorithm Core efforts:<br />
<br />
* Left atrium segmentation: In collaboration with the Afib DBP. Graph-cut based segmentation that loads meshes, allows users to interactively "center" the model, perform the graph-cut segmentation, scan convert results into a volumetric format. Contact: Gopal Veni, University of Utah.<br />
<br />
* Multimaterial meshing: Surface and volumetric meshing of multimaterial volumes with output surface triangles viewable within Slicer. Contact: Jonathan Bronson, University of Utah.<br />
<br />
* Interactive segmentation: Control based interactive segmentation module, allowing users to use feedback and observer based principles to drive active contours to equilibrium position and capture desired features. Contact: Ivan Kolesov, SUNY Stony Brook.<br />
<br />
* Sobolev active contours: Robust implementation of the active contour methodology using a Sobolev norm, giving much better results in the presence of noise. Contact: Arie Nakhmani, UAB.<br />
<br />
* Model-based RSS for left atrium segmentation: RSS integrated with a shape prior that is specifically desgined for segmentating the left atrium from MR images. Contact: Liangjia Zhu, SUNY Stony Brook.<br />
<br />
* Left atrial scar segmentation: Given the endocardium of the left atrium, this module automatically extracts the scarring tissue. Contact: Liangjia Zhu, SUNY Stony Brook.<br />
<br />
* DTI Fiber Cleaning & Cropping via FiberViewerLight: Given Slicer fiber tracts, perform semi-automatic cleaning and clustering of fibers, define parametrization planes and crop fibers as necessary. Contact: Francois Budin, UNC<br />
<br />
* Alternative diffusion and fiber processing via DTIProcess: Alternative set of tools for diffusion reconstruction, processing, fiber tracking and processing (dtiestim, dtiprocess, fiber track and fiber process, fiberstats (statistics over fiber sets), dtiaverage (averaged over multiple dti images). Contact: Francois Budin, UNC<br />
<br />
* DTI Registration and DTI atlas building via DTIAtlasBuilder/DTI-Reg: Unbiased group-wise atlas building including additional refinement step, also provides pari-wise DTI registration tool. Contact: Francois Budin, UNC<br />
<br />
* DTI fiber profile extraction & analysis via DTIAtlasFiberAnalyzer: Fiber resampling, profile extraction, statistics gathering and fusion of precomputed attributes, stat results with fibers for visualization. . Contact: Francois Budin, UNC<br />
<br />
* SPHARM-PDM & Particle shape correspondence and analysis: From binary segmentations, generate SPHARM-PDM descriptions, updated via the particle-group wise correspondence. Include statistical analysis and QC visualization of many multiple surfaces at the same time. Contact: Francois Budin & Beatriz Panigua, UNC<br />
<br />
* Registration and segmentation of clinical quality brain MRI scans, with application to stroke. Contact: Ramesh Sridharan, MIT.</div>Polinahttps://www.na-mic.org/w/index.php?title=Renewal-06-2013&diff=81033Renewal-06-20132013-05-14T04:15:21Z<p>Polina: </p>
<hr />
<div> [[2013_Summer_Project_Week#Agenda|Back to Summer project week Agenda]]<br />
<br />
Closed Door Session with Ron. Room [[MIT_Project_Week_Rooms#32-D407|32-D407]]<br />
<br />
=Agenda=<br />
Getting together in one room will allow us to revisit the overall concept, to fine tune our approach, and to discuss open questions with respect to the grant as a whole.<br />
=Participants=<br />
TRD PI's and their delegates.<br />
*Ron Kikinis<br />
*Polina Golland (by google hangout)</div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2013.pptx&diff=79157File:NAMIC-AHM-MIT-2013.pptx2013-01-04T02:26:42Z<p>Polina: uploaded a new version of "File:NAMIC-AHM-MIT-2013.pptx"</p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=AHM_2013_alg_core_presentations&diff=79075AHM 2013 alg core presentations2013-01-03T18:09:52Z<p>Polina: </p>
<hr />
<div> [[AHM_2013#Agenda|Back to AHM_2013 Agenda]]<br />
<br />
<br />
=Presentations=<br />
<br />
* Ross Whitaker: [[Media:NAMIC-AHM-Jan2013-Ross.pptx|Slides]]<br />
* Polina Golland [[Media:NAMIC-AHM-MIT-2013.pptx|Slides]]<br />
* Martin Styner<br />
* Guido Gerig<br />
* Allen Tannenbaum: [[Media:NAMIC-AHM-Jan2013-Allen.pptx|Slides]]</div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2013.pptx&diff=79074File:NAMIC-AHM-MIT-2013.pptx2013-01-03T18:08:58Z<p>Polina: </p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=Projects:GenerativeBrainConnectivity&diff=78583Projects:GenerativeBrainConnectivity2012-12-10T21:30:38Z<p>Polina: /* Publications */</p>
<hr />
<div>Back to [[Main_Page|NA-MIC Collaborations]], [[Algorithm:MIT|MIT Algorithms]]<br />
__NOTOC__<br />
Our goal is to use measures of connectivity between various ROIs as an avenue for understanding the structural and functional organization of the brain. We assess functional and anatomical connectivity using both fMRI correlations and DWI tractography measures, respectively.<br />
<br />
= From Brain Connectivity Models to Identifying Foci of a Neurological Disorder =<br />
<br />
Aberrations in functional connectivity inform us about neuropsychiatric disorders. Functional connectivity is measured via temporal correlations in resting-state functional Magnetic Resonance Imaging (fMRI). Although various studies identify functional connections affected by a clinical disease, connectivity results are difficult to interpret and validate. Specifically, the bulk of our knowledge about the brain is organized around regions (i.e., functional localization, tissue properties, morphometry) and not the connections between them. Moreover, it is nearly impossible to design non-invasive experiments that target a particular connection between two brain regions. In contrast to prior work, we propose a novel framework that pinpoints regions, which we call ``foci", whose functional connectivity patterns are the most disrupted by the disorder.<br />
<br />
Using a probabilistic setting, we define a latent (hidden) graph that characterizes the network of abnormal functional connectivity emanating from the affected brain regions. This generates population differences in the observed fMRI correlations. We use neural anatomy as a substrate for modeling functional connectivity. In particular, we rely on Diffusion Weighted Imaging (DWI) tractography to estimate the underlying white matter fibers in the brain. Since neural communication is constrained by white matter fibers, we hypothesize that the strongest effects of a disorder will occur along direct anatomical connections. Hence, we model whole-brain functional connectivity but only use functional abnormalities between anatomically connected regions to identify the disease foci.<br />
<br />
'''Fig 1. (Left) A network model of connectivity. The nodes correspond to regions in the brain, and the lines denote anatomical connections between them. The green nodes and edges are normal. The red nodes are foci of the disease, and the red edges specify pathways of abnormal functional connectivity. The solid lines are deterministic given the region labels; the dashed lines are probabilistic. (Right) Graphical model representation. Vector ''R'' specifies diseased regions. ''A_ij'' and ''F_ij'' represent the latent anatomical and functional connectivity, respectively, between regions ''i'' and ''j''. Variables associated with the diseased population are identified by an overbar. Boxes denote non-random parameters; circles indicate random variables; shaded variables are observed.'''<br />
<table><br />
<tr> <td align="center"><br />
[[Image:NetworkBrain.png |300px]]<br />
<td align="center" width="100"><br />
<td align="center"><br />
[[Image:TreeModel.png |300px]]<br />
</table><br />
<br />
The nodes in Fig. 1 correspond to regions in the brain. The green nodes are healthy, and the red nodes are diseased. The edges denote neural connections, which are captured by latent anatomical connectivity ''A_ij''. Specifically, the presence or absence of edge in the network is governed by the value of ''A_ij''. The anatomical network structure is shared between the control and clinical populations. The regions in this work correspond to (large) Brodmann areas. Prior results in the field suggest that the anatomical differences between schizophrenia patients and normal controls are very small in this case.<br />
<br />
Based on the region assignments, aberrant functional connectivity along anatomical pathways is defined using a simple set of rules: (1) a connection between two diseased regions is always abnormal (solid red lines in Fig. 1, (2) a connection between two healthy regions is never abnormal (solid green lines), and (3) a connection between a healthy and a diseased region is abnormal with some unknown probability (dashed lines). We use latent functional connectivity to model the neural synchrony between two regions in the control and clinical populations. Ideally, the connectivity should be the same for healthy connections and different for abnormal connections. However, due to noise, we assume that the latent templates can deviate from the above rules with some small probability.<br />
<br />
The observed DWI measurements ''D'' and fMRI correlations ''B'' provide noisy information about the latent network structure.<br />
<br />
''' ''Experimental Results'' '''<br />
<br />
We demonstrate our model on a study of 18 male patients with chronic schizophrenia and 18 male healthy controls. For each subject, an anatomical scan (SPGR, TR=7.4s, TE=3ms, FOV=26cm^2, res=1mm^3), a diffusion-weighted scan (EPI, TR=17s, TE=78ms, FOV=24cm^2, res=1.66x1.66x1.7mm, 51 gradient directions with b=900s/mm^2, 8 baseline scans with b=0s/mm^2) and a resting-state functional scan (EPI-BOLD, TR=3s, TE=30ms, FOV=24cm^2, res=1.875x1.875x3mm) were acquired using a 3T GE Echospeed system.<br />
<br />
We segmented the structural images into 77 anatomical regions with Freesurfer. The DWI data is analyzed using a two-tensor tractography algorithm. The connectivity measure is the average FA along all detected fibers between regions. The measure is set to zero if no tracts are found. We compute the fMRI connectivity as the Pearson correlation coefficient between the mean time courses of the two regions.<br />
<br />
'''Fig 2. Significant regions based on permutation tests. The colorbar corresponds to the negative log p-value. We present the lateral and medial viewpoints for each hemisphere. The highlighted regions are the posterior cingulate (R PCC) and the superior temporal gyrus (L STG & R STG).'''<br />
<table><br />
<tr> <td align="center"><br />
[[Image:01010_SigRegionsM10_lh_lateral.png|400px]]<br />
<td align="center"><br />
[[Image:01010_SigRegionsM10_rh_lateral.png|400px]]<br />
<tr> <td align="center"><br />
[[Image:01010_SigRegionsM10_lh_medial.png|400px]]<br />
<td align="center"><br />
[[Image:01010_SigRegionsM10_rh_medial.png|400px]] <br />
</table><br />
<br />
Prior studies have found abnormalities in the superior temporal gyri in schizophrenia. These impairments correlate with clinical measures of auditory hallucination and attentional deficits. The default network has been implicated in resting-state fMRI studies. Reduced connectivity in the posterior cingulate correlate with both positive and negative symptoms of schizophrenia.<br />
<br />
'''Fig 3. Estimated graph of functional connectivity differences. The red nodes indicate the disease foci. Blue lines indicate reduced functional connectivity and yellow lines indicate increased functional connectivity in the schizophrenia population.'''<br />
<table><br />
<tr> <td align="center"><br />
[[Image:SigRegionsM10_EstimateT.png|300px]]<br />
</table><br />
<br />
In Fig. 3, we observe that functional abnormalities originating in the posterior cingulate project to the midbrain and frontal lobe, whereas abnormalities stemming from the right and left superior temporal gyri tend to span their respective hemispheres. Overall, schizophrenia patients exhibit reduced functional connectivity. Of notable exception are connections to the frontal lobe. This phenomenon has been reported in prior studies of schizophrenia and is believed to interfere with perception by misdirecting attentional resources.<br />
<br />
= Joint Modeling of Anatomical and Functional Connectivity for Population Studies =<br />
<br />
The interaction between functional and anatomical connectivity provides a rich framework for understanding the brain. Functional connectivity is commonly measured via temporal correlations in resting-state fMRI data. These correlations are believed to reflect the intrinsic functional organization of the brain. Anatomical connectivity is often measured using DWI tractography, which estimates the configuration of underlying white matter fibers. In this work we propose and demonstrate a novel probabilistic framework to infer the relationship between these modalities. The model is based on ''latent'' connectivities between brain regions and makes intuitive assumptions about the data generation process. We present a natural extension of the model to population studies, which we use to identify widespread connectivity changes in schizophrenia.<br />
<br />
'''Fig 4. Joint model for the effects of schizophrenia. The pairwise connections are indexed with ''n=1,...,N''. ''A_n'' represents the latent anatomical connectivity of the ''nth'' connection in the control template, and ''F_n'' denotes the corresponding latent functional connectivity. ''D_nj'' and ''B_nj'' are the observed DWI and fMRI measurements, respectively, for the ''nth'' connection in the ''jth'' subject in the control population. The schizophrenia templates are identified by an overbar, and the subjects are indexed by ''m=1,\ldots,M''. Squares indicate non-random parameters; circles indicate random variables; observed variables are shaded.'''<br />
<table><br />
<tr> <td align="center"><br />
[[Image:GenModel3_not.png]]<br />
</table><br />
<br />
Unlike voxel- and ROI-based analysis, we model the behavior of pairwise connections between regions of the brain. Fig. 4 depicts our generative model. We define two latent variables: ''anatomical connectivity'' is a binary random variable that indicates the presence or absence of a direct anatomical pathway between the regions. ''Functional connectivity'' is a tri-state random variable that represent little or no functional co-activation, positive functional synchrony, and negative functional synchrony between the regions. These variables specify templates for each (control, schizophrenia) population. Our observed variables are correlations in resting-state fMRI and average FA values along the white matter tracts. We model differences between the groups within the latent connectivities alone and share the data likelihood distributions between the two populations.<br />
<br />
''' ''Experimental Results'' '''<br />
<br />
We demonstrate our model on a study of 18 male patients with chronic schizophrenia and 18 male healthy controls. For each subject, an anatomical scan (SPGR, TR=7.4s, TE=3ms, FOV=26cm^2, res=1mm^3), a diffusion-weighted scan (EPI, TR=17s, TE=78ms, FOV=24cm^2, res=1.66x1.66x1.7mm, 51 gradient directions with b=900s/mm^2, 8 baseline scans with b=0s/mm^2) and a resting-state functional scan (EPI-BOLD, TR=3s, TE=30ms, FOV=24cm^2, res=1.875x1.875x3mm) were acquired using a 3T GE Echospeed system.<br />
<br />
We segmented the structural images into 77 anatomical regions with Freesurfer. To inject prior clinical knowledge, we pre-selected 8 brain structures (corresponding to 16 regions) that are believed to play a role in schizophrenia: the superior temporal gyrus, rostral middle frontal gyrus, hippocampus, amygdala, posterior cingulate, rostral anterior cingulate, parahippocampal gyrus, and transverse temporal gyrus. We model only the 1096 unique pairwise connections between these ROIs and all other regions in the brain.<br />
<br />
'''Fig 5. Significant anatomical and functional connectivity differences. Blue lines indicate higher connectivity in the control group; yellow lines indicate higher connectivity in the schizophrenia population.'''<br />
<table><br />
<tr> <td align="center"><br />
[[Image:JointEM_Anat_p05_10000.png |405px]]<br />
<td align="center"><br />
[[Image:JointEM_Func_p05_10000.png |400px]]<br />
<tr> <th> '''Anatomical''' <th> '''Functional''' <br />
</table><br />
<br />
Fig. 5 depicts the significantly different anatomical and functional connections identified by the algorithm. As seen, schizophrenia patients exhibit increased functional connectivity between the parietal/posterior cingulate region and the frontal lobe and reduced functional connectivity between the parietal/posterior cingulate region and the temporal lobe. These results confirm the hypotheses of widespread functional connectivity changes in schizophrenia and of functional abnormalities involving the default network.<br />
<br />
The differences in anatomical connectivity implicate the superior temporal gyrus and hippocampus. We note that relatively few anatomical connections exhibit significant differences between the two populations. This may stem from our choice of ROIs. In particular, we rely on Freesurfer parcellations, which provide anatomically meaningful correspondences across subjects and mitigate the effects of minor registration errors. However, they may be too big to capture structural differences between the groups. We emphasize that our model can be easily applied to finer scale parcelations in future studies.<br />
<br />
Table 1 reports classification accuracies for the generative model and SVM classifiers. Despite not being optimized for classification, our model exhibits above-chance generalization accuracy. We note that even the SVM does not achieve high discrimination accuracy. This underscores the well-documented challenge of finding robust functional and anatomical changes induced by schizophrenia. We stress that our main goal is to explain differences in connectivity. Classification is only presented for validation.<br />
<br />
<table><br />
<tr> <td align="center"> '''Table 1. Training and testing accuracy of ten-fold cross validation for the control (NC) and Schizophrenic (SZ) populations.'''<br />
<tr> <td align="center"><br />
[[Image:JointModel_Classification.png |700px]]<br />
</table><br />
<br />
= Key Investigators =<br />
*MIT: Archana Venkataraman, Polina Golland<br />
*Harvard: Carl-Frederik Westin, Marek Kubicki<br />
<br />
= Publications =<br />
[http://www.na-mic.org/publications/pages/display?search=Projects%3AGenerativeBrainConnectivity&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&sponsors=checked&searchbytag=checked| NA-MIC Publications Database on Brain Connectivity]</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78579Algorithm:MIT2012-12-10T18:30:34Z<p>Polina: /* Generative Models of Brain Connectivity */</p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:GenerativeBrainConnectivity|Generative Models of Brain Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
||<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
|-<br />
<br />
<br />
|| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
<font color="red">'''New: '''</font> E. Vul, D. Lashkari, P.-J. Hsieh, P. Golland; N.G. Kanwisher. Data-driven functional clustering reveals dominance of face, place, and body selectivity in the ventral visual pathway. Journal of Neurophysiology, 108:2306-2322, 2012.<br />
<br />
<font color="red">'''New: '''</font> D. Lashkari, R. Sridharan, E. Vul, P.-J. Hsieh, N.G. Kanwisher, and P. Golland. Search for Patterns of Functional Specificity in the Brain: A Nonparametric Hierarchical Bayesian Model for Group fMRI Data. NeuroImage, 59(2):1348-1368, 2012. <br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78578Algorithm:MIT2012-12-10T18:28:37Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:generativeBrainConnectivityConnectivity|Generative Models of Brain Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
||<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
|-<br />
<br />
<br />
|| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
<font color="red">'''New: '''</font> E. Vul, D. Lashkari, P.-J. Hsieh, P. Golland; N.G. Kanwisher. Data-driven functional clustering reveals dominance of face, place, and body selectivity in the ventral visual pathway. Journal of Neurophysiology, 108:2306-2322, 2012.<br />
<br />
<font color="red">'''New: '''</font> D. Lashkari, R. Sridharan, E. Vul, P.-J. Hsieh, N.G. Kanwisher, and P. Golland. Search for Patterns of Functional Specificity in the Brain: A Nonparametric Hierarchical Bayesian Model for Group fMRI Data. NeuroImage, 59(2):1348-1368, 2012. <br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78577Algorithm:MIT2012-12-10T18:21:06Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:generativeBrainConnectivityConnectivity|generative Models of Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
||<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
|-<br />
<br />
<br />
|| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
<font color="red">'''New: '''</font> E. Vul, D. Lashkari, P.-J. Hsieh, P. Golland; N.G. Kanwisher. Data-driven functional clustering reveals dominance of face, place, and body selectivity in the ventral visual pathway. Journal of Neurophysiology, 108:2306-2322, 2012.<br />
<br />
<font color="red">'''New: '''</font> D. Lashkari, R. Sridharan, E. Vul, P.-J. Hsieh, N.G. Kanwisher, and P. Golland. Search for Patterns of Functional Specificity in the Brain: A Nonparametric Hierarchical Bayesian Model for Group fMRI Data. NeuroImage, 59(2):1348-1368, 2012. <br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78575Algorithm:MIT2012-12-10T17:51:04Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
<br />
| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
<font color="red">'''New: '''</font> E. Vul, D. Lashkari, P.-J. Hsieh, P. Golland; N.G. Kanwisher. Data-driven functional clustering reveals dominance of face, place, and body selectivity in the ventral visual pathway. Journal of Neurophysiology, 108:2306-2322, 2012.<br />
<br />
<font color="red">'''New: '''</font> D. Lashkari, R. Sridharan, E. Vul, P.-J. Hsieh, N.G. Kanwisher, and P. Golland. Search for Patterns of Functional Specificity in the Brain: A Nonparametric Hierarchical Bayesian Model for Group fMRI Data. NeuroImage, 59(2):1348-1368, 2012. <br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78574Algorithm:MIT2012-12-10T17:48:26Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
<br />
| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78573Algorithm:MIT2012-12-10T17:47:33Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
C. Wachinger and P. Golland. Spectral Label Fusion. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 7512:410-417, 2012.<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> <br />
A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. IEEE Transactions on Medical Imaging, 31(2):164-182, 2012.<br />
<br />
<font color="red">'''New: '''</font> <br />
<br />
A. Venkataraman, T.J. Whitford, C-F. Westin, P. Golland and M. Kubicki. Whole Brain Resting State Functional Connectivity Abnormalities in Schizophrenia. Schizophrenia Research, 139(1-3):7-12, 2012.<br />
<br />
<font color="red">'''New: '''</font> <br />
<br />
A. Venkataraman, M. Kubicki and P. Golland. From Brain Connectivity Models to Identifying Foci of a Neurological Disorder. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervention, LNCS 7510:715-722, 2012.<br />
<br />
|-<br />
<br />
<br />
| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, LNAI 7263:68-75, 2012.<br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=78572Algorithm:MIT2012-12-10T17:42:45Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
|| [[Image:GI_15_p05_orig.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:DataDrivenFunctionalConnectivity|Data Driven Functional Connectivity]] ==<br />
This project uses standard machine learning algorithms to automatically identify relevant patterns in functional connectivity data. Our first application is to determine predictive differences between a control and clinical population. Our second application is to partition the brain into different functional systems. [[Projects:DataDrivenFunctionalConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. To appear in IEEE Transactions on Medical Imaging, 2011. <br />
<br />
|-<br />
<br />
<br />
| [[Image:georgehc_disc_front.png|250px]]<br />
||<br />
<br />
== [[Projects:ModelingFunctionalActivationPatterns| Modeling Functional Activation Patterns]] ==<br />
<br />
For a given cognitive task such as language processing, the location of corresponding functional regions in the brain may vary across subjects relative to anatomy. We present a probabilistic generative model that accounts for such variability as observed in functional magnetic resonance imaging (fMRI) data. We relate our approach to sparse coding that estimates a basis consisting of functional regions in the brain. Individual fMRI data is represented as a weighted sum of these functional regions that undergo deformations. We demonstrate the proposed method on a language fMRI study. Our method identified activation regions that agree with known literature on language processing and established correspondences among activation regions across subjects, producing more robust group-level effects than anatomical alignment alone. [[Projects:ModelingFunctionalActivationPatterns|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Chen, E. Fedorenko, N.G. Kanwisher, and P. Golland. Deformation-Invariant Sparse Coding for Modeling Spatial Variability of Functional Patterns in the Brain. In Proc. Neural Information Processing Systems (NIPS) Workshop on Machine Learning and Interpretation in Neuroimaging, 2012.<br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Dalca, G. Danagoulian, R. Kikinis, E. Schmidt, and P. Golland. Segmentation of Nerve Bundles and Ganglia in Spine MRI Using Particle Filters. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 6893:537, 2011. <br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, B.H. Menze, D. Lashkari, and P. Golland. Detecting Stable Distributed Patterns of Brain Activation Using Gini Contrast. NeuroImage, 56(2):497-507, 2011.<br />
<br />
|-<br />
<br />
|<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
|-<br />
<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=ClosedSession2013&diff=78501ClosedSession20132012-12-03T19:43:02Z<p>Polina: /* Translations */</p>
<hr />
<div>=NA-MIC renewal=<br />
<br />
Definition of the roles of the TRD components<br />
<br />
===Algorithm research===<br />
*Research new algorithms<br />
===Applications===<br />
*turn algorithm prototypes into tools in Slicer: open source, high performance extensions with a graphical user interface in Slicer<br />
<br />
===Translation===<br />
*develop Slicer based, documented complete workflows for the DBP's<br />
<br />
===Success criteria for TRDs===<br />
* a working, documented extension to Slicer with a tutorial and example data<br />
* compliant with [http://www.slicer.org/slicerWiki/index.php/Documentation-Rons-Rules-For-Tools Rons Rules For Tools]<br />
* the extension needs to be usable by somebody who is not part of the NA-MIC community.<br />
<br />
==Budgets==</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77555Call for Identification of Medical Image Computing Grant Applications2012-09-04T20:12:28Z<p>Polina: </p>
<hr />
<div>[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (MIC) is a young field of research. To the best of our knowledge, there is no study section at NIH specializing on this topic. This is in contrast to the well established field of [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], which is focused on improving image acquisition and reconstruction and has its own specialized study section.<br />
<br />
We would like to raise the visibility of the field of Medical Image Computing (MIC) with the long term goal of initiating the creation of a study section focused on our field. This would provide a better match not only of the individual reviewers but also of the study section as a whole, which would be better attuned to MIC content. NIH needs evidence that enough grants on the topic are submitted at sufficient frequency to initiate this process. The typical threshold is around 20 submissions per cycle. Typically, an ad-hoc study section is created first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call to the Medical Image Computing community. When submitting a MIC themed grant application to the NIH, please include the term '''Medical Image Computing''' in your grant summary and the keywords. You don't need to do anything else, just add the term. If, as a community, we can sustain the volume of applications that are labeled like this, then we can lobby for the process of study section formation to begin.<br />
<br />
Our goal is to use the existing policies and governance to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the reviewing system relative to the current state where Medical Image Computing applications are sent to a variety of different study sections and are evaluated by reviewers with core competences largely outside the MIC field.<br />
<br />
=Actions Requested=<br />
* Please include '''Medical Image Computing''' in the summary and keywords of all your future grant applications to NIH. <br />
* Review the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. Improve the wikipedia page by editing and adding content.<br />
<br />
=Signed=<br />
#[http://people.csail.mit.edu/polina Polina Golland]<br />
#[http://www.spl.harvard.edu/pages/People/kikinis Ron Kikinis]<br />
#[http://www.martinstyner.org Martin Styner]<br />
#[http://www.sci.utah.edu/people/gerig.html Guido Gerig]<br />
#[http://www.na-mic.org/Wiki/index.php/Algorithm:BU Allen Tannenbaum]<br />
#[http://lmi.bwh.harvard.edu/~westin Carl-Fredrik Westin]<br />
#[http://www.cs.utah.edu/~crj/ Chris Johnson]<br />
#[http://www.stanford.edu/people/Sandy.Napel Sandy Napel]<br />
#[http://www.cs.queensu.ca/~gabor Gabor Fichtinger]<br />
#[http://www.iacl.ece.jhu.edu/ Aaron Carass]<br />
#[https://masi.vuse.vanderbilt.edu/index.php/Main_Page Bennett Landman]<br />
#[http://www.cise.ufl.edu/~vemuri Baba C. Vemuri]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77549Call for Identification of Medical Image Computing Grant Applications2012-09-04T15:22:58Z<p>Polina: /* Signed */</p>
<hr />
<div>[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (MIC) is a young field of research. To the best of our knowledge, there is no study section at NIH specializing on this topic. This is in contrast to the well established field of [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], which is focused on improving image acquisition and reconstruction and has its own specialized study section.<br />
<br />
We would like to raise the visibility of the field of Medical Image Computing (MIC) with the long term goal of initiating the creation of a study section focused on our field. This would provide a better match not only of the individual reviewers but also of the study section as a whole, which would be better attuned to MIC content. NIH needs evidence that enough grants on the topic are submitted at sufficient frequency to initiate this process. The typical threshold is around 20 submissions per cycle. Typically, an ad-hoc study section is created first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call to the Medical Image Computing community. When submitting a grant application to the NIH, please include the term '''Medical Image Computing''' in your grant summary and the keywords. You don't need to do anything else, just add the term. If, as a community, we can sustain the volume of applications that are labeled like this, then we can lobby for the process of study section formation to begin.<br />
<br />
Our goal is to use the existing policies and governance to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the reviewing system relative to the current state where Medical Image Computing applications are sent to a variety of different study sections and are evaluated by reviewers with core competences largely outside the MIC field.<br />
<br />
=Actions Requested=<br />
* Please include '''Medical Image Computing''' in the summary and keywords of all your future grant applications to NIH. <br />
* Review the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. Improve the wikipedia page by editing and adding content.<br />
<br />
=Signed=<br />
#[http://people.csail.mit.edu/polina Polina Golland]<br />
#[http://www.spl.harvard.edu/pages/People/kikinis Ron Kikinis]<br />
#[http://www.martinstyner.org Martin Styner]<br />
#[http://www.sci.utah.edu/people/gerig.html Guido Gerig]<br />
#[http://www.na-mic.org/Wiki/index.php/Algorithm:BU Allen Tannenbaum]<br />
#[http://lmi.bwh.harvard.edu/~westin Carl-Fredrik Westin]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77543Call for Identification of Medical Image Computing Grant Applications2012-09-04T02:10:09Z<p>Polina: </p>
<hr />
<div>[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (MIC) is a young field of research. To the best of our knowledge, there is no study section at NIH specializing on this topic. This is in contrast to the well established field of [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], which is focused on improving image acquisition and reconstruction and has its own specialized study section.<br />
<br />
We would like to raise the visibility of the field of Medical Image Computing (MIC) with the long term goal of initiating the creation of a study section focused on our field. This would provide a better match not only of the individual reviewers but also of the study section as a whole, which would be better attuned to MIC content. NIH needs evidence that enough grants on the topic are submitted at sufficient frequency to initiate this process. The typical threshold is around 20 submissions per cycle. Typically, an ad-hoc study section is created first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call to the Medical Image Computing community. When submitting a grant application to the NIH, please include the term '''Medical Image Computing''' in your grant summary and the keywords. You don't need to do anything else, just add the term. If, as a community, we can sustain the volume of applications that are labeled like this, then we can lobby for the process of study section formation to begin.<br />
<br />
Our goal is to use the existing policies and governance to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the reviewing system relative to the current state where Medical Image Computing applications are sent to a variety of different study sections and are evaluated by reviewers with core competences largely outside the MIC field.<br />
<br />
=Actions Requested=<br />
* Please include '''Medical Image Computing''' in the summary and keywords of all your future grant applications to NIH. <br />
* Review the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. Improve the wikipedia page by editing and adding content.<br />
<br />
=Signed=<br />
#[http://www.spl.harvard.edu/pages/People/kikinis Ron Kikinis]<br />
#[http://www.martinstyner.org Martin Styner]<br />
#[http://www.sci.utah.edu/people/gerig.html Guido Gerig]<br />
#[http://www.na-mic.org/Wiki/index.php/Algorithm:BU Allen Tannenbaum]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77542Call for Identification of Medical Image Computing Grant Applications2012-09-04T02:09:53Z<p>Polina: </p>
<hr />
<div>[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] is a young field of research. To the best of our knowledge, there is no study section at NIH specializing on this topic. This is in contrast to the well established field of [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], which is focused on improving image acquisition and reconstruction and has its own specialized study section.<br />
<br />
We would like to raise the visibility of the field of Medical Image Computing (MIC) with the long term goal of initiating the creation of a study section focused on our field. This would provide a better match not only of the individual reviewers but also of the study section as a whole, which would be better attuned to MIC content. NIH needs evidence that enough grants on the topic are submitted at sufficient frequency to initiate this process. The typical threshold is around 20 submissions per cycle. Typically, an ad-hoc study section is created first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call to the Medical Image Computing community. When submitting a grant application to the NIH, please include the term '''Medical Image Computing''' in your grant summary and the keywords. You don't need to do anything else, just add the term. If, as a community, we can sustain the volume of applications that are labeled like this, then we can lobby for the process of study section formation to begin.<br />
<br />
Our goal is to use the existing policies and governance to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the reviewing system relative to the current state where Medical Image Computing applications are sent to a variety of different study sections and are evaluated by reviewers with core competences largely outside the MIC field.<br />
<br />
=Actions Requested=<br />
* Please include '''Medical Image Computing''' in the summary and keywords of all your future grant applications to NIH. <br />
* Review the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. Improve the wikipedia page by editing and adding content.<br />
<br />
=Signed=<br />
#[http://www.spl.harvard.edu/pages/People/kikinis Ron Kikinis]<br />
#[http://www.martinstyner.org Martin Styner]<br />
#[http://www.sci.utah.edu/people/gerig.html Guido Gerig]<br />
#[http://www.na-mic.org/Wiki/index.php/Algorithm:BU Allen Tannenbaum]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77526Call for Identification of Medical Image Computing Grant Applications2012-09-01T00:45:59Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term '''Medical Image Computing''' in your grant summary/abstract and keywords. You don't need to do anything else differently, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Computing. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77521Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:39:40Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term Medical Image Analysis in your grant summary/abstract and keywords. You don't need to do anything else differently, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Analysis. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77520Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:38:18Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term Medical Image Analysis in your grant summary/abstract and keywords. You don't need to do anything different, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Analysis. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77519Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:37:56Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term Medical Image Analysis in your grant summary/abstract and keywords. You don't need to do anything different, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Analysis. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]. [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77518Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:37:33Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term Medical Image Analysis in your grant summary/abstract and keywords. You don't need to do anything different, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Analysis. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]. [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77517Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:34:19Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing]. And yet, we struggle to get NIH funding for methodological developments in this area of research. While we get encouragement from the program officers, the applications often gets poor scores from the study sections. To the best of our knowledge, there is no study section at NIH on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image Computing] (rather than [http://en.wikipedia.org/wiki/Medical_imaging Medical Imaging], for example, that is much more focused on improving image acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on the topic are submitted to warrant an ad-hoc study section first, which can later be converted to a permanent study section if the stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to NIH. Please mention the term Medical Image Analysis in your grant summary/abstract and keywords. You don't need to do anything different, just add the keyword to the text. After 3-4 grant submission cycles, this will give NIH enough evidence (by searching the applications) to warrant a special ad-hoc study section on Medical Image Analysis. This will be a start. If as a community, we can sustain the volume of applications for a separate section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH review process. Our goal is to use the existing structure to create a completely valid avenue for Medical Image Computing grant applications to compete against others in this field on equal footing and for the NIH reviewers to select the best science and engineering in this field with the highest potential to improve medical care. This will improve the system relative to the current state where Medical Image Computing applications are sent to many other study sections and are evaluated by reviewers largely outside the field.<br />
<br />
All you need to do to help with the process is to mention [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing] in the summary and the keywords of the next grant applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on [http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77516Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:28:11Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of<br />
[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]. And yet, we struggle to get NIH funding for methodological<br />
developments in this area of research. While we get encouragement from<br />
the program officers, the applications often gets poor scores from the<br />
study sections. To the best of our knowledge, there is no study<br />
section at NIH on Medical Image Computing (rather than Medical<br />
Imaging, for example, that is much more focused on improving image<br />
acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on<br />
the topic are submitted to warrant an ad-hoc study section first,<br />
which can later be converted to a permanent study section if the<br />
stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to<br />
NIH. Please mention the term Medical Image Analysis in your abstract<br />
and keywords. You don't need to do anything different, just list the<br />
keyword. After 3-4 grant submission cycles, this will give NIH enough<br />
evidence (by searching the applications) to warrant a special ad-hoc<br />
study section on Medical Image Analysis. This will be a start. If as a<br />
community, we can sustain the volume of applications for a separate<br />
section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH<br />
review process. Our goal is to use the existing structure to create a<br />
completely valid avenue for Medical Image Computing grant applications<br />
to compete against others in this field on equal footing and for the<br />
NIH reviewers to select the best science and engineering in this field<br />
with the highest potential to improve medical care.<br />
<br />
All you need to do to help with the process is to mention<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]] in the summary and the keywords of the next grant<br />
applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77515Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:27:01Z<p>Polina: </p>
<hr />
<div>Many of us work in a clinically relevant area of<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]]. And yet, we struggle to get NIH funding for methodological<br />
developments in this area of research. While we get encouragement from<br />
the program officers, the applications often gets poor scores from the<br />
study sections. To the best of our knowledge, there is no study<br />
section at NIH on Medical Image Computing (rather than Medical<br />
Imaging, for example, that is much more focused on improving image<br />
acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on<br />
the topic are submitted to warrant an ad-hoc study section first,<br />
which can later be converted to a permanent study section if the<br />
stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to<br />
NIH. Please mention the term Medical Image Analysis in your abstract<br />
and keywords. You don't need to do anything different, just list the<br />
keyword. After 3-4 grant submission cycles, this will give NIH enough<br />
evidence (by searching the applications) to warrant a special ad-hoc<br />
study section on Medical Image Analysis. This will be a start. If as a<br />
community, we can sustain the volume of applications for a separate<br />
section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH<br />
review process. Our goal is to use the existing structure to create a<br />
completely valid avenue for Medical Image Computing grant applications<br />
to compete against others in this field on equal footing and for the<br />
NIH reviewers to select the best science and engineering in this field<br />
with the highest potential to improve medical care.<br />
<br />
All you need to do to help with the process is to mention<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]] in the summary and the keywords of the next grant<br />
applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing Medical Image<br />
Computing]].</div>Polinahttps://www.na-mic.org/w/index.php?title=Call_for_Identification_of_Medical_Image_Computing_Grant_Applications&diff=77514Call for Identification of Medical Image Computing Grant Applications2012-08-30T21:25:43Z<p>Polina: Created page with 'Many of us work in a clinically relevant area of Medical Image Computing. And yet, we struggle to get NIH funding for met…'</p>
<hr />
<div>Many of us work in a clinically relevant area of<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image<br />
Computing]]. And yet, we struggle to get NIH funding for methodological<br />
developments in this area of research. While we get encouragement from<br />
the program officers, the applications often gets poor scores from the<br />
study sections. To the best of our knowledge, there is no study<br />
section at NIH on Medical Image Computing (rather than Medical<br />
Imaging, for example, that is much more focused on improving image<br />
acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on<br />
the topic are submitted to warrant an ad-hoc study section first,<br />
which can later be converted to a permanent study section if the<br />
stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to<br />
NIH. Please mention the term Medical Image Analysis in your abstract<br />
and keywords. You don't need to do anything different, just list the<br />
keyword. After 3-4 grant submission cycles, this will give NIH enough<br />
evidence (by searching the applications) to warrant a special ad-hoc<br />
study section on Medical Image Analysis. This will be a start. If as a<br />
community, we can sustain the volume of applications for a separate<br />
section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH<br />
review process. Our goal is to use the existing structure to create a<br />
completely valid avenue for Medical Image Computing grant applications<br />
to compete against others in this field on equal footing and for the<br />
NIH reviewers to select the best science and engineering in this field<br />
with the highest potential to improve medical care.<br />
<br />
All you need to do to help with the process is to mention<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing | Medical Image<br />
Computing]] in the summary and the keywords of the next grant<br />
applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image<br />
Computing]].</div>Polinahttps://www.na-mic.org/w/index.php?title=Main_Page&diff=77513Main Page2012-08-30T21:25:10Z<p>Polina: /* Call for Medical Image Computing Grant Applications */</p>
<hr />
<div>__NOTOC__<br />
__NOTOC__<br />
='''Welcome to the NA-MIC Wiki!''' <br> <br> http://wiki.na-mic.org=<br />
{| border="00" cellpadding="5" cellspacing="0" width="90%"<br />
|-<br />
| rowspan="2"| [[Image:NIH_Logo.png|[[Image:NIH_Logo.png|Image:NIH_Logo.png]]]][[Image:Dhhs_logo.png|[[Image:Dhhs_logo.png|Image:Dhhs_logo.png]]]]<br />
<br />
''Welcome!''<br />
<br />
These wiki pages are meant to encourage quick and efficient communication among the participating investigators and the interested users of NA-MIC. If you are interested in the BIG picture or need an introduction to our project please go to our main web page [http://www.na-mic.org/ NA-MIC]. To get an idea of the ongoing activities in this project, follow the links in the Navigation box on the left side of this page: Cores and Projects contains information about the activities in the individual NA-MIC cores as well as cross-NCBC activities, the Events pages contains information about upcoming and past NA-MIC events including teleconferences, and the Resources pages contain information about NA-MIC software.<br />
| style="background: #ebeced" colspan="2" align="center"| [[Image:Slicer4Announcement-HiRes.png|400px]]<br />
|-<br />
| style="background: #ebeced"| <br />
| style="background: #ebeced"|Slicer 4.1 released in March 2012. See the [http://www.slicer.org/slicerWiki/index.php/Documentation/4.1/Announcements Announcement] for more information.<br />
|}<br />
<br><br />
----<br />
<br />
==[[Events|Events]]==<br />
A list of all our past and upcoming events.<br />
<br />
==[[NA-MIC_Collaborations|NA-MIC Collaborations]]==<br />
This is a list of our internal and external collaborative projects.<br />
<br />
==[[NA-MIC-Kit|NA-MIC Kit]]==<br />
The NA-MIC Kit consists of software and software engineering methods that are used and developed by NA-MIC, including [http://www.slicer.org Slicer3]. For training in the use of Slicer3 see [http://www.slicer.org/slicerWiki/index.php/Slicer3.4:Training#Software_tutorials|'''here'''].<br />
<br />
==[[Project_Events|NA-MIC Programming/Project Events]]==<br />
NA-MIC Project Week is a hands on activity -- programming using the NA-MIC Kit, algorithm design, and clinical applications. The link above leads to results from project weeks held since 2005.<br />
<br />
<br />
==[[Call_for_Medical_Image_Computing_Grant_Applications|Call for Medical Image Computing Grant Applications]]==<br />
<br />
This is a call to help us improve the review process for Medical Image Computing grant applications by NIH.<br />
<br />
==Pages for Affiliated Research Teams and Organizations ==<br />
----<br />
<br />
==[[NIH-Page|NIH Page]]==<br />
* This page contains useful information provided by our NIH officers.<br />
<br />
==[[Historic-Links|Other Links]]==</div>Polinahttps://www.na-mic.org/w/index.php?title=Medical_Image_Computing_NIH&diff=77512Medical Image Computing NIH2012-08-30T21:23:29Z<p>Polina: Created page with '== Call for Medical Image Computing Grant Applications == Many of us work in a clinically relevant area of [[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image C…'</p>
<hr />
<div>== Call for Medical Image Computing Grant Applications ==<br />
<br />
Many of us work in a clinically relevant area of<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image<br />
Computing]. And yet, we struggle to get NIH funding for methodological<br />
developments in this area of research. While we get encouragement from<br />
the program officers, the applications often gets poor scores from the<br />
study sections. To the best of our knowledge, there is no study<br />
section at NIH on Medical Image Computing (rather than Medical<br />
Imaging, for example, that is much more focused on improving image<br />
acquisition). <br />
<br />
To create such study section, NIH needs evidence that enough grants on<br />
the topic are submitted to warrant an ad-hoc study section first,<br />
which can later be converted to a permanent study section if the<br />
stream of applications is sustained over several application cycles.<br />
<br />
This is a call for everyone who is submitting a grant application to<br />
NIH. Please mention the term Medical Image Analysis in your abstract<br />
and keywords. You don't need to do anything different, just list the<br />
keyword. After 3-4 grant submission cycles, this will give NIH enough<br />
evidence (by searching the applications) to warrant a special ad-hoc<br />
study section on Medical Image Analysis. This will be a start. If as a<br />
community, we can sustain the volume of applications for a separate<br />
section, the ad-hoc study section will convert to a permanent one.<br />
<br />
We are not calling for any drastic changes in the structure of the NIH<br />
review process. Our goal is to use the existing structure to create a<br />
completely valid avenue for Medical Image Computing grant applications<br />
to compete against others in this field on equal footing and for the<br />
NIH reviewers to select the best science and engineering in this field<br />
with the highest potential to improve medical care.<br />
<br />
All you need to do to help with the process is to mention<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image<br />
Computing] in the summary and the keywords of the next grant<br />
applications you are sending to NIH. And help us improve the<br />
visibility of the field by editing the wikipedia page on<br />
[[http://en.wikipedia.org/wiki/Medical_image_computing|Medical Image<br />
Computing].</div>Polinahttps://www.na-mic.org/w/index.php?title=Main_Page&diff=77511Main Page2012-08-30T21:23:08Z<p>Polina: /* NA-MIC Programming/Project Events */</p>
<hr />
<div>__NOTOC__<br />
__NOTOC__<br />
='''Welcome to the NA-MIC Wiki!''' <br> <br> http://wiki.na-mic.org=<br />
{| border="00" cellpadding="5" cellspacing="0" width="90%"<br />
|-<br />
| rowspan="2"| [[Image:NIH_Logo.png|[[Image:NIH_Logo.png|Image:NIH_Logo.png]]]][[Image:Dhhs_logo.png|[[Image:Dhhs_logo.png|Image:Dhhs_logo.png]]]]<br />
<br />
''Welcome!''<br />
<br />
These wiki pages are meant to encourage quick and efficient communication among the participating investigators and the interested users of NA-MIC. If you are interested in the BIG picture or need an introduction to our project please go to our main web page [http://www.na-mic.org/ NA-MIC]. To get an idea of the ongoing activities in this project, follow the links in the Navigation box on the left side of this page: Cores and Projects contains information about the activities in the individual NA-MIC cores as well as cross-NCBC activities, the Events pages contains information about upcoming and past NA-MIC events including teleconferences, and the Resources pages contain information about NA-MIC software.<br />
| style="background: #ebeced" colspan="2" align="center"| [[Image:Slicer4Announcement-HiRes.png|400px]]<br />
|-<br />
| style="background: #ebeced"| <br />
| style="background: #ebeced"|Slicer 4.1 released in March 2012. See the [http://www.slicer.org/slicerWiki/index.php/Documentation/4.1/Announcements Announcement] for more information.<br />
|}<br />
<br><br />
----<br />
<br />
==[[Events|Events]]==<br />
A list of all our past and upcoming events.<br />
<br />
==[[NA-MIC_Collaborations|NA-MIC Collaborations]]==<br />
This is a list of our internal and external collaborative projects.<br />
<br />
==[[NA-MIC-Kit|NA-MIC Kit]]==<br />
The NA-MIC Kit consists of software and software engineering methods that are used and developed by NA-MIC, including [http://www.slicer.org Slicer3]. For training in the use of Slicer3 see [http://www.slicer.org/slicerWiki/index.php/Slicer3.4:Training#Software_tutorials|'''here'''].<br />
<br />
==[[Project_Events|NA-MIC Programming/Project Events]]==<br />
NA-MIC Project Week is a hands on activity -- programming using the NA-MIC Kit, algorithm design, and clinical applications. The link above leads to results from project weeks held since 2005.<br />
<br />
<br />
==[[Medical_Image_Computing_NIH|Call for Medical Image Computing Grant Applications]]==<br />
<br />
==Pages for Affiliated Research Teams and Organizations ==<br />
----<br />
<br />
==[[NIH-Page|NIH Page]]==<br />
* This page contains useful information provided by our NIH officers.<br />
<br />
==[[Historic-Links|Other Links]]==</div>Polinahttps://www.na-mic.org/w/index.php?title=2012-Nov-NIH-event-planning&diff=775062012-Nov-NIH-event-planning2012-08-30T14:38:02Z<p>Polina: /* Potential Names */</p>
<hr />
<div>=Background=<br />
Peter:Regarding Nov 8-9 NCBC Showcase. Some items that need quick attention so<br />
we can do a full court press on publicity.<br />
<br />
# As soon as possible, send Jen and me a list of five high-profile individuals whom we can invite on the ‘testimonial’ panel (i.e., will make a 15 minute presentation about they have used your work/software, and sit on panel). Give us a ranking and brief statement of what the testimonial will be about. Extra points for anyone who can speak to more than one NCBC. <br />
# If you haven’t sent us the list of five young people, can you do that. Also in rank order with brief explanation.<br />
# Someone made the suggestion that since young trainees are so important we reinstate the lightening talks and reduce the NCBC PI presentation to 20 minutes. We’re ok with that. It will be busy, but the junior people are so important.<br />
<br />
=email by R. K.=<br />
Hi,<br />
<br />
Peter Lyster at NIGMS is organizing an event in November to give the NCBC program more visibility. He wants to circulate the program to NIH folks in order to get it onto their schedules. See his email below on this topic.<br />
<br />
We will have a tcon tomorrow to plan our contribution to this event, which is part of the effort to make a competitive renewal of NA-MIC happen. If you can not participate, please email me your thoughts. This whole procedure is on a short fuse.<br />
<br />
The tcon will take place on Friday, August 31, from 11am - 11:30am. Please use the following number: 800-501-8979, access code: 7327389<br />
<br />
Talk to you tomorrow<br />
<br />
Ron<br />
<br />
=Potential Names=<br />
*Established:<br />
**Medical<br />
***Alex Golby<br />
**Technical<br />
***Gabor Fichtinger<br />
***Terry Peters<br />
***Russ Taylor<br />
***Andras Lasso<br />
*Up and Coming<br />
**Andrei Irimia<br />
**Danielle Pace<br />
**Andrey Fedorov<br />
**Archana Venkataraman - just finished her PhD<br />
**Mert Sabuncu - faculty at MGH, did his postdoc on NAMIC-related problems</div>Polinahttps://www.na-mic.org/w/index.php?title=2012-Nov-NIH-event-planning&diff=775052012-Nov-NIH-event-planning2012-08-30T14:36:42Z<p>Polina: </p>
<hr />
<div>=Background=<br />
Peter:Regarding Nov 8-9 NCBC Showcase. Some items that need quick attention so<br />
we can do a full court press on publicity.<br />
<br />
# As soon as possible, send Jen and me a list of five high-profile individuals whom we can invite on the ‘testimonial’ panel (i.e., will make a 15 minute presentation about they have used your work/software, and sit on panel). Give us a ranking and brief statement of what the testimonial will be about. Extra points for anyone who can speak to more than one NCBC. <br />
# If you haven’t sent us the list of five young people, can you do that. Also in rank order with brief explanation.<br />
# Someone made the suggestion that since young trainees are so important we reinstate the lightening talks and reduce the NCBC PI presentation to 20 minutes. We’re ok with that. It will be busy, but the junior people are so important.<br />
<br />
=email by R. K.=<br />
Hi,<br />
<br />
Peter Lyster at NIGMS is organizing an event in November to give the NCBC program more visibility. He wants to circulate the program to NIH folks in order to get it onto their schedules. See his email below on this topic.<br />
<br />
We will have a tcon tomorrow to plan our contribution to this event, which is part of the effort to make a competitive renewal of NA-MIC happen. If you can not participate, please email me your thoughts. This whole procedure is on a short fuse.<br />
<br />
The tcon will take place on Friday, August 31, from 11am - 11:30am. Please use the following number: 800-501-8979, access code: 7327389<br />
<br />
Talk to you tomorrow<br />
<br />
Ron<br />
<br />
=Potential Names=<br />
*Established:<br />
**Medical<br />
***Alex Golby<br />
**Technical<br />
***Gabor Fichtinger<br />
***Terry Peters<br />
***Russ Taylor<br />
***Andras Lasso<br />
*Up and Coming<br />
**Andrei Irimia<br />
**Danielle Pace<br />
**Andrey Fedorov<br />
**Archana Venkataraman</div>Polinahttps://www.na-mic.org/w/index.php?title=Core_1_Retreat_2012&diff=77237Core 1 Retreat 20122012-07-20T03:37:22Z<p>Polina: </p>
<hr />
<div> [[events|Back to NA-MIC events page]]<br />
<br />
August 20 and 21<br />
<br />
Park City, Utah<br />
<br />
=Overview=<br />
* Starting at 8:30am on Monday (please come in the night before). Finishing 2pm on Tuesday.<br />
* Business issues<br />
** DBPs<br />
** Research interactions between groups<br />
** Renewal planning<br />
** Logistics of Core and NA-MIC<br />
* Presentations from students, fellows, faculty - approximately 10 minutes each. <br />
** Assume a tech savvy audience that knows these topics somewhat already<br />
** Presentations should focus on technological developments - no need for "motivation", "introduction", etc. <br />
<br />
=Agenda=<br />
* NA-MIC renewal update<br />
<br />
= Attendees =<br />
# Ross Whitaker<br />
# Ron Kikinis<br />
# Allen Tannenbaum<br />
# Yi Gao<br />
# Guido Gerig<br />
# Bo Wang<br />
# James Fishbaugh<br />
# Anuja Sharma<br />
# Martin Styner<br />
# Polina Golland<br />
# Kayhan Batmanghelich<br />
<br />
=Logistics=<br />
*Venue: The Lodge at Deer Valley Resort<br />
*Hotel reservations. $125/night. Make reservations by filling out and mailing/faxing this [[:File:DV_lodge_hotel.pdf|form]].<br />
*Fee $250.00 to cover breakfasts, lunches, and room fees. Please register [https://umarket.utah.edu/ecom/checkout.tpl?App_Type=0046&Item_Num=NAMICC1R here]</div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2012.pptx&diff=73369File:NAMIC-AHM-MIT-2012.pptx2012-01-12T16:16:55Z<p>Polina: uploaded a new version of "File:NAMIC-AHM-MIT-2012.pptx"</p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2012.pptx&diff=73316File:NAMIC-AHM-MIT-2012.pptx2012-01-12T05:09:11Z<p>Polina: uploaded a new version of "File:NAMIC-AHM-MIT-2012.pptx"</p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2012.pptx&diff=73129File:NAMIC-AHM-MIT-2012.pptx2012-01-10T03:19:11Z<p>Polina: uploaded a new version of "File:NAMIC-AHM-MIT-2012.pptx"</p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=AHM_2012&diff=73128AHM 20122012-01-10T03:10:41Z<p>Polina: /* Agenda */</p>
<hr />
<div> Back to [[Events]]<br />
[[Image:PW-SLC2012.png|300px]]<br />
<br />
January 9-13, 2012, Salt Lake City, Utah<br />
== Introduction ==<br />
{| border="00" cellpadding="8" cellspacing="0"<br />
|-<br />
| rowspan="2" align="left" | '''This is the home page for the 2012 NA-MIC all hands meeting (AHM).''' NA-MIC participants meet for a AHM once a year. The purpose of the AHM is to coordinate, discuss plans and report to NIH officers and the external advisory board (EAB). The external advisory board meets with the NA-MIC leadership immediately after the AHM. In parallel, NA-MIC is organizing a project week. These events, with the exception of the EAB meeting, are open to collaborators and potential collaborators.<br />
<br />
For more information about the project weeks in general, click [[Engineering:Programming_Events|'''here''']]. <br />
<br />
For information about the January 2012 project week, see below.<br />
<br />
For information about Utah as a travel destination click [http://www.utah.com '''here'''].<br />
| style="background: #ebeced" align="center"| [[Image:SLC.jpg|center|350px|View of the City]]<br />
|-<br />
| style="background: #ebeced"|The 2012 AHM, EAB and Project Week will be held <br>'''January 9-13, 2012''', in '''Salt Lake City''', Utah. <br />
|}<br />
<br />
== Dates, Venue, Registration ==<br />
{|<br />
|align="left" style="width:60%"|<br />
'''Dates:'''<br />
* The All Hands Meeting and External Advisory Board Meeting will be held on '''Thursday, January 12th'''. <br />
* Project Activities will be held rest of the week between '''Monday, January 9th and Friday, January 13th'''.<br />
<br />
'''Registration:''' Please click [http://www.sci.utah.edu/namic2012.html '''here'''] to register online before '''January 3, 2012'''. All participants must a pay registration fee ('''$200''' for AHM only, and '''$450''' for AHM+Project Week), which covers our catering and facilities costs.<br />
<br />
'''Venue:''' The venue for the meeting is the Marriott, Salt Lake City, Utah. Please either call the hotel at +1-801-961-8700 (toll free) and mention the group code "sciscia" or book online [http://www.marriott.com/hotels/travel/slccc-salt-lake-city-marriott-city-center/ '''here''']. Please note that '''''we need attendees to use this hotel''''' in order not to incur additional charges for use of the conference rooms and keep registration fees low. The group rate is $149/night + tax and is valid for reservations made until '''December 9'''. After that it is $229/night + tax.<br />
<br />
|style="width:40%" |[[image:Marriott-floorplan.png|thumb |250px|'''Meeting Rooms:''' See [http://www.marriott.com/hotels/event-planning/floor-plans/slccc-salt-lake-city-marriott-city-center/ here] for the web version.]]<br />
|}<br />
<br />
== Agenda== <br />
{| border="1" cellpadding="5"<br />
|- style="background:#eeeeee; font-size:125%; color:#0063B6" align="center" <br />
| style="width:5%"| '''Time'''<br />
| style="width:15%" | '''Monday, January 9''' <br />
| style="width:15%" | '''Tuesday, January 10'''<br />
| style="width:15%" | '''Wednesday, January 11''' <br />
| style="width:35%" | '''Thursday, January 12 '''<br />
| style="width:15%" | '''Friday, January 13''' <br />
|-<br />
| style="background:#eeeeee; color:black"|<br />
| style="background:#ffffff; color:#522200"| '''[[2012_Winter_Project_Week|Project Activities]] ''' <br><font color="#44AA88">''(Capitol BC)''</font><br />
| style="background:#dbf3ff; color:#522200"| '''[[2012_Winter_Project_Week|Project Activities]] '''<br><font color="#44AA88">''(Capitol BC)''</font><br />
| style="background:#dbf3ff; color:#522200"| '''[[2012_Winter_Project_Week|Project Activities]] ''' <br><font color="#44AA88">''(Capitol BC)''</font><br />
| style="background:#F2E5D3; color:#522200"| '''AHM''' <br><font color="#44AA88">''(Capitol ABC)''</font>, '''[http://wiki.na-mic.org/Wiki/index.php/2012_EAB EAB]'''<br />
| style="background:#dbf3ff; color:#522200"|'''[[2012_Winter_Project_Week|Project Activities]] ''' <br><font color="#44AA88">''(Capitol BC)''</font><br />
|-<br />
| style="background:#eeeeee; color:black"|'''7:30-8:00''' <br />
| style="background:#ffffff; color:black"| <br />
| style="background:#dbf3ff; color:black"| Breakfast <br><font color="#BB9933">''(Olympus A)''</font><br />
| style="background:#dbf3ff; color:black"| Breakfast <br><font color="#BB9933">''(Olympus A)''</font><br />
| style="background:#F2E5D3; color:black"| Breakfast <br><font color="#BB9933">''(Olympus A)''</font><br />
| style="background:#dbf3ff; color:black"| Breakfast <br><font color="#BB9933">''(Olympus A)''</font><br />
|-<br />
| style="background:#eeeeee; color:black"|'''8:00-10:00''' <br />
|'''9-10am''': [[AHM2012-DICOM-Huddle|DICOM General Breakout Session]] <br><font color="#9966cc">''(Amethyst)''</font><br />
|'''8-10am''': [[AHM2012-Slicer-Overview-and-Migration|Slicer 4: Overview and Migration]] (for Developers) <br><font color="#44AA88">''(Capitol A)''</font><br />
|[[AHM2012-3D-US-Slicer-Breakout|Breakout: 3D Ultrasound in Slicer]] (Noby Hata) <br><font color="#9966cc">''(Amethyst)''</font><br />
| '''8:05-9am''': Keynote: iDASH: Integrating Data for Analysis, Anonymization, and Sharing, Lucila Ohno-Machado, PhD, UCSD <br> '''9-10am''': Algorithms Core Update [[media:Bu.namic.ahm.zip|BU]], [[media:NAMIC-AHM-MIT-2012.pptx|MIT]], [[media:2012_01_UNC_Update.pptx|UNC]], [[media:2012_01_Ross-Utah_Update.pptx|Utah I]], [[media:UtahII-AHM2012-12Min.pptx|Utah II]]<br />
| style="background:#dbf3ff; color:#522200"|[[2012_Winter_Project_Week|Project Review]] <br><font color="#44AA88">''(Capitol BC)''</font><br />
|-<br />
| style="background:#eeeeee; color:black"|'''10:00-10:30'''<br />
| style="background:#ffffff; color:black"|<br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
| style="background:#F2E5D3; color:black"| Coffee <br>''(General area)''<br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
|-<br />
| style="background:#eeeeee; color:black"|'''10:30-12:00'''<br />
| Core and Site PIs meeting with Ron <br><font color="#44AA88">''(Capitol A)''</font><br />
| [[2012_Winter_Project_Week_SimpleITK_and_Slicer4|Breakout: SimpleITK and Slicer 4.0]] (Hans Johnson & Bradley Lowekamp) <br><font color="#9966cc">''(Amethyst)''</font><br />
| [[AHM2012-3D-US-Slicer-Breakout|Breakout: 3D Ultrasound in Slicer]] (Noby Hata) <br><font color="#9966cc">''(Amethyst)''</font><br />
| '''10:30-11:30am''': Engineering Core Update <br> '''11:30-12pm''': Outreach Update, Sonia Pujol<br />
|<br />
|-<br />
| style="background:#eeeeee; color:black"|'''12:00-1:00''' <br />
| style="background:#dbf3ff; color:black"| Lunch <br><font color="#BB9933">''(Olympus A)''</font><br />
| style="background:#dbf3ff; color:black"| Lunch <br><font color="#BB9933">''(Olympus A)''</font> <br> <br />
| style="background:#dbf3ff; color:black"| Lunch <br><font color="#BB9933">''(Olympus A)''</font><br> <br />
| style="background:#F2E5D3; color:black"| Lunch <br><font color="#BB9933">''(Olympus A)''</font><br />
| style="background:#dbf3ff; color:black"| Boxed Lunch and Adjourn <br><font color="#BB9933">''(Olympus A)''</font> <br />
|-<br />
| style="background:#eeeeee; color:black"|'''1:00-3:00'''<br />
| style="background:#dbf3ff; color:#522200"|[[2012_Winter_Project_Week|Project Presentations]]<br><font color="#44AA88">''(Capitol BC)''</font><br />
| [[2012_Winter_Project_Week_Slicer4_Module_Design_Breakout|Breakout: Slicer 4 Module Design with Individual Teams]] <br><font color="#44AA88">''(Capitol A)''</font><br />
|'''DBP Team Meetings''' <br><font color="#44AA88">''(Capitol A)''</font> <br> '''1-2pm''': [[2012_Winter_Project_Week_DBP_MGH_Team_Meeting|DBP MGH Head and Neck Cancer]] <br>'''2-3pm''': [[2012_Winter_Project_Week_DBP_Utah_Team_Meeting|DBP Utah Atrial Fibrillation]]<br />
| '''1-1:45pm''': International Research Organizations contribute to NA-MIC <br>'''1-1:30pm''': Best Practices from a Past DBP, Gabor Fichtinger, PhD, Queens University<br> '''Current DBP Updates''' <br> '''1:30pm''': Huntington's Disease, Hans Johnson, U Iowa <br> '''1:50pm''': Atrial Fibrillation, Rob McLeod, U Utah <br>''' 2:10pm''': Traumatic Brain Injury, Jack Van Horn, UCLA<br> '''2:30pm''': Head and Neck Cancer, Greg Sharp, MGH<br />
|<br />
|-<br />
| style="background:#eeeeee; color:black"|'''3:00-3:30''' <br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
| style="background:#dbf3ff; color:black"| Coffee <br>''(General area)''<br />
| style="background:#F2E5D3; color:black"| Coffee <br>''(General area)''<br />
| style="background:#ffffff; color:black"|<br />
|-<br />
| style="background:#eeeeee; color:black"|'''3:00-5:00''' <br />
|[[AHM2012-Slicer-with-Ron|Breakout: Slicer 4 with Ron (for Users)]] <br><font color="#44AA88">''(Capitol A)''</font><br />
| [[2012_Winter_Project_Week_DICOM_RT_Breakout|Breakout: DICOM RT]] <br><font color="#9966cc">''(Amethyst)''</font><br />
|'''DBP Team Meetings''' <br><font color="#44AA88">''(Capitol A)''</font> <br> '''3-4pm''': [[2012_Winter_Project_Week_DBP_UCLA_Team_Meeting|DBP UCLA Traumatic Brain Injury]] <br>'''4-5pm''': [[2012_Winter_Project_Week_DBP_Iowa_Team_Meeting|DBP Iowa Huntington's Disease]]<br />
|'''3-4pm''': [[2012_EAB|EAB meeting]] <br><font color="#9966cc">''(Amethyst)''</font><br> '''4-5pm:''' EAB closed session <br><font color="#9966cc">''(Amethyst)''</font><br />
| style="background:#ffffff; color:black"|<br />
|-<br />
| style="background:#eeeeee; color:black"|'''05:00-07:00''' <br />
| style="background:#dbf3ff; color:black"|<br />
| style="background:#dbf3ff; color:black"|<br />
| style="background:#dbf3ff; color:black"|<br />
| style="background:#F2E5D3; color:black"|'''6:00''' Optional: [http://www.murphysbarandgrillut.com/ Beer at Murphy's] (like last year)<br />
| style="background:#ffffff; color:black"| <br />
|}<br />
<br />
'''General Announcements:'''<br />
<br />
**Will be added here<br />
<br />
==Registered Attendees==<br />
<br />
<big>'''NOTE:'''</big> <font color="maroon">The registered attendee list will be posted here by the organizers. '''DO NOT''' add your name to this list yourself.</font> To register, please click [http://www.sci.utah.edu/namic2012-registration.html here].<br />
<br />
# Ackerman Michael , National Library of Medicine, NIH, OHPPC<br />
# Aucoin Nicole , BWH<br />
# Aylward Stephen , Kitware<br />
# Baumgartner Christian , Psychiatry Neuroimaging Lab - BWH Boston<br />
# Berger Jean-Baptiste , <br />
# Blezek Daniel Mayo Clinic<br />
# Blumenfeld Morry , Brigham and Womens Hospital<br />
# Blumfield Anthony , Radnostics<br />
# Bowers Michael , Johns Hopkins University<br />
# Cates Josh , University of Utah<br />
# Chambers Micah , UCLA<br />
# Chapman Brian , University of California, San Diego<br />
# Chauvin Laurent , BWH<br />
# Chen Xiaojun , Surgical Plan Lab,Brigham Womens Hospital<br />
# Chen Elvis , Robarts Research Institute<br />
# Datar Manasi , SCI Institute<br />
# Diedrich Karl , AZE Research and Development<br />
# Egger Jan , SPL, BWH, HMS<br />
# Fedorov Andriy , BWH<br />
# Fichtinger Gabor , Queens University<br />
# Fillion-Robin Jean-Christophe , Kitware<br />
# Finet Julien , Kitware<br />
# Fishbaugh James , SCI Institute<br />
# Gao Yi , Brigham And Womens Hospital<br />
# Gardner Greg , SCI Institute<br />
# George Ashvin , SCI Institute<br />
# Gerig Guido , SCI Institute<br />
# Ghosh Satrajit , Isomics, Inc.<br />
# Golland Polina , MIT<br />
# Gouaillard Alexandre , CoSMo Software<br />
# Hata Nobuhiko , BWH<br />
# Iftekharuddin Khan , Old Dominion University<br />
# Irimia Andrei , University of California, Los Angeles<br />
# Johnson Chris , EAB, Chair<br />
# Johnson Hans , University of Iowa<br />
# Kalpathy-Cramer Jayashree , MGH<br />
# Kikinis Ron , Brigham and Womens Hospital<br />
# Kim Eun Young Regina , University of Iowa<br />
# Kochis Donna Kitware<br />
# Kolesov Ivan , Georgia Institute of Technology<br />
# Lasso Andras , Queens University<br />
# Long Benjamin , Kitware<br />
# Lorensen Bill , Brigham and Womens Hospital<br />
# Lou Yifei , Georgia Tech<br />
# Lowekamp Bradley , <br />
# MacLeod Rob , SCI Institute<br />
# Marcus Daniel , Washington University<br />
# Matsui Joy , University of Iowa<br />
# Milchenko Mikhail , Washington University in St. Louis<br />
# Miller James , GE Research<br />
# Montillo Albert , GE<br />
# Moradi Mehdi , BWH Harvard Medical School<br />
# Morris Alan , SCI Institute<br />
# Napel Sandy , Brigham and Womens Hospital<br />
# Norton Isaiah , Brigham Womens Hospital<br />
# Oguz Ipek , UNC<br />
# Ohno-Machado Lucila , Plenary Speaker<br />
# Pace Danielle , Kitware<br />
# Paniagua Beatriz , University of North Carolina at Chapel Hill<br />
# Patel Pratik , Brainlab<br />
# Perry Daniel , SCI Institute<br />
# Pieper Steve , Isomics, Inc.<br />
# Pierpaoli Carlo , EAB<br />
# Pinter Csaba , Queens University<br />
# Pohl Kilian , UPEN<br />
# Prior Fred , Brigham and Womens Hospital<br />
# Roger Gwendoline , UNC<br />
# Ryan William , Mayo Clinic<br />
# Savadjiev Peter , Brigham and Womens Hospital<br />
# Schroeder William , Kitware<br />
# Shackleford James , MGH<br />
# Sharma Anuja , SCI Institute<br />
# Sharp Gregory , MGH<br />
# Shusharina Nadya , <br />
# Scully Mark , University of Iowa<br />
# Sridharan Ramesh , MIT CSAIL<br />
# Styner Martin , University of North Carolina<br />
# Tannenbaum Allen , Boston University<br />
# Tibrewal Radhika , BWH<br />
# Toews Matthew , BWH HMS<br />
# Tokuda Junichi , BWH<br />
# Tustison Nick , University of Virginia<br />
# Ungi Tamas , Queens University<br />
# Vachet Clement , UNC Chapel Hill<br />
# Van Horn John , UCLA<br />
# Veeraraghavan Harini , General Electric Research<br />
# Veni Gopalkrishna , SCI Institute<br />
# Wachinger Christian , MIT CSAIL<br />
# Wang Kevin , University Health Network<br />
# Wang Bo , SCI Institute<br />
# Wasem Andrew , CoSMo Software<br />
# Wasserman Demian , Brigham and Womens Hospital<br />
# Wedlake Chris , Robarts Research Institute<br />
# Welch Dave , University of Iowa<br />
# Whitaker Ross , SCI Institute<br />
# Yarmarkovich Alexander , Isomics<br />
# Yeniaras Erol , MD Anderson Cancer Center<br />
# Yoo Terry , National Libraray of Medicine at NIH, OHPCC<br />
# Zhu Liangjia , Georgia Institute of Technology<br />
# zhu yingxuan , GE Global Research<br />
# Zygmunt Kris , SCI Institute<br />
<br />
<br />
<br />
<br />
<br />
as of January 5, 2012 9:30 AM MST</div>Polinahttps://www.na-mic.org/w/index.php?title=File:NAMIC-AHM-MIT-2012.pptx&diff=73127File:NAMIC-AHM-MIT-2012.pptx2012-01-10T03:08:26Z<p>Polina: </p>
<hr />
<div></div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=71627Algorithm:MIT2011-10-31T19:07:34Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
<font color="red">'''New: '''</font> B. Menze, K. Van Leemput, A. Honkela, E. Konukoglu, M.A. Weber, N. Ayache and P.A. Golland. A generative approach for image-based modeling of tumor growth. In Proc. IPMI: Information Processing in Medical Imaging, LNCS 6801:735-747, 2011. <br />
<br />
<br />
|-<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Dalca, G. Danagoulian, R. Kikinis, E. Schmidt, and P. Golland. Segmentation of Nerve Bundles and Ganglia in Spine MRI Using Particle Filters. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 6893:537, 2011. <br />
<br />
|-<br />
<br />
<br />
|| [[Image: JointEM_Func_p05_10000.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:BrainConnectivity|Brain Connectivity]] ==<br />
Our goal is to use measures of connectivity between various ROIs as an avenue for understanding the structural and functional organization of the brain. We assess functional and anatomical connectivity using both fMRI correlations and DWI tractography measures, respectively. [[Projects:BrainConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. To appear in IEEE Transactions on Medical Imaging, 2011. <br />
<br />
|-<br />
<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, D. Lashkari, A. Sweet, Y. Tie, L. Rigolo, A.J. Golby, and P. Golland. Learning an Atlas of a Cognitive Process via Functional Geometry. In Proc. IPMI: International Conference on Information Processing and Medical Imaging, 6801:135-146, 2011.<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, B.H. Menze, D. Lashkari, and P. Golland. Detecting Stable Distributed Patterns of Brain Activation Using Gini Contrast. NeuroImage, 56(2):497-507, 2011.<br />
<br />
|-<br />
<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=71626Algorithm:MIT2011-10-31T19:06:42Z<p>Polina: /* Brain Tumor Segmentation and Modeling */</p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
<font color="red">'''New: '''</font> B. Menze, K. Van Leemput, A. Honkela, E. Konukoglu, M.A. Weber, N. Ayache and P.A. Golland. A generative approach for image-based modeling of tumor growth. In Proc. IPMI: Information Processing in Medical Imaging, LNCS 6801:735-747, 2011. <br />
<br />
<br />
|-<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, D. Lashkari, A. Sweet, Y. Tie, L. Rigolo, A.J. Golby, and P. Golland. Learning an Atlas of a Cognitive Process via Functional Geometry. In Proc. IPMI: International Conference on Information Processing and Medical Imaging, 6801:135-146, 2011.<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, B.H. Menze, D. Lashkari, and P. Golland. Detecting Stable Distributed Patterns of Brain Activation Using Gini Contrast. NeuroImage, 56(2):497-507, 2011.<br />
<br />
|-<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Dalca, G. Danagoulian, R. Kikinis, E. Schmidt, and P. Golland. Segmentation of Nerve Bundles and Ganglia in Spine MRI Using Particle Filters. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 6893:537, 2011. <br />
<br />
|-<br />
<br />
<br />
|| [[Image: JointEM_Func_p05_10000.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:BrainConnectivity|Brain Connectivity]] ==<br />
Our goal is to use measures of connectivity between various ROIs as an avenue for understanding the structural and functional organization of the brain. We assess functional and anatomical connectivity using both fMRI correlations and DWI tractography measures, respectively. [[Projects:BrainConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. To appear in IEEE Transactions on Medical Imaging, 2011. <br />
<br />
|-<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=Algorithm:MIT&diff=71625Algorithm:MIT2011-10-31T19:05:43Z<p>Polina: </p>
<hr />
<div> Back to [[Algorithm:Main|NA-MIC Algorithms]]<br />
__NOTOC__<br />
= Overview of MIT Algorithms (PI: Polina Golland) =<br />
<br />
Our group seeks to model statistical variability of anatomy and function across subjects and between populations and to utilize computational models of such variability to improve predictions for individual subjects, as well as characterize populations. Our long-term goal is to develop methods for joint modeling of anatomy and function and to apply them in clinical and scientific studies. We work primarily with anatomical, DTI and fMRI images. We actively contribute implementations of our algorithms to the NAMIC-kit.<br />
<br />
= MIT Projects =<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
<br />
<br />
|| [[Image:Segmentation_example2.png|250px]]<br />
||<br />
<br />
== [[Projects:NonparametricSegmentation| Nonparametric Models for Supervised Image Segmentation]] ==<br />
<br />
We propose a non-parametric, probabilistic model for the automatic segmentation of medical images,<br />
given a training set of images and corresponding label maps. The resulting inference algorithms we<br />
develop rely on pairwise registrations between the test image and individual training images. The<br />
training labels are then transferred to the test image and fused to compute a final segmentation of<br />
the test subject. [[Projects:NonparametricSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
|| [[Image:Mdepa_scar_DE-MRI_projection.png| 250px]]<br />
||<br />
<br />
== [[Projects:CardiacAblation | Segmentation and Visualization for Cardiac Ablation Procedures]] ==<br />
<br />
Catheter radio-frequency (RF) ablation is a technique used to treat atrial fibrillation, a very common heart condition. The objective of this project is to provide automatic segmentation and visualization tools to aid in the planning and outcome evaluation of cardiac ablation procedures. Specifically, we develop methods for the automatic segmentation of the left atrium of the heart and visualization of the ablation scars resulting from the procedure in clinical MR images.<br />
[[Projects:CardiacAblation|More...]]<br />
<br />
<font color="red">'''New: '''</font> M. Depa, G. Holmvang, E.J. Schmidt, P. Golland and M.R. Sabuncu. Towards Efficient Label Fusion by Pre-Alignment of Training Data. In Proc. MICCAI Workshop on Multi-atlas Labeling and Statistical Fusion, 38-46, 2011. <br />
<br />
<br />
|-<br />
<br />
<br />
| | [[Image:BjoernTumor3.png|center|200px]]<br />
| |<br />
<br />
== [[Projects:TumorModeling|Brain Tumor Segmentation and Modeling]] ==<br />
<br />
We are interested in developing computational methods for the assimilation of magnetic resonance image data into physiological models of glioma - the most frequent primary brain tumor - for a patient-adaptive modeling of tumor growth. [[Projects:TumorModeling|More...]]<br />
<br />
<font color="red">'''New: '''</font> B. Menze, K. Van Leemput, A. Honkela, E. Konukoglu, M.A. Weber, N. Ayache and P.A. Golland. A generative approach for image-based modeling of tumor growth. To appear in Proc. IPMI: Information Processing in Medical Imaging, 2011.<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Atlas_OneCluster.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:ConnectivityAtlas| Functional connectivity atlases and tumors]] ==<br />
We learn an atlas of the functional connectivity structure that emerges during a cognitive process from a group of individuals. The atlas is a group-wise generative model that describes the fMRI responses of all subjects in the embedding space. The atlas is not directly coupled to the anatomical space, and can represent functional networks that are variable in their spatial distribution.<br />
[[Projects:ConnectivityAtlas|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, D. Lashkari, A. Sweet, Y. Tie, L. Rigolo, A.J. Golby, and P. Golland. Learning an Atlas of a Cognitive Process via Functional Geometry. In Proc. IPMI: International Conference on Information Processing and Medical Imaging, 6801:135-146, 2011.<br />
<br />
|-<br />
<br />
| | [[Image:GiniContrast_Icon.png|center| 150px]]<br />
| |<br />
<br />
== [[Projects:GiniContrast| Multi-variate activation detection]] ==<br />
We study and demonstrate the benefits of Random Forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a mul- tivariate neural response. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead it uses the predictive power of features to characterize their relevance for encoding task information. <br />
[[Projects:GiniContrast|More...]]<br />
<br />
<font color="red">'''New: '''</font> G. Langs, B.H. Menze, D. Lashkari, and P. Golland. Detecting Stable Distributed Patterns of Brain Activation Using Gini Contrast. NeuroImage, 56(2):497-507, 2011.<br />
<br />
|-<br />
<br />
| | [[Image:NerveSegRes1.jpg|center| 200px]]<br />
| |<br />
<br />
== [[Projects:NerveSegmentation|Segmentation of Nerve and Nerve Ganglia in the Spine]] ==<br />
Automatic segmentation of neural tracts in the dural sac and outside of the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves in high resolution MR images makes segmentation a challenging task. [[Projects:NerveSegmentation|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Dalca, G. Danagoulian, R. Kikinis, E. Schmidt, and P. Golland. Segmentation of Nerve Bundles and Ganglia in Spine MRI Using Particle Filters. In Proc. MICCAI: International Conference on Medical Image Computing and Computer Assisted Intervenion, LNCS 6893:537, 2011. <br />
<br />
|-<br />
<br />
<br />
|| [[Image: JointEM_Func_p05_10000.png|center| 200px]]<br />
| |<br />
<br />
== [[Projects:BrainConnectivity|Brain Connectivity]] ==<br />
Our goal is to use measures of connectivity between various ROIs as an avenue for understanding the structural and functional organization of the brain. We assess functional and anatomical connectivity using both fMRI correlations and DWI tractography measures, respectively. [[Projects:BrainConnectivity|More...]]<br />
<br />
<font color="red">'''New: '''</font> A. Venkataraman, Y. Rathi, M. Kubicki, C.-F. Westin, and P. Golland. Joint Modeling of Anatomical and Functional Connectivity for Population Studies. To appear in IEEE Transactions on Medical Imaging, 2011. <br />
<br />
|-<br />
<br />
| | [[Image:Namic wiki.png|200px]]<br />
| |<br />
<br />
== [[Projects:QuantitativeSusceptibilityMapping| Quantitative Susceptibility Mapping ]] ==<br />
<br />
There is increasing evidence that excessive iron deposition in specific regions<br />
of the brain is associated with neurodegenerative disorders such as Alzheimer's<br />
and Parkinson's disease. The role of iron in the pathogenesis of these diseases<br />
remains unknown and is difficult to determine without a non-invasive method<br />
to quantify its concentration in-vivo. Since iron is a ferromagnetic substance,<br />
changes in iron concentration result in local changes in the magnetic susceptibility of tissue. <br />
In magnetic resonance imaging (MRI) experiments, differences<br />
in magnetic susceptibility cause perturbations in the local magnetic field, which<br />
can be computed from the phase of the MR signal. [[Projects:QuantitativeSusceptibilityMapping|More...]]<br />
<br />
<font color="red">'''New: '''</font> Poynton C., Wells W. A Variational Approach to Susceptibility Estimation That is Insensitive to B0 Inhomogeneity. In Proc. ISMRM: International Society of Magnetic Resonance in Medicine, 2011.<br />
<br />
|-<br />
| | [[Image:TGIt.gif|center| 150px]]<br />
| |<br />
<br />
== [[Projects:LatentAtlasSegmentation|Joint Segmentation of Image Ensembles via Latent Atlases]] ==<br />
<br />
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. The atlases are typically generated by averaging manual labels of aligned brain regions across different subjects. However, the availability of comprehensive, reliable and suitable manual segmentations is limited. We therefore propose a joint segmentation of corresponding, aligned structures in the entire population that does not require a probability atlas. <br />
[[Projects:LatentAtlasSegmentation|More...]]<br />
<br />
|-<br />
<br />
<br />
{| cellpadding="10" style="text-align:left;"<br />
|| [[Image:lh.pm14686.BA2.gif|250px]]<br />
||<br />
<br />
== [[Projects:LearningRegistrationCostFunctions| Learning Task-Optimal Registration Cost Functions]] ==<br />
<br />
We present a framework for learning the parameters of registration cost functions. The parameters of the registration cost function -- for example, the tradeoff between the image similarity and regularization terms -- are typically determined manually through inspection of the image alignment and then fixed for all applications. We propose a principled approach to learn these parameters with respect to particular applications. [[Projects:LearningRegistrationCostFunctions|More...]] <br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:CoordinateChart.png|250px]]<br />
| |<br />
<br />
== [[Projects:SphericalDemons|Spherical Demons: Fast Surface Registration]] ==<br />
<br />
We present the fast Spherical Demons algorithm for registering two spherical images. By exploiting spherical vector spline interpolation theory, we show that a large class of regularizers for the modified demons objective function can be efficiently approximated on the sphere using convolution. Based on the one parameter subgroups of diffeomorphisms, [[Projects:SphericalDemons|More...]]<br />
<br />
<br />
|-<br />
<br />
<br />
<br />
<br />
| | [[Image:mit_fmri_clustering_parcellation2_xsub.png|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIClustering|Improving fMRI Analysis using Supervised and Unsupervised Learning]] ==<br />
<br />
One of the major goals in the analysis of fMRI data is the detection of networks in the brain with similar functional behavior. A wide variety of methods including hypothesis-driven statistical tests, supervised, and unsupervised learning methods have been employed to find these networks. In this project, we develop novel learning algorithms that enable more efficient inferences from fMRI measurements. [[Projects:fMRIClustering|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:FMRIEvaluationchart.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:fMRIDetection|fMRI Detection and Analysis]] ==<br />
<br />
We are exploring algorithms for improved fMRI detection and interpretation by incorporting spatial priors and anatomical information to guide the detection. [[Projects:fMRIDetection|More...]]<br />
<br />
|-<br />
<br />
<br />
| | [[Image:epi_correction_small.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:FieldmapFreeDistortionCorrection|Fieldmap-Free EPI Distortion Correction]] ==<br />
<br />
In this project we aim to improve the EPI distortion correction algorithms. [[Projects:FieldmapFreeDistortionCorrection|More...]]<br />
<br />
|-<br />
<br />
{| cellpadding="10" style="text-align:left;" <br />
|| [[Image:TetrahedralAtlasWarp.gif |250px]]<br />
||<br />
<br />
== [[Projects:BayesianMRSegmentation| Bayesian Segmentation of MRI Images]] ==<br />
<br />
The aim of this project is to develop, implement, and validate a generic method for segmenting MRI images that automatically adapts to different acquisition sequences. [[Projects:BayesianMRSegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ICluster_templates.gif|250px]]<br />
| |<br />
<br />
== [[Projects:MultimodalAtlas|Multimodal Atlas]] ==<br />
<br />
In this work, we propose and investigate an algorithm that jointly co-registers a collection of images while computing multiple templates. The algorithm, called '''iCluster''', is used to compute multiple atlases for a given population.<br />
[[Projects:MultimodalAtlas|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:GroupwiseSummary.PNG|200px]]<br />
| |<br />
<br />
== [[Projects:GroupwiseRegistration|Groupwise Registration]] ==<br />
<br />
We extend a previously demonstrated entropy based groupwise registration method to include a free-form deformation model based on B-splines. We provide an efficient implementation using stochastic gradient descents in a multi-resolution setting. We demonstrate the method in application to a set of 50 MRI brain scans and compare the results to a pairwise approach using segmentation labels to evaluate the quality of alignment.<br />
<br />
In a related project, we develop a method that reconciles the practical advantages of symmetric registration with the asymmetric nature of image-template registration by adding a simple correction factor to the symmetric cost function. We instantiate our model within a log-domain diffeomorphic registration framework. Our experiments show exploiting the asymmetry in image-template registration improves alignment in the image coordinates. [[Projects:GroupwiseRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:JointRegSeg.png|200px]]<br />
| |<br />
<br />
== [[Projects:RegistrationRegularization|Optimal Atlas Regularization in Image Segmentation]] ==<br />
<br />
We propose a unified framework for computing atlases from manually labeled data sets at various degrees of “sharpness” and the joint registration and segmentation of a new brain with these atlases. Using this framework, we investigate the tradeoff between warp regularization and image fidelity, i.e. the smoothness of the new subject warp and the sharpness of the atlas in a segmentation application.<br />
[[Projects:RegistrationRegularization|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:FoldingSpeedDetection.png|150px|]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysisWithOvercompleteWavelets|Shape Analysis With Overcomplete Wavelets]] ==<br />
<br />
In this work, we extend the Euclidean wavelets to the sphere. The resulting over-complete spherical wavelets are invariant to the rotation of the spherical image parameterization. We apply the over-complete spherical wavelet to cortical folding development [[Projects:ShapeAnalysisWithOvercompleteWavelets|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Models.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIModeling|Fiber Tract Modeling, Clustering, and Quantitative Analysis]] ==<br />
<br />
The goal of this work is to model the shape of the fiber bundles and use this model description in clustering and statistical analysis of fiber tracts. [[Projects:DTIModeling|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:Progress_Registration_Segmentation_Shape.jpg|180px]]<br />
| |<br />
<br />
== [[Projects:ShapeBasedSegmentationAndRegistration|Shape Based Segmentation and Registration]] ==<br />
<br />
This type of algorithm assigns a tissue type to each voxel in the volume. Incorporating prior shape information biases the label assignment towards contiguous regions that are consistent with the shape model. [[Projects:ShapeBasedSegmentationAndRegistration|More...]]<br />
<br />
<br />
<br />
|-<br />
<br />
| | [[Image:MIT_DTI_JointSegReg_atlas3D.jpg|200px]]<br />
| |<br />
<br />
== [[Projects:DTIFiberRegistration|Joint Registration and Segmentation of DWI Fiber Tractography]] ==<br />
<br />
The goal of this work is to jointly register and cluster DWI fiber tracts obtained from a group of subjects. [[Projects:DTIFiberRegistration|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:brain.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIClustering|DTI Fiber Clustering and Fiber-Based Analysis]] ==<br />
<br />
The goal of this project is to provide structural description of the white matter architecture as a partition into coherent fiber bundles and clusters, and to use these bundles for quantitative measurement. [[Projects:DTIClustering|More...]]<br />
<br />
<br />
|-<br />
<br />
| | [[Image:Thalamus_algo_outline.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTISegmentation|DTI-based Segmentation]] ==<br />
<br />
Unlike conventional MRI, DTI provides adequate contrast to segment the thalamic nuclei, which are gray matter structures. [[Projects:DTISegmentation|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:ConnectivityMap.png|200px]]<br />
| |<br />
<br />
== [[Projects:DTIStochasticTractography|Stochastic Tractography]] ==<br />
<br />
This work calculates posterior distributions of white matter fiber tract parameters given diffusion observations in a DWI volume. [[Projects:DTIStochasticTractography|More...]]<br />
<br />
|-<br />
<br />
| | [[Image:HippocampalShapeDifferences.gif|200px]]<br />
| |<br />
<br />
== [[Projects:ShapeAnalysis|Population Analysis of Anatomical Variability]] ==<br />
<br />
Our goal is to develop mathematical approaches to modeling anatomical variability within and across populations using tools like local shape descriptors of specific regions of interest and global constellation descriptors of multiple ROI's. [[Projects:ShapeAnalysis|More...]]<br />
<br />
|}</div>Polinahttps://www.na-mic.org/w/index.php?title=2011_Algorithms_Retreat&diff=713542011 Algorithms Retreat2011-10-14T17:10:40Z<p>Polina: </p>
<hr />
<div> [[Events#2011|Back to events page]]<br />
<br />
*October 14-15, 2011<br />
*Wylie Inn - Beverly, MA: http://www.wyliecenter.com<br />
<br />
=Agenda=<br />
==Friday==<br />
*9:00am--12:00pm (with break)<br />
**DBP discussions. Updates on progress and status including people, software, data, algorithms.<br />
***Afib (Ross, Allen)<br />
***Head&Neck Cancer (Polina)<br />
***Huntington's (Martin)<br />
***TBI (Guido)<br />
***Discussions of logistics with DBPs<br />
*12:pm-1:30pm - Lunch<br />
*1:30pm-5:pm (with break) - Technical presentations (10-20mins each + discussions):<br />
**Shape Growth Trajectories from Time Series Data (James, Guido)<br />
**Patient-specific segmentation of longitudinal multi-channel MRI in TBI (Bo Wang,Guido)<br />
**Spatiotemporal anatomical models via 4D segmentation (Marcel, Suyash, Guido, ..)<br />
**Shape Correspondence (Manasi Datar)<br />
**UNC update (Martin Styner) including<br />
*** DTI QC using directional entropy<br />
*** DTI Tensor calibration for registration<br />
*** Entropy over normals for particle correspondence<br />
*** Human brain like DTI phantom for evaluating tractography<br />
*** Atlas based DTI fiber tract analysis tools for Slicer<br />
**NonParametric Segmentation (Amelia Arbisser, Christian Wachinger, Polina Golland)<br />
**Images Spaces (Ramesh Sridharan, Adrian Dalca, Polina Golland)<br />
**Joint modeling of anatomical and functional connectivity (Archana Venkataraman, Polina Golland)<br />
**"What I am doing for NA-MIC" : Overviews from PIs and Distinguished Guests<br />
<br />
*Dinner at Capt. Carlo's, reservation for 7pm<br />
27-29 Harbor Loop<br />
Gloucester, MA 01930<br />
Phone: (978) 283-6342<br />
www.captcarlo.com<br />
<br />
==Saturday==<br />
*8:00am--9:00am: Discussion of Core 1 logistics/organization (and NAMIC)<br />
*9:00am--12:00pm: Discussion of future plans. Some of the options are:<br />
**competitive renewal (currently not an option, some discussions at NIH).<br />
**smaller grants: sliced vertically or horizontally<br />
<br />
=Attendees=<br />
* Ross Whitaker (Utah)<br />
* Manasi Datar (Utah)<br />
* Guido Gerig (Utah)<br />
* James Fishbaugh (Utah)<br />
* Ron Kikinis (BWH SPL)<br />
* Marc Niethammer (UNC)<br />
* Martin Styner (UNC)<br />
* Alan Tannenbaum (GA Tech)<br />
* Sandy Wells (BWH SPL)<br />
* Polina Golland (MIT)<br />
* Adrian Dalca (MIT)<br />
* Ramesh Sridharan (MIT)<br />
* Christian Wachinger (MIT)<br />
* Fern DeOliveira (MIT)</div>Polinahttps://www.na-mic.org/w/index.php?title=2011_Algorithms_Retreat&diff=713532011 Algorithms Retreat2011-10-14T17:09:17Z<p>Polina: </p>
<hr />
<div> [[Events#2011|Back to events page]]<br />
<br />
*October 14-15, 2011<br />
*Wylie Inn - Beverly, MA: http://www.wyliecenter.com<br />
<br />
=Agenda=<br />
==Friday==<br />
*9:00am--12:00pm (with break)<br />
**DBP discussions. Updates on progress and status including people, software, data, algorithms.<br />
***Afib (Ross, Allen)<br />
***Head&Neck Cancer (Polina)<br />
***Huntington's (Martin)<br />
***TBI (Guido)<br />
***Discussions of logistics with DBPs<br />
*12:pm-1:30pm - Lunch<br />
*1:30pm-5:pm (with break) - Technical presentations (10-20mins each + discussions):<br />
**Shape Growth Trajectories from Time Series Data (James, Guido)<br />
**Patient-specific segmentation of longitudinal multi-channel MRI in TBI (Bo Wang,Guido)<br />
**Spatiotemporal anatomical models via 4D segmentation (Marcel, Suyash, Guido, ..)<br />
**Shape Correspondence (Manasi Datar)<br />
**UNC update (Martin Styner) including<br />
*** DTI QC using directional entropy<br />
*** DTI Tensor calibration for registration<br />
*** Entropy over normals for particle correspondence<br />
*** Human brain like DTI phantom for evaluating tractography<br />
*** Atlas based DTI fiber tract analysis tools for Slicer<br />
**NonParametric Segmentation (Amelia Arbisser, Christian Wachinger, Polina Golland)<br />
**Images Spaces (Ramesh Sridharan, Adrian Dalca, Polina Golland)<br />
**Joint modeling of anatomical and functional connectivity (Archana Venkataraman, Polina Golland)<br />
**"What I am doing for NA-MIC" : Overviews from PIs and Distinguished Guests<br />
<br />
*Dinner at Capt. Carlo's, reservation for 7pm<br />
27-29 Harbor Loop<br />
Gloucester, MA 01930<br />
Phone: (978) 283-6342<br />
www.www.captcarlo.com<br />
<br />
==Saturday==<br />
*8:00am--9:00am: Discussion of Core 1 logistics/organization (and NAMIC)<br />
*9:00am--12:00pm: Discussion of future plans. Some of the options are:<br />
**competitive renewal (currently not an option, some discussions at NIH).<br />
**smaller grants: sliced vertically or horizontally<br />
<br />
=Attendees=<br />
* Ross Whitaker (Utah)<br />
* Manasi Datar (Utah)<br />
* Guido Gerig (Utah)<br />
* James Fishbaugh (Utah)<br />
* Ron Kikinis (BWH SPL)<br />
* Marc Niethammer (UNC)<br />
* Martin Styner (UNC)<br />
* Alan Tannenbaum (GA Tech)<br />
* Sandy Wells (BWH SPL)<br />
* Polina Golland (MIT)<br />
* Adrian Dalca (MIT)<br />
* Ramesh Sridharan (MIT)<br />
* Christian Wachinger (MIT)<br />
* Fern DeOliveira (MIT)</div>Polinahttps://www.na-mic.org/w/index.php?title=2011_Algorithms_Retreat&diff=713432011 Algorithms Retreat2011-10-14T13:22:29Z<p>Polina: /* Friday */</p>
<hr />
<div> [[Events#2011|Back to events page]]<br />
<br />
*October 14-15, 2011<br />
*Wylie Inn - Beverly, MA: http://www.wyliecenter.com<br />
<br />
=Agenda=<br />
==Friday==<br />
*9:00am--12:00pm (with break)<br />
**DBP discussions. Updates on progress and status including people, software, data, algorithms.<br />
***Afib (Ross, Allen)<br />
***Head&Neck Cancer (Polina)<br />
***Huntington's (Martin)<br />
***TBI (Guido)<br />
***Discussions of logistics with DBPs<br />
*12:pm-1:30pm - Lunch<br />
*1:30pm-5:pm (with break) - Technical presentations (10-20mins each + discussions):<br />
**Shape Growth Trajectories from Time Series Data (James, Guido)<br />
**Patient-specific segmentation of longitudinal multi-channel MRI in TBI (Bo Wang,Guido)<br />
**Spatiotemporal anatomical models via 4D segmentation (Marcel, Suyash, Guido, ..)<br />
**Shape Correspondence (Manasi Datar)<br />
**DTI QC using directional entropy (Martin Styner)<br />
**DTI Tensor calibration for registration (Martin Styner)<br />
**Entropy over normals for particle correspondence (Martin Styner)<br />
**NonParametric Segmentation (Amelia Arbisser, Christian Wachinger, Polina Golland)<br />
**Images Spaces (Ramesh Sridharan, Adrian Dalca, Polina Golland)<br />
**Joint modeling of anatomical and functional connectivity (Archana Venkataraman, Polina Golland)<br />
**"What I am doing for NA-MIC" : Overviews from PIs and Distinguished Guests<br />
**TBD<br />
<br />
==Saturday==<br />
*8:00am--9:00am: Discussion of Core 1 logistics/organization (and NAMIC)<br />
*9:00am--12:00pm: Discussion of future plans. Some of the options are:<br />
**competitive renewal (currently not an option, some discussions at NIH).<br />
**smaller grants: sliced vertically or horizontally<br />
<br />
=Attendees=<br />
* Ross Whitaker (Utah)<br />
* Manasi Datar (Utah)<br />
* Guido Gerig (Utah)<br />
* James Fishbaugh (Utah)<br />
* Ron Kikinis (BWH SPL)<br />
* Marc Niethammer (UNC)<br />
* Martin Styner (UNC)<br />
* Alan Tannenbaum (GA Tech)<br />
* Sandy Wells (BWH SPL)<br />
* Polina Golland (MIT)<br />
* Adrian Dalca (MIT)<br />
* Ramesh Sridharan (MIT)<br />
* Christian Wachinger (MIT)<br />
* Fern DeOliveira (MIT)</div>Polinahttps://www.na-mic.org/w/index.php?title=2011_Algorithms_Retreat&diff=713422011 Algorithms Retreat2011-10-14T13:21:45Z<p>Polina: </p>
<hr />
<div> [[Events#2011|Back to events page]]<br />
<br />
*October 14-15, 2011<br />
*Wylie Inn - Beverly, MA: http://www.wyliecenter.com<br />
<br />
=Agenda=<br />
==Friday==<br />
*9:00am--12:00pm (with break)<br />
**DBP discussions. Updates on progress and status including people, software, data, algorithms.<br />
***Afib (Ross, Allen)<br />
***Head&Neck Cancer (Polina)<br />
***Huntington's (Martin)<br />
***TBI (Guido)<br />
***Discussions of logistics with DBPs<br />
*12:pm-1:30pm - Lunch<br />
*1:30pm-5:pm (with break) - Technical presentations (10-20mins each + discussions):<br />
**Shape Growth Trajectories from Time Series Data (James, Guido)<br />
**Patient-specific segmentation of longitudinal multi-channel MRI in TBI (Bo Wang,Guido)<br />
**Spatiotemporal anatomical models via 4D segmentation (Marcel, Suyash, Guido, ..)<br />
**Shape Correspondence (Manasi Datar)<br />
**DTI QC using directional entropy (Martin Styner)<br />
**DTI Tensor calibration for registration (Martin Styner)<br />
**Entropy over normals for particle correspondence (Martin Styner)<br />
**NonParametric Segmentation (Amelia Arbisser, Christian Wachinger, Polina Golland)<br />
**Images Spaces (Ramesh Sridharan, Adrian Dalca, Polina Golland)<br />
**"What I am doing for NA-MIC" : Overviews from PIs and Distinguished Guests<br />
**TBD<br />
<br />
==Saturday==<br />
*8:00am--9:00am: Discussion of Core 1 logistics/organization (and NAMIC)<br />
*9:00am--12:00pm: Discussion of future plans. Some of the options are:<br />
**competitive renewal (currently not an option, some discussions at NIH).<br />
**smaller grants: sliced vertically or horizontally<br />
<br />
=Attendees=<br />
* Ross Whitaker (Utah)<br />
* Manasi Datar (Utah)<br />
* Guido Gerig (Utah)<br />
* James Fishbaugh (Utah)<br />
* Ron Kikinis (BWH SPL)<br />
* Marc Niethammer (UNC)<br />
* Martin Styner (UNC)<br />
* Alan Tannenbaum (GA Tech)<br />
* Sandy Wells (BWH SPL)<br />
* Polina Golland (MIT)<br />
* Adrian Dalca (MIT)<br />
* Ramesh Sridharan (MIT)<br />
* Christian Wachinger (MIT)<br />
* Fern DeOliveira (MIT)</div>Polina