2017 Winter Project Week

From NAMIC Wiki
Revision as of 13:58, 9 December 2016 by Marianna (talk | contribs)
Jump to: navigation, search
Home < 2017 Winter Project Week

PW-Winter2017.png

Welcome to the web page for the 24th Project Week!

The 24th NA-MIC Project Week open source hackathon is being held during the week of January 9-13, 2017 at MIT. Please go through this page for information, and if you have questions, please contact Tina Kapur, PhD.

Logistics

  • Dates: January 9-13, 2017.
  • Location: MIT CSAIL, Cambridge, MA. (Rooms: Kiva, R&D)
  • REGISTRATION: Register here. Registration Fee: $330.
  • Hotel: Similar to previous years, no rooms have been blocked in a particular hotel.


Introduction

The National Alliance for Medical Image Computing (NAMIC), was founded in 2005 and chartered with building a computational infrastructure to support biomedical research as part of the NIH funded NCBC program. The work of this alliance has resulted in important progress in algorithmic research, an open source medical image computing platform 3D Slicer, enhancements to the underlying building blocks VTK, ITK, CMake, and 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 open source hackathon event called Project Week.

Project Week is a semi-annual open source hackathon which draws 60-120 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.

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.

Several funded projects use the Project Week as a place to convene and collaborate. These include NAC, NCIGT, QIICR, and OCAIRO.

A summary of all previous Project Events is available here.

This project week is an event endorsed by the MICCAI society.

Please make sure that you are on the NA-MIC Project Week mailing list

Conference Calls for Preparation

Domestic conference call number: 800-501-8979
Access code: 7327389

International conference call numbers
Access code: 7327389

Weekly, Tuesdays 10am, Boston time from November 22nd, 2016 to January 3rd, 2017.


Tcon #4: December 6

  • 10am Boston time
  • Project Discussions with focus on Machine Learning and Web-based software for clinical research/trials

Participants

  • Tina Kapur (MIT) - organizer
  • Steve Pieper (Isomics/BWH)
  • Beatriz, JC (Kitware)

Tcon #3: November 29

  • 10am Boston time
  • Project Discussions with focus on Machine Learning and Web-based software for clinical research/trials

Participants

  • Tina Kapur (MIT) - organizer; planning Nvidia webinars. Proposal to use Monday as a schedule for the deep learning workshop before workshop begins.
  • Steve Pieper (Isomics/BWH) - NVidia update; met with Abdul at NVidia (Medical applications of deep learning). Positive meeting and Slicer might be a reference platform. NVIdia will host a Monday Afternoon session at Project Week and hold outside webinars for basic deep learning information. Considering two or three days of a few hours each for webinar. Discussion of a prize board awarded for demonstrations that Nvidia could use.
  • Patmal (Univ. of Pennsylvania Biomedical Group) Showcase some of their capability: cancer & phenomics toolkit; facilitate integration from their toolkit to/from Slicer; They have a few applications that might be interesting to others during project week - (1) fibre tracking in brain, (2) lung tumor segmentation, (3) density estimation
  • Beatriz, Alexis, and JC (Kitware) - Slicer support and 3 other projects (1) customized childrern's medical, (1) Alex submitted volumetric meshing project in Slicer idea to the NA-MIC email list; have a discussion on Meshing; the goal is for Finite Element analsis and light imaging (2), better MATLAB integration (use Python-like interface). (3) Beatrix - shape analysis algorithms to be added to Slicer based on recently-funded grant.
  • JC (Kitware) - integration of iPython and Slicer; Tina Suggested also Deep Infer framework to integrate with Slicer
  • Louise Oram (Stockholm) - Specialization of Slicer for Liver surgery, possibly using SliceLet approach or other way to tailor the Slicer UI. Currently customizations need to be in the Extension catalog. Also interested in Liver vessel segmentation project and other Liver segmentation tasks. This might complement with MeVIS lab capability focused on liver. Separate modules for liver surgery that might be integrated together later.
  • Frank Pricework (BWH) - General GPU programming; experiment with rehosting algorithms has has previously developed to GPU.
  • Paolo, Italy - (Summer Project Week Host)
  • Naboo (Old Dominion) - two possible projects, not certain yet - (1) smaller training datasets for medical images, (2) braining atlas segmentation integration with Slicer.
  • Curt Lisle (KnowledgeVis) - (1) web-based transition of subset of Slicer capability, (2) Iowa Meshing Module move from 3.6 to 4.7 (with Alex from Kitware); (3) possible integration of web-based volume rendering;
  • Patmal (Univ. of Pennsylvania Biomedical Group) Showcase some of their capability: cancer & phenomics toolkit; facilitate integration from their toolkit to/from Slicer; They have a few applications that might be interesting to others during project week - (1) fibre tracking in brain, (2) lung tumor segmentation, (3) density estimation
  • Eric Seigler - OHIS Cornerstone Lesion Tracker author; Integrating interactive segmentation into the web-based framework

Discussions

  • Training deep learning networks with smaller datasets.
  • Integrating of projects with Slicer & architecture will be a discussion topic during the week.
  • Everybody, be sure to register on the Wiki for the workshop; come up with a title and short description of the project(s) you will work on.
  • OK to send info to the NA-MIC email list

Tcon #2: November 22

  • 10am Boston time
  • Topics: continue Deep Learning, Web-based software
  • Participants (interests)
  1. Tina Kapur, BWH (needle detection)
  2. Steve Pieper, Isomics (web-based software, GPU computing)
  3. Mahbub, Old Dominion University (creating architectures for deep learning networks in matlab, bridge to Slicer, MICCAI challenge code into Slicer, make learning faster and with less training)
  4. Siddiqi, Old Dominion
  5. Nicole Aucoin, BWH
  6. Abdul, NVIDIA Business Development (potential deep learning tutorials by web conference before the event, then at the event)
  7. Able Brown, NVIDIA
  8. JC, Kitware
  9. Krisztina Fischer, BWH
  10. Andrew Beard, MGH (deep learning, parameter estimation from MRI)
  11. Gordon Harris, MGH
  12. Laurent Chauvin, ETS Montreal (CNN, GPUs)
  13. John Toeber, Bremen U
  14. Lauren O'Donnell, BWH
  15. Fan Zhang, BWH
  16. Isaiah Norton, BWH
  17. Wu Ye, BWH
  18. Erik Siegler, MGH (Slicer / ePad connection with LesionTracker; more web-based technologies; discussion of ePad custom widget that will send out connections to remote jobs., PET/CT Lymphoma workshop as extension to lesion tracker.)
  19. Pete Anderson (Open source tracker)
  20. Guillaume Pernelle, Imperial College (CNNs, LSTMs, Deep Learning, GPUs)
  21. Mike Halle, BWH (slicer cross-platform architecture to work for hardware-specific; proxy running cloud that can support interface, Atlas browser is an active project for web-based interface. Slicer success is primarily application-level tools. The community could benefit with architectural study.)
  22. Louise, Oslo, Norway (high-speed pipelining of image processing for liver resections. )
  23. Paolo, Catanzaro, Italy (Multiple GPU system architecture)
  24. Salvatore, Catanzaro, Italy
  25. Daniel Rubin, Stanford
  26. Curt Lisle, Knowledgevis (has image web-based workflow systems; Deeply interested in web transition of imaging technologies. Also interested (but not experienced) in deep learning application; particularly feature recognition; small animal imaging applications)
  27. Charles Guttman, BWH (has MS data, wants to use Docker-based repository. (Boutique looks like a good repository)

Tcon #1: November 15

  • 10am Boston time
  • Emergent interest in the application of Deep Learning techniques to medical image analysis.

Participants and interests

    1. Tina Kapur, BWH -- needle detection
    2. Steve Pieper, Isomics - GPUs
    3. Andras Lasso, Queens - Slicer expert
    4. Frankie Preiswerk, BWH -- hybrid ultrasound and MRI, interested in NVIDIA workshop
    5. JC, Kitware -- Slicer expert
    6. Mike Halle, BWH -- image feature search using deep learning (w/ Sandy Wells)
    7. Peter Neher, DKFZ (filling in for Marco Nolden) -- experience with deep learning with face recognition
    8. Nicole Aucoin, BWH -- Slicer expert
    9. Alireza Mehrtash, UBC, BWH -- deep learning for prostate interventions, extension server for deep learning for Slicer
    10. Daniel Rubin deep learning
    11. Krisztina Fischer -- teaching

Agenda

Time Monday, January 9 Tuesday, January 10 Wednesday, January 11 Thursday, January 12 Friday, January 13
Project Presentations Work on Projects Work on Projects Work on Projects Reporting Day
8:30am Breakfast Breakfast Breakfast Breakfast
9:00am-10:30am Clinical Topics Clinical Topics Clinical Topics Clinical Topics
10:30am-12pm: Talk (Sebastian Ourselin, PhD, UCL) Project Reporting
12:00pm-1:00pm Lunch Lunch Lunch Lunch Lunch boxes; Adjourn by 1:30pm
1:00-5:30pm 1:00pm-2:30pm: Project Presentations 1:30-2:30pm: AMIGO Tour
5:30pm Adjourn for the day Adjourn for the day Adjourn for the day Adjourn for the day
(Optional) Dinner on Thursday Night

Calendar

The events are listed in the calendar below. Note that due to a current known limitation of our infrastructure, you will need to manually navigate to the week of January 8, 2017 to see the relevant events.


Error in widget Google Calendar: unable to write file /opt/mediawiki/1.33.0/extensions/Widgets/compiled_templates/wrt67414c0b536926_58985358

iCal (.ics) link: https://calendar.google.com/calendar/ical/kitware.com_sb07i171olac9aavh46ir495c4%40group.calendar.google.com/public/basic.ics

Projects

Learning and GPUs

Web Technologies

Visualization

IGT

Infrastructure

DICOM

Registrants

Do not add your name to this list - it is maintained by the organizers based on your paid registration. To register, visit this registration site.

Retrieved from "https://www.na-mic.org/w/index.php?title=2017_Winter_Project_Week&oldid=93849"