Difference between revisions of "2008 Winter Project Week:Lesions"

From NAMIC Wiki
Jump to: navigation, search
 
(21 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
{|
 
{|
 
|[[Image:NAMIC-SLC.jpg|thumb|320px|Return to [[2008_Winter_Project_Week]] ]]
 
|[[Image:NAMIC-SLC.jpg|thumb|320px|Return to [[2008_Winter_Project_Week]] ]]
−
|valign="top"|[[Image:Case24-coronal-tensors-edit.png |thumb|320px|The Cingulum Bundle Anchor Tract]]
+
|valign="top"|[[Image:Lupus.png|320px]]
 
|}
 
|}
  
Line 8: Line 8:
 
* MIND: Jeremy Bockolt, Mark Scully
 
* MIND: Jeremy Bockolt, Mark Scully
 
* BWH: Sonia Pujol
 
* BWH: Sonia Pujol
 +
* Utah: Marcel Prastawa
 +
* Iowa: Vincent Magnotta
 
* Kitware: Brad Davis
 
* Kitware: Brad Davis
  
Line 15: Line 17:
  
 
<h1>Objective</h1>
 
<h1>Objective</h1>
−
Objectives here
+
Our objective is to make progress on the roadmap initiative of creating an end to end solution that provides a tutorial for NA-MIC kit users to perform lesion analyses in Slicer3.
  
 
</div>
 
</div>
Line 22: Line 24:
  
 
<h1>Approach, Plan </h1>
 
<h1>Approach, Plan </h1>
−
Approach, Plan here
+
For this week, we will attend and participate in the following training relevant to this DBP activities:
 +
*EM Segmenter User Group
 +
*Plugins for Slicer3
 +
*DBP Engineers Lunch
 +
*Registration Breakout
 +
*Batchmake
 +
 
 +
Fully analyze 2 lupus subjects and 2 matched healthy normal volunteer data-sets collected:
 +
*EM Segment
 +
*BRAINS
 +
*Prastawa/Gerig Lesion analysis method
 +
 
 +
We see our roadmap initiative breaking into the following stages:
 +
 
 +
a) Criteria and definition of what does an expert define and perceive as a
 +
lesion (like rules on multi-contrast MRI), creation of a
 +
document/catalogue that guides manual segmentation but also algorithm
 +
developers.
 +
 
 +
b) Specification of advanced software for user-guided
 +
efficient segmentation of lesions (e.g. 3D level set evolution etc.,
 +
definition of MRI contrast to use to do that, etc.).
 +
 
 +
c) Towards approaches towards fully automatic lesion segmentation using
 +
multi-contrast MRI.,
 +
 
 +
d) Validateion/test framework for comparison of
 +
user-defined lesion patterns to automated/automatic lesion segmentation,
 +
definition of comparison metrics.
 +
 
 +
 
 
</div>
 
</div>
  
Line 28: Line 60:
  
 
<h1>Progress</h1>
 
<h1>Progress</h1>
 +
====Feb 2008 Updates====
 +
* Provided Killian with a two channel lesion segmentation performed with EMSegment.
 +
* Waiting on EMSegment update to resolve errors relating to additional input channels and weighting by image. ( We need the third channel since we have flair. )
 +
* Waiting on Marcel to update and provide a copy of his lesion analysis tool.
 +
 +
 +
====Jan 2008 Project Week====
 +
* attended EM-segment breakout session
 +
* attended Slicer Module breakout session
 +
* attended Registration breakout
 +
* attended Batchmake breakout
 +
* met with Marcel to review his method and results of lesion analysis
 +
* met with Brad and Kilian to work out EM-Segment issues
 +
* successfully built Slicer3 from SVN on Mac G4/G5 OSX 10.4 platforms
 +
** we would like to figure out how to get it to buildon on Mac x86 OSX 10.5 platform
 +
* successfully ran EM-Segment on tutorial data-set
 +
* successfully ran EM-Segment on lupus and normal control cases
 +
** we have not yet gotten the segmentation of white matter into normal and lesion to work
 +
* met with Vince Magnotta regarding BRAINS/ITK lesion segmentation method
 +
** we will have a modified method to try in about two weeks
 +
* we plan to submit a paper to [http://miccai2008.rutgers.edu/ MICCAI 2008]
  
 
====June 2007 Project Week====
 
====June 2007 Project Week====
−
During this Project Week, we did a lot of algorithmic design work, focusing on leveraging optimal or geodesic path information to provide for volumetric segmentations of fiber bundles.  Working with Marek Kubicki and the Harvard DBP, we were able to begin the process of applying our algorithm to the full cingulum bundle with new labelmaps and to a new fiber bundle - Arcuate. We have recently achieved significant results in volumetric segmentations using a locally-constrained region-based technique (see the images above).
+
First meeting as a new DBP in lupus.
 +
We received hands on training on ITK/VTK, as well as, EM Segment.
 +
We processed lupus case using EM Segment.
  
 
====Jan 2007 Project Half Week====
 
====Jan 2007 Project Half Week====
−
We finished the itkDirectionalIterator which will be needed in the Fast Sweeping implementation.  Furthermore, we made progress in porting our Matlab code to ITK.
+
Jeremy attended this meeting in order to learn about NA-MIC
−
 
 
 
</div>
 
</div>
  
Line 43: Line 97:
  
 
===References===
 
===References===
−
* J. Melonakos, M. Niethammer, V. Mohan, M. Kubicki, J. Miller, A. Tannenbaum. Locally-Constrained Region-Based Methods for DW-MRI Segmentation. Submitted to MMBIA 2007.
+
*
−
* V. Mohan, J. Melonakos, M. Niethammer, M. Kubicki, and A. Tannenbaum. Finsler Level Set Segmentation for Imagery in Oriented Domains. BMVC 2007.
 
−
* J. Melonakos, V. Mohan, M. Niethammer, K. Smith, M. Kubicki, and A. Tannenbaum. Finsler Tractography for White Matter Connectivity Analysis of the Cingulum Bundle. MICCAI 2007.
 
−
* J. Melonakos, E. Pichon, S. Angenet, and A. Tannenbaum. Finsler Active Contours. IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear in 2007.
 
−
* E. Pichon and A. Tannenbaum. Curve segmentation using directional information, relation to pattern detection. In IEEE International Conference on Image Processing (ICIP), volume 2, pages 794-797, 2005.
 
−
* E. Pichon, C-F Westin, and A. Tannenbaum. A Hamilton-Jacobi-Bellman approach to high angular resolution diffusion tractography. In International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pages 180-187, 2005.
 

Latest revision as of 17:02, 6 February 2008

Home < 2008 Winter Project Week:Lesions
Return to 2008_Winter_Project_Week
 Lupus.png


Key Investigators

  • MIND: Jeremy Bockolt, Mark Scully
  • BWH: Sonia Pujol
  • Utah: Marcel Prastawa
  • Iowa: Vincent Magnotta
  • Kitware: Brad Davis

Objective

Our objective is to make progress on the roadmap initiative of creating an end to end solution that provides a tutorial for NA-MIC kit users to perform lesion analyses in Slicer3.

Approach, Plan

For this week, we will attend and participate in the following training relevant to this DBP activities:

  • EM Segmenter User Group
  • Plugins for Slicer3
  • DBP Engineers Lunch
  • Registration Breakout
  • Batchmake

Fully analyze 2 lupus subjects and 2 matched healthy normal volunteer data-sets collected:

  • EM Segment
  • BRAINS
  • Prastawa/Gerig Lesion analysis method

We see our roadmap initiative breaking into the following stages:

a) Criteria and definition of what does an expert define and perceive as a lesion (like rules on multi-contrast MRI), creation of a document/catalogue that guides manual segmentation but also algorithm developers.

b) Specification of advanced software for user-guided efficient segmentation of lesions (e.g. 3D level set evolution etc., definition of MRI contrast to use to do that, etc.).

c) Towards approaches towards fully automatic lesion segmentation using multi-contrast MRI.,

d) Validateion/test framework for comparison of user-defined lesion patterns to automated/automatic lesion segmentation, definition of comparison metrics.


Progress

Feb 2008 Updates

  • Provided Killian with a two channel lesion segmentation performed with EMSegment.
  • Waiting on EMSegment update to resolve errors relating to additional input channels and weighting by image. ( We need the third channel since we have flair. )
  • Waiting on Marcel to update and provide a copy of his lesion analysis tool.


Jan 2008 Project Week

  • attended EM-segment breakout session
  • attended Slicer Module breakout session
  • attended Registration breakout
  • attended Batchmake breakout
  • met with Marcel to review his method and results of lesion analysis
  • met with Brad and Kilian to work out EM-Segment issues
  • successfully built Slicer3 from SVN on Mac G4/G5 OSX 10.4 platforms
    • we would like to figure out how to get it to buildon on Mac x86 OSX 10.5 platform
  • successfully ran EM-Segment on tutorial data-set
  • successfully ran EM-Segment on lupus and normal control cases
    • we have not yet gotten the segmentation of white matter into normal and lesion to work
  • met with Vince Magnotta regarding BRAINS/ITK lesion segmentation method
    • we will have a modified method to try in about two weeks
  • we plan to submit a paper to MICCAI 2008

June 2007 Project Week

First meeting as a new DBP in lupus. We received hands on training on ITK/VTK, as well as, EM Segment. We processed lupus case using EM Segment.

Jan 2007 Project Half Week

Jeremy attended this meeting in order to learn about NA-MIC



References

Retrieved from "https://www.na-mic.org/w/index.php?title=2008_Winter_Project_Week:Lesions&oldid=21923"