Difference between revisions of "Projects/Structural/2007 Project Week EMSegmentation Validation"

From NAMIC Wiki
Jump to: navigation, search
 
(12 intermediate revisions by the same user not shown)
Line 1: Line 1:
 
{|
 
{|
 
|[[Image:ProjectWeek-2007.png|thumb|320px|Return to [[2007_Programming/Project_Week_MIT|Project Week Main Page]] ]]
 
|[[Image:ProjectWeek-2007.png|thumb|320px|Return to [[2007_Programming/Project_Week_MIT|Project Week Main Page]] ]]
|[[Image:genuFAp.jpg|thumb|320px|Scatter plot of the original FA data through the genu of the corpus callosum of a normal brain.]]
+
|[[Image:EMSegment31Structures.png|thumb|400px|Brain segmentation using EMSegment and ModelMaker in Slicer3.]]
|[[Image:genuFA.jpg|thumb|320px|Regression of FA data; solid line represents the mean and dotted lines the standard deviation.]]
+
|[[Image:EMSegment31Structures2.png|thumb|400px|Brain segmentation using EMSegment and ModelMaker in Slicer3.]]
 
|}
 
|}
  
Line 22: Line 22:
 
<h1>Approach, Plan</h1>
 
<h1>Approach, Plan</h1>
  
Our approach for analyzing diffusion tensors is summarized in the IPMI 2007 reference below.  The main challenge to this approach is <foo>.  Our plan for the week is <bar>.
+
The validation study is based on a statistical comparison with results from earlier implementations of the EMSegment algorithm.  The study will be carried out by members of the Psychiatry Neuroimiging Laboratory (PNL) at Brigham and Women's Hospital, on their data, using the newly developed command line version of the EMSegment algorithm.  Kitware will provide software support and assist if problems arise with the results.  Details are provided in the reference below.  Our plan for the project week is to train the PNL staff on use of the new EMSegment tools, coordinate the validation study, and work out any bugs/interface problems as early as possible.
  
 
</div>
 
</div>
Line 30: Line 30:
 
<h1>Progress</h1>
 
<h1>Progress</h1>
  
Software for the fiber tracking and statistical analysis along the tracts has been implemented. The statistical methods for diffusion tensors are implemented as ITK code as part of the [[NA-MIC/Projects/Diffusion_Image_Analysis/DTI_Software_and_Algorithm_Infrastructure|DTI Software Infrastructure]] project. The methods have been validated on a repeated scan of a healthy individual. This work has been published as a conference paper (MICCAI 2005) and a journal version (MEDIA 2006). Our recent IPMI 2007 paper includes a nonparametric regression method for analyzing data along a fiber tract.
+
Preparations: develop EMSegment command line executable (DONE), add intensity normalization to module (Done)
 +
 
 +
Discussions: registration in EMSegmenter (design, coding UNDERWAY), application to white matter lesions (Jeremy Bockholt, Mark Scully at MIND, Kilian Pohl)
 +
 
 +
Updates: allow user to specify atlas files from the command line (DONE)
 +
 
 +
To Do: begin validation study
  
 
</div>
 
</div>
Line 40: Line 46:
  
 
===References===
 
===References===
* Fletcher, P.T., Tao, R., Jeong, W.-K., Whitaker, R.T., "A Volumetric Approach to Quantifying Region-to-Region White Matter Connectivity in Diffusion Tensor MRI," to appear Information Processing in Medical Imaging (IPMI) 2007.
+
 
* Corouge, I., Fletcher, P.T., Joshi, S., Gilmore, J.H., and Gerig, G., "Fiber Tract-Oriented Statistics for Quantitative Diffusion Tensor MRI Analysis," Medical Image Analysis 10 (2006), 786--798.
+
* [http://na-mic.org/Wiki/index.php/DBP:Harvard:Software:Testing:EMABC_Validation Slicer2 Validation Page]
* Corouge, I., Fletcher, P.T., Joshi, S., Gilmore J.H., and Gerig, G., Fiber Tract-Oriented Statistics for Quantitative Diffusion Tensor MRI Analysis, Lecture Notes in Computer Science LNCS, James S. Duncan and Guido Gerig, editors, Springer Verlag, Vol. 3749, Oct. 2005, pp. 131 -- 138
+
* [http://wiki.na-mic.org/Wiki/index.php/Slicer3:EM EMSegment wiki page]
* C. Goodlett, I. Corouge, M. Jomier, and G. Gerig, A Quantitative DTI Fiber Tract Analysis Suite, The Insight Journal, vol. ISC/NAMIC/ MICCAI Workshop on Open-Source Software, 2005, Online publication: http://hdl.handle.net/1926/39 .
+
* [[Media:EMSegmentValidationDescription.pdf | Detailed validation plan (pdf)]]

Latest revision as of 13:06, 29 June 2007

Home < Projects < Structural < 2007 Project Week EMSegmentation Validation
Brain segmentation using EMSegment and ModelMaker in Slicer3.
Brain segmentation using EMSegment and ModelMaker in Slicer3.


Key Investigators

  • Kitware: Brad Davis
  • BWH: Sylvain Bouix

Objective

Our goal is to begin a validation study that will establish the accuracy and dependability of the Slicer3 EMSegment module. This objective is part of a larger, ongoing development effort for this module.

Approach, Plan

The validation study is based on a statistical comparison with results from earlier implementations of the EMSegment algorithm. The study will be carried out by members of the Psychiatry Neuroimiging Laboratory (PNL) at Brigham and Women's Hospital, on their data, using the newly developed command line version of the EMSegment algorithm. Kitware will provide software support and assist if problems arise with the results. Details are provided in the reference below. Our plan for the project week is to train the PNL staff on use of the new EMSegment tools, coordinate the validation study, and work out any bugs/interface problems as early as possible.

Progress

Preparations: develop EMSegment command line executable (DONE), add intensity normalization to module (Done)

Discussions: registration in EMSegmenter (design, coding UNDERWAY), application to white matter lesions (Jeremy Bockholt, Mark Scully at MIND, Kilian Pohl)

Updates: allow user to specify atlas files from the command line (DONE)

To Do: begin validation study



References