Difference between revisions of "2012 Winter Project Week:EndoSeg"

From NAMIC Wiki
Jump to: navigation, search
m
 
(6 intermediate revisions by 3 users not shown)
Line 1: Line 1:
 
__NOTOC__
 
__NOTOC__
 
<gallery>
 
<gallery>
Image:PW-SLC2011.png|[[2011_Winter_Project_Week#Projects|Projects List]]
+
Image:PW-SLC2012.png|[[2012_Winter_Project_Week#Projects|Projects List]]
 
</gallery>
 
</gallery>
 +
 +
<gallery>
 +
Image:CARMA_N19_Atlas_LGE.png|Atlas Image
 +
Image:CAMRA_N26_LGE.png|Non-atlas Image
 +
</gallery>
 +
 +
<gallery>
 +
Image:AFibEndoSegAtlasAndRSS_axial.png|Axial view of segmentation result. Red contour: manual segmentation; Green mask: automatic segmentation
 +
Image:AFibEndoSegAtlasAndRSS_sagittal.png|Sagittal view
 +
Image:AFibEndoSegAtlasAndRSS_coronal.png|Coronal view
 +
</gallery>
 +
  
 
==Key Investigators==
 
==Key Investigators==
Yi Gao, Liang-Jia Zhu, Josh Cates, Gregory Phillip Gardner, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum
+
Yi Gao, Liang-Jia Zhu, Josh Cates, Alan Morris, Danny Perry, Greg Gardner, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum
  
 
<div style="margin: 20px;">
 
<div style="margin: 20px;">
Line 11: Line 23:
  
 
<h3>Objective</h3>
 
<h3>Objective</h3>
We are developing methods for segmenting the endocardium from the DE-MRI.
+
* We are developing methods for segmenting the endocardium from the DE-MRI.  The current proposed method is a multi-atlas based registration approach.  The user is presented with a weighted average of all registered atlas segmentations.  The final LA segmentation is a thresholded volume from this weighted average.  Weighting is based on the accuracy of the registration, as determined by a mutual information metric.
 
+
* There is a prototype module developed by Yi that is currently in Slicer.  We propose to expand and tweak this module to specifications determined by our experience using the algorithm on many real patient datasets.
 +
* We will also discuss posssible collaborative paper ideas based on this work.
  
 
</div>
 
</div>
Line 20: Line 33:
 
<h3>Approach, Plan</h3>
 
<h3>Approach, Plan</h3>
  
Approach to be filled here.
+
* Improve the speed and accuracy using the multi-scale scheme
 +
* Improve the accuracy of atlas segmentation accuracy with better label fusion techniques.
  
 
</div>
 
</div>

Latest revision as of 21:55, 12 January 2012

Home < 2012 Winter Project Week:EndoSeg


Key Investigators

Yi Gao, Liang-Jia Zhu, Josh Cates, Alan Morris, Danny Perry, Greg Gardner, Rob MacLeod, Sylvain Bouix, Allen Tannenbaum

Objective

  • We are developing methods for segmenting the endocardium from the DE-MRI. The current proposed method is a multi-atlas based registration approach. The user is presented with a weighted average of all registered atlas segmentations. The final LA segmentation is a thresholded volume from this weighted average. Weighting is based on the accuracy of the registration, as determined by a mutual information metric.
  • There is a prototype module developed by Yi that is currently in Slicer. We propose to expand and tweak this module to specifications determined by our experience using the algorithm on many real patient datasets.
  • We will also discuss posssible collaborative paper ideas based on this work.

Approach, Plan

  • Improve the speed and accuracy using the multi-scale scheme
  • Improve the accuracy of atlas segmentation accuracy with better label fusion techniques.

Progress

The current segmentation module is in the Slicer extension manager.

Delivery Mechanism

This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)

  1. Slicer Module
    1. Extension -- commandline

References