2012 Winter Project Week:TBIRegistration - Revision history

Yflou: /* Key Investigators */

2012-02-06T00:29:42Z

Key Investigators

2012-02-06T00:25:14Z

Key Investigators

2012-01-04T19:47:16Z

Key Investigators

2011-11-19T04:14:19Z

Key Investigators

2011-11-19T04:11:28Z

@@ Line 36: / Line 36: @@
 <h3>Progress</h3>
 * We have tailored a 10-page paper for a conference submission
-* We have discussed a few aspects on how to polish our paper
+* We have discussed a few feasible aspects to polish our paper as in Approach
-* We will submit a journal paper shortly
+* We will submit a journal version shortly

@@ Line 13: / Line 13: @@
 <h3>Objective</h3>
-* Design a registration algorithm that can deal with topological changes for TBI patients.
+* A short version of conference submission.
-* Design metrics to quantify the degree of changes of TBI
+* A in-depth discussion on the similarity measures for TBI image registration as a journal submission.
@@ Line 23: / Line 25: @@
 <h3>Approach, Plan</h3>
-Approach to be filled here.
+* Analyze on different similarity measures, such as mutual information, Bhattacharyya Distance, J-R Divergence and cross correlation etc
 </div>
@@ Line 30: / Line 35: @@
 <h3>Progress</h3>

@@ Line 30: / Line 30: @@
 <h3>Progress</h3>
-The current segmentation module is in the Slicer extension manager.
 </div>

@@ Line 13: / Line 13: @@
 <h3>Objective</h3>
-* 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.
+* Design a registration algorithm that can deal with topological changes for TBI patients.
-* 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.
+* Design metrics to quantify the degree of changes of TBI
-* We will also discuss posssible collaborative paper ideas based on this work.
 </div>

@@ Line 1: / Line 1: @@
 ==Key Investigators==
 *Georgia Tech: Yifei Lou and Patricio Vela
@@ Line 5: / Line 10: @@
 <div style="margin: 20px;">
 <h3>Objective</h3>
-We are developing a Slicer4 module that can receive tracked ultrasound images through an OpenIGTLink connection, and create a representation of the real-time ultrasound image in the Slicer scene.
+* 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.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Approach, Plan</h3>
-The PLUS (Public Library for Ultrasound) library will send OpenIGTLink messages to Slicer. Images to update the ultrasound image data, and transforms to update the ultrasound slice position and other surgical tools in the scene.
 </div>
@@ Line 19: / Line 30: @@
 <h3>Progress</h3>
+The current segmentation module is in the Slicer extension manager.
 </div>
@@ Line 25: / Line 36: @@
 <div style="width: 97%; float: left;">