2010 Winter Project Week Musco Skeletal Segmentation - Revision history

Spal5: /* Key Investigators */

2010-01-07T16:28:12Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-06T22:47:30Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:26:52Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:26:11Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:22:00Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:21:06Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:20:37Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:08:30Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T01:02:09Z

Key Investigators

Spal5: /* Key Investigators */

2010-01-04T00:41:03Z

Key Investigators

@@ Line 15: / Line 15: @@
 ==Key Investigators==
 * Stanford: Harish Doddi, Saikat Pal, Scott Delp
-* Kitware: Luis Ibanez
+* Kitware: Luis Ibanez, Harvey Cline
 * GE Research: Xiaodong Tao
@@ Line 42: / Line 42: @@
 a. Incorporate a method to refine label maps (remove undesired bridge connections).
 <BR>
-b. Implement an algorithm to extract smoothed boundaries from label maps.
+b. Implement an algorithm to assign fiducial points to region boundaries for manual adjustments of geometries.
 </div>
@@ Line 49: / Line 49: @@
 <h3>Progress</h3>
-* Implemented algorithm to rapidly segment structures of interest from multi-constrast MR images.
+* Implemented algorithm to segment structures of interest from multi-constrast MR images.
 * Generated label maps of knee and hip structures.
 </div>
 </div>

@@ Line 16: / Line 16: @@
 * Stanford: Harish Doddi, Saikat Pal, Scott Delp
 * Kitware: Luis Ibanez
 <div style="margin: 20px;">

@@ Line 49: / Line 49: @@
 <h3>Progress</h3>
 * Implemented algorithm to rapidly segment structures of interest from multi-constrast MR images.
-<BR>
+* Generated label maps of knee and hip structures.
 </div>
 </div>

@@ Line 36: / Line 36: @@
 For more details, please visit http://www.na-mic.org/Wiki/index.php/Stanford_Simbios_group
 <BR>
 <i><u>Plan: </u></i>
 <BR>
-a. Incorporate a method to clean label maps (remove undesired bridge connections).
+a. Incorporate a method to refine label maps (remove undesired bridge connections).
 <BR>
 b. Implement an algorithm to extract smoothed boundaries from label maps.
@@ Line 49: / Line 48: @@
 <h3>Progress</h3>
-Finished segmenting different regions of interest like bones, cartilage etc.
+* Implemented algorithm to rapidly segment structures of interest from multi-constrast MR images.
 </div>
 </div>

@@ Line 36: / Line 36: @@
 For more details, please visit http://www.na-mic.org/Wiki/index.php/Stanford_Simbios_group
 <BR>
 <BR>

@@ Line 26: / Line 26: @@
 <BR>
 . Generation of simulation-ready models from existing atlas and label maps of individual structures.
 </div>

@@ Line 35: / Line 35: @@
 <i><u>Approach:</u></i>
 <BR>
-Objective 1: We have adopted a multi-contrast MR methodology to segment knee bones and cartilage structures.  The algorithm utilizes tissue intensity information from multiple MR contrasts to segment structures of interest.  Inputs to the algorithm included n registered MR image sets.  The algorithm created an n-dimensional space of voxel intensities associated with the n image sets. The user assigned seed points to the structures of interest, and the algorithm created a cluster center for each structure of interest. Cluster radii were calculated based on standard deviations obtained from seed points, and tissue structures classified based on intensity clustering of voxels.
+Objective 1: We have adopted a multi-contrast MR methodology to segment knee bones and cartilage structures.  The algorithm utilizes tissue intensity information from multiple MR contrasts to segment structures of interest.  Inputs to the algorithm included n registered MR image sets.  The algorithm created an n-dimensional space of voxel intensities associated with the n image sets. The user assigned seed points to the structures of interest, and the algorithm created a cluster center for each structure of interest. Cluster radii were calculated based on standard deviations obtained from seed points, and tissue structures were classified as label maps.
+For more details, please visit http://www.na-mic.org/Wiki/index.php/Stanford_Simbios_group
 <BR>
 <BR>
@@ Line 46: / Line 43: @@
 <i><u>Plan: </u></i>
 <BR>
-a. Smooth the existing segmented label maps
+a. Incorporate a method to clean label maps (remove undesired bridge connections).
 <BR>
-b. Build models for bones and cartilage from the existing segmented label maps.
+b. Implement an algorithm to extract smoothed boundaries from label maps.
 </div>

@@ Line 25: / Line 25: @@
 . Rapid segmentation of target structures into label maps.
 <BR>
-. Generation of simulation-ready models from label maps of individual structures.
+. Generation of simulation-ready models from existing atlas and label maps of individual structures.
@@ Line 35: / Line 35: @@
 <i><u>Approach:</u></i>
 <BR>
 Multi-Contrast MR images are collected and seed points for each region of interest are taken as input. Cluster center and standard deviation are calculated for each ROI based on pixel intensities of the seed points. The pixels are clustered based on different pixel intensity values in multiple MR images to the nearest cluster center radius.

@@ Line 22: / Line 22: @@
 <h3>Objective</h3>
 The aim of this project is to develop a methodology for rapid segmentation of knee structures from magnetic resonance (MR) images for subject-specific modeling. The overall goal can be broken down into two specific objectives -
 . Rapid segmentation of target structures into label maps.
 . Generation of simulation-ready models from label maps of individual structures.