2014 Project Week:MultiAtlas MultiImage Segmentation - Revision history

Mjkim at 21:28, 6 January 2014

2014-01-06T21:28:36Z

Mjkim at 18:47, 2 January 2014

2014-01-02T18:47:40Z

Mjkim at 16:23, 2 January 2014

2014-01-02T16:23:25Z

Mjkim: Created page with 'NOTOC Image:PW-SLC2014.png|Projects List Image: | left: ground truth labels, right: our labeling result ==Key Inv…'

2014-01-02T16:16:51Z

Created page with '__NOTOC__ <gallery> Image:PW-SLC2014.png|Projects List Image: | left: ground truth labels, right: our labeling result </gallery> ==Key Inv…'

New page

__NOTOC__

<gallery>
Image:PW-SLC2014.png|[[2014_Winter_Project_Week#Projects|Projects List]]
Image: | left: ground truth labels, right: our labeling result
</gallery>

==Key Investigators==

* Minjeong Kim, Dinggang Shen, UNC Chapel Hill
* Xiaofeng Liu, Jim Miller, GE Research

==Project Description==

<div style="margin: 20px;">
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Objective</h3>
We develop a Slicer module for multi-atlas-based multi-image segmentation of brain images. To deal with the limitation of existing pairwise registration methods between images with large shape difference, our algorithm in the module performs 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Approach, Plan</h3>
We have developed the Slicer module called MABMIS and fully tested it using LONI LPBA40 and IXI datasets. The result by our Slicer module shows 2% improvement compared to pairwise registration methods in terms of the averaged overlap ratio between automatic segmentation and ground truth labels.
</div>
<div style="width: 27%; float: left; padding-right: 3%;">
<h3>Progress</h3>
We are releasing our Slice module in NITRC (https://www.nitrc.org).
</div>
</div>

@@ Line 26: / Line 26: @@
 <h3>Progress</h3>
 We have developed the Slicer module called MABMIS and fully tested it using LONI LPBA40 and IXI datasets. The result by our Slicer module shows 2% improvement compared to pairwise registration framework in terms of the averaged overlap ratio between automatic segmentation and ground truth labels.
-We are releasing our Slice module in NITRC (https://www.nitrc.org).
+We are releasing our Slice module in NITRC (http://www.nitrc.org/projects/mabmis_slicer4/).
 </div>
 </div>

@@ Line 3: / Line 3: @@
 <gallery>
 Image:PW-SLC2014.png|[[2014_Winter_Project_Week#Projects|Projects List]]
-Image: | left: ground truth labels, right: our labeling result
+Image:groundtruthMABMIS.png| Manual labels (ground truth) in IXI dataset
 </gallery>

@@ Line 16: / Line 16: @@
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Objective</h3>
-We develop a Slicer module for multi-atlas-based multi-image segmentation of brain images. To deal with the limitation of existing pairwise registration methods between images with large shape difference, our algorithm in the module performs 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images.
+To deal with the limitations of existing pairwise registration methods between images with large shape difference, we develop an algorithm for multi-atlas-based multi-image segmentation of brain images and release it as a Slicer module.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Approach, Plan</h3>
-We have developed the Slicer module called MABMIS and fully tested it using LONI LPBA40 and IXI datasets. The result by our Slicer module shows 2% improvement compared to pairwise registration methods in terms of the averaged overlap ratio between automatic segmentation and ground truth labels.
+Our algorithm in the module performs 1) a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 2) an iterative groupwise segmentation method for simultaneous consideration of segmentation information propagated from all available images, including the atlases and other newly segmented target images.
 </div>
 <div style="width: 27%; float: left; padding-right: 3%;">
 <h3>Progress</h3>
 We are releasing our Slice module in NITRC (https://www.nitrc.org).
 </div>
 </div>

2014 Project Week:MultiAtlas MultiImage Segmentation - Revision history

Mjkim at 21:28, 6 January 2014

Mjkim at 18:47, 2 January 2014

Mjkim at 16:23, 2 January 2014

Mjkim: Created page with '__NOTOC__ Image:PW-SLC2014.png|Projects List Image: | left: ground truth labels, right: our labeling result ==Key Inv…'

Mjkim: Created page with 'NOTOC Image:PW-SLC2014.png|Projects List Image: | left: ground truth labels, right: our labeling result ==Key Inv…'