Documentation/Nightly/Extensions/MABMIS - Revision history

XiaofengLiu at 14:29, 17 January 2014

2014-01-17T14:29:32Z

XiaofengLiu: /* Training */

2014-01-16T22:20:36Z

Training

XiaofengLiu at 22:19, 16 January 2014

2014-01-16T22:19:29Z

XiaofengLiu at 22:18, 16 January 2014

2014-01-16T22:18:29Z

XiaofengLiu: /* Training */

2014-01-16T22:06:14Z

Training

XiaofengLiu at 22:01, 16 January 2014

2014-01-16T22:01:52Z

XiaofengLiu at 22:01, 16 January 2014

2014-01-16T22:01:02Z

XiaofengLiu at 21:59, 16 January 2014

2014-01-16T21:59:45Z

XiaofengLiu at 21:55, 16 January 2014

2014-01-16T21:55:56Z

XiaofengLiu at 21:53, 16 January 2014

2014-01-16T21:53:29Z

@@ Line 29: / Line 29: @@
 <!-- ---------------------------- -->
 {|
-|[[Image:MABMIS_algorithm.png|thumb|600px|Example: MABMIS segmentation results]]
+|[[Image:MABMIS_algorithm.png|thumb|600px|MABMIS algorithm overview. ]]
 |}

@@ Line 62: / Line 62: @@
 The GUI for the training module is shown below:
 {|
-|[[Image:MABMIS_trainning_GUI.png|thumb|600px|MABMAS training module]]
+|[[Image:MABMIS_trainning_GUI.png|thumb|800px|MABMAS training module]]
 |}
@@ Line 76: / Line 76: @@
 * [-s sigma]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
 * TrainingData.xml : an xml file that specifies information about the training images, including the number of training data, filenames of T1-weighted image and the segmented label images. An example can be found in the test folder.
 * TrainedAtlas.xml: an xml file for output, that stores information about the trained atlas tree which can be used to segment.
 == Testing ==

@@ Line 29: / Line 29: @@
 <!-- ---------------------------- -->
 {|
-|[[Image:MABMIS_algorithm.png|thumb|340px|Example: MABMIS segmentation results]]
+|[[Image:MABMIS_algorithm.png|thumb|600px|Example: MABMIS segmentation results]]
 |}
@@ Line 48: / Line 48: @@
 {{documentation/{{documentation/version}}/module-section|Use Cases}}
 {|
-|[[Image:MABMIS_results.png|thumb|340px|Example: MABMIS segmentation results]]
+|[[Image:MABMIS_results.png|thumb|600px|Example: MABMIS segmentation results]]
-|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
+|[[Image:MABMIS_groundtruth.png|thumb|600px|Example: The ground truth]]
 |}
@@ Line 62: / Line 62: @@
 The GUI for the training module is shown below:
 {|
-|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
+|[[Image:MABMIS_trainning_GUI.png|thumb|600px|MABMAS training module]]
 |}
@@ Line 82: / Line 82: @@
 The GUI for the testing module is shown below:
 {|
-|[[Image:MABMIS_testing_GUI.png|thumb|400px|MABMAS testing module]]
+|[[Image:MABMIS_testing_GUI.png|thumb|600px|MABMAS testing module]]
 |}

@@ Line 11: / Line 11: @@
 <br>
 Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]]<br>
-Acknowledgments: This project was supported by NIH grant xxxxxxx. <br>
+Acknowledgments: This project was supported by NIH grant 2R01EB006733-04A1. <br>
 Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. <br>

@@ Line 60: / Line 60: @@
 == Training ==
-The GUI for the training model is shown below:
+The GUI for the training module is shown below:
 {|
 |[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
@@ Line 74: / Line 74: @@
 * [-i xx,xx,xx]:(OPTIONAL) number of iterations used in image registration. It is three numbers separated by comma. Default value is 5,3,2.
-* [-s sigma] : the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
+* [-s sigma]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
 * TrainingData.xml : an xml file that specifies information about the training images, including the number of training data, filenames of T1-weighted image and the segmented label images. An example can be found in the test folder.
-* TrainedAtlas.xml: an xml file for output, that stores information about the trained atlas tree which can be used to segment
+* TrainedAtlas.xml: an xml file for output, that stores information about the trained atlas tree which can be used to segment.

@@ Line 71: / Line 71: @@
 '''IGR3D_MABMIS_Training'''   ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML  TrainedAtlas.xml ''
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Panels and their use}}
-*[-i xx,xx,xx]:(OPTIONAL) number of iterations used in image registration. It is three numbers separated by comma. Default value is 5,3,2.
 <!-- ---------------------------- -->
 {{documentation/{{documentation/version}}/module-section|Similar Modules}}

@@ Line 29: / Line 29: @@
 <!-- ---------------------------- -->
 {|
-|[[Image:MABMIS_algorithm.png|thumb|400px|MABMIS algorithm overview]]
+|[[Image:MABMIS_algorithm.png|thumb|340px|Example: MABMIS segmentation results]]
 |}
 The figure above shows an overview of the algorithm. MABMIS contains two modules: the training module, and the testing module.
 <br>
 In the training module, multiple atlas image pairs are required as the input. Each atlas image pair contains one pre-processed  T1-weighted intensity image and one label image on which each interested structure on the T1 image is manually identified and assigned a unique label. The label image is generally generated by an expert. In the training module, the multiple atlas pairs are processed to construct an atlas tree, where each atlas is one node of the tree. The tree is constructed based on the similarity among the atlases and tree-based groupwise registration.
 In the testing module, a group of target images are segmented based on the atlas tree. First, a novel tree-based groupwise registration method is employed to simultaneously register them to the atlas tree, the target images are segmented simultaneously using an iterative groupwise segmentation strategy, which provides improved accuracy and across-image consistency.
 Before applying the modules, both atlas images and target images need to be pre-processed. The processing steps include bias correction ( e.g., N4), skull stripping (e.g., skullstripper in slicer), histogram matching. All images are then registered to a common space using affine registration. The pre-processing tools are not included in the module.
 Detailed description of the algorithm can be found in [1].
 {{documentation/{{documentation/version}}/module-section|Use Cases}}
 {|
-|[[Image:MABMIS_results.png|thumb|400px|Example: MABMIS segmentation results]]
+|[[Image:MABMIS_results.png|thumb|340px|Example: MABMIS segmentation results]]
-|[[Image:MABMIS_groundtruth.png|thumb|400px|Example: The ground truth]]
+|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
 |}