Slicer Wiki - User contributions [en]

File:MABMIS results.png

2014-03-10T17:29:15Z

XiaofengLiu: uploaded a new version of "File:MABMIS results.png"

File:MABMIS groundtruth.png

2014-03-10T17:28:55Z

XiaofengLiu: uploaded a new version of "File:MABMIS groundtruth.png"

File:MABMIS Icon.png

2014-01-17T16:09:23Z

XiaofengLiu: uploaded a new version of "File:MABMIS Icon.png"

File:MABMIS testing GUI.png

2014-01-17T14:31:53Z

XiaofengLiu: uploaded a new version of "File:MABMIS testing GUI.png"

File:MABMIS trainning GUI.png

2014-01-17T14:31:41Z

XiaofengLiu: uploaded a new version of "File:MABMIS trainning GUI.png"

File:MABMIS trainning GUI.png

2014-01-17T14:31:00Z

XiaofengLiu: uploaded a new version of "File:MABMIS trainning GUI.png"

Documentation/Nightly/Extensions/MABMIS

2014-01-17T14:29:32Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant 2R01EB006733-04A1. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[Image:MABMIS_algorithm.png|thumb|600px|MABMIS algorithm overview. ]]
|}

The figure above shows an overview of the algorithm. MABMIS contains two modules: the training module, and the testing module.
 

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|600px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|600px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training module is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|800px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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]: (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 ==

The GUI for the testing module is shown below:
{|
|[[Image:MABMIS_testing_GUI.png|thumb|600px|MABMAS testing module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Testing''' ''[-i xx,xx,xx] [-s sigma] --atlasTreeXML TrainedAtlas.xml -- imageListXML TestImageList.xml --outputfolder OutputFolder''

 

* [-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]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
* TrainedAtlas.xml: an xml file that contains the trained atlas resulted from the training module.
* TestImageList.xml: an xml file that contains a list of test images to be segmented. An example can be found in the test folder
* OutputFolder: The location to save the segmentation results.


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

File:MABMIS algorithm.png

2014-01-17T14:28:39Z

XiaofengLiu: uploaded a new version of "File:MABMIS algorithm.png"

File:MABMIS Icon.png

2014-01-17T14:24:08Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:20:36Z

XiaofengLiu: /* Training */

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant 2R01EB006733-04A1. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[Image:MABMIS_algorithm.png|thumb|600px|Example: MABMIS segmentation results]]
|}

The figure above shows an overview of the algorithm. MABMIS contains two modules: the training module, and the testing module.
 

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|600px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|600px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training module is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|800px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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]: (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 ==

The GUI for the testing module is shown below:
{|
|[[Image:MABMIS_testing_GUI.png|thumb|600px|MABMAS testing module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Testing''' ''[-i xx,xx,xx] [-s sigma] --atlasTreeXML TrainedAtlas.xml -- imageListXML TestImageList.xml --outputfolder OutputFolder''

 

* [-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]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
* TrainedAtlas.xml: an xml file that contains the trained atlas resulted from the training module.
* TestImageList.xml: an xml file that contains a list of test images to be segmented. An example can be found in the test folder
* OutputFolder: The location to save the segmentation results.


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:19:29Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant 2R01EB006733-04A1. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[Image:MABMIS_algorithm.png|thumb|600px|Example: MABMIS segmentation results]]
|}

The figure above shows an overview of the algorithm. MABMIS contains two modules: the training module, and the testing module.
 

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|600px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|600px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training module is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|600px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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]: (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 ==

The GUI for the testing module is shown below:
{|
|[[Image:MABMIS_testing_GUI.png|thumb|600px|MABMAS testing module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Testing''' ''[-i xx,xx,xx] [-s sigma] --atlasTreeXML TrainedAtlas.xml -- imageListXML TestImageList.xml --outputfolder OutputFolder''

 

* [-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]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
* TrainedAtlas.xml: an xml file that contains the trained atlas resulted from the training module.
* TestImageList.xml: an xml file that contains a list of test images to be segmented. An example can be found in the test folder
* OutputFolder: The location to save the segmentation results.


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:18:29Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant 2R01EB006733-04A1. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training module is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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]: (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 ==

The GUI for the testing module is shown below:
{|
|[[Image:MABMIS_testing_GUI.png|thumb|400px|MABMAS testing module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Testing''' ''[-i xx,xx,xx] [-s sigma] --atlasTreeXML TrainedAtlas.xml -- imageListXML TestImageList.xml --outputfolder OutputFolder''

 

* [-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]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
* TrainedAtlas.xml: an xml file that contains the trained atlas resulted from the training module.
* TestImageList.xml: an xml file that contains a list of test images to be segmented. An example can be found in the test folder
* OutputFolder: The location to save the segmentation results.


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:06:14Z

XiaofengLiu: /* Training */

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant xxxxxxx. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training module is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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]: (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 ==

The GUI for the testing module is shown below:
{|
|[[Image:MABMIS_testing_GUI.png|thumb|400px|MABMAS testing module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Testing''' ''[-i xx,xx,xx] [-s sigma] --atlasTreeXML TrainedAtlas.xml -- imageListXML TestImageList.xml --outputfolder OutputFolder''

 

* [-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]: (OPTIONAL)the size of the smoothing kernel that is used for smoothing deformation fields. Default value is 1.5.
* TrainedAtlas.xml: an xml file that contains the trained atlas resulted from the training module.
* TestImageList.xml: an xml file that contains a list of test images to be segmented. An example can be found in the test folder
* OutputFolder: The location to save the segmentation results.


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

File:MABMIS testing GUI.png

2014-01-16T22:03:56Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:01:52Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant xxxxxxx. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training model is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''
 

* [-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.
* 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


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T22:01:02Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant xxxxxxx. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training model is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''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.
* [-s sigma] : 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

{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:59:45Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant xxxxxxx. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Training ==

The GUI for the training model is shown below:
{|
|[[Image:MABMIS_trainning_GUI.png|thumb|400px|MABMAS training module]]
|}

 

To run it as a command line:
 

'''IGR3D_MABMIS_Training''' ''[-i xx,xx,xx] [-s sigma] -- trainingXML TrainingData.xml -- atlasTreeXML TrainedAtlas.xml ''


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

File:MABMIS trainning GUI.png

2014-01-16T21:57:04Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:55:56Z

XiaofengLiu:

<noinclude>{{documentation/versioncheck}}</noinclude>

{{documentation/{{documentation/version}}/module-header}}



{{documentation/{{documentation/version}}/module-section|Introduction and Acknowledgements}}
{{documentation/{{documentation/version}}/module-introduction-start|{{documentation/modulename}}}}
{{documentation/{{documentation/version}}/module-introduction-row}}
MABMIS is a Slicer extension that implements a multi-atlas based multi-image method for group-wise segmentation [1]. The method utilizes a novel tree-based groupwise registration method for concurrent alignment of both the atlases and the target images, and 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.
 
Extension: [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS: Multi-atlas based group-wise segmentation]] 
Acknowledgments: This project was supported by NIH grant xxxxxxx. 

Contributor: Xiaofeng Liu, Minjeong Kim, Jim Miller, Dinggang Shen. 
Contact: Xiaofeng Liu, <email>xiaofeng.liu@ge.com</email> 

{{documentation/{{documentation/version}}/module-introduction-row}}
{{documentation/{{documentation/version}}/module-introduction-logo-gallery
|{{collaborator|logo|unc}}|{{collaborator|longname|unc}}
|{{collaborator|logo|ge}}|{{collaborator|longname|ge}}
}}

{{documentation/{{documentation/version}}/module-introduction-end}}


{{documentation/{{documentation/version}}/module-section|Module Description}}

{|
|[[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.
 

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|340px|Example: MABMIS segmentation results]]
|[[Image:MABMIS_groundtruth.png|thumb|340px|Example: The ground truth]]
|}


{{documentation/{{documentation/version}}/module-section|Tutorials}}
The module has two parts: training and testing. The training module requires as input a set of atlases, where each atlas contains an intensity image and a pre-segmented label images. The module then generates a trained atlas tree that can be used for multi-structure segmentation in the testing phase. The testing module requires two inputs. The first one is the trained atlas tree, and the second one is the set of images to be segmented. As a result, the testing module outputs multi-structure segmentation results on these images.
 

== Trainning ==


{{documentation/{{documentation/version}}/module-section|Panels and their use}}


{{documentation/{{documentation/version}}/module-section|Similar Modules}}


{{documentation/{{documentation/version}}/module-section|References}}
*Hongjun Jia, Pew-Thian Yap, Dinggang Shen, "Iterative multi-atlas-based multi-image segmentation with tree-based registration", NeuroImage, 59:422-430, 2012.


{{documentation/{{documentation/version}}/module-section|Information for Developers}}
{{documentation/{{documentation/version}}/module-developerinfo}}


{{documentation/{{documentation/version}}/module-footer}}
[[Category:Documentation/{{documentation/version}}/Modules/Segmentation]]

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:53:29Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:52:44Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:51:23Z

XiaofengLiu:

File:MABMIS algorithm.png

2014-01-16T21:50:10Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:49:39Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:49:00Z

XiaofengLiu:

File:MABMIS groundtruth.png

2014-01-16T21:43:22Z

XiaofengLiu:

File:MABMIS results.png

2014-01-16T21:43:08Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:26:25Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:16:03Z

XiaofengLiu:

Documentation/Nightly/Extensions/MABMIS

2014-01-16T21:10:51Z

XiaofengLiu: Created page with '<noinclude>{{documentation/versioncheck}}</noinclude>  {{documentation/{{documentation/version}}/module-header}} <!-- -----------------------…'

Documentation/Nightly/Extensions

2014-01-16T21:00:13Z

XiaofengLiu: /* Cat 2 */

<noinclude>{{documentation/versioncheck}}</noinclude>
<noinclude>
__TOC__
</noinclude>= Extensions by Category =

==Cat 1==

==Cat 2==
* [[Documentation/{{documentation/version}}/Extensions/SkullStripper|SkullStripper]] (Xiaodong Tao)
* [[Documentation/{{documentation/version}}/Extensions/MABMIS|MABMIS]] (Xiaofeng Liu)
* [[Documentation/{{documentation/version}}/Extensions/SwissSkullStripper|SwissSkullStripper]] (Bill Lorensen)
* [[Documentation/{{documentation/version}}/Extensions/CARMA|Cardiac MRI Toolkit]] (Alan Morris, Salma Bengali)[[image:UnderConstruction.png|tumb|10px]]
* [[Documentation/{{documentation/version}}/Extensions/PkModeling|PkModeling]] (Emma Zhu, Jim Miller)
* [[Documentation/{{documentation/version}}/Extensions/FacetedVisualizer|FacetedVisualizer]] (Harini Veeraraghavan, Jim Miller)
* [[Documentation/{{documentation/version}}/Extensions/Reporting|Reporting]] (Andrey Fedorov, Nicole Aucoin, Steve Pieper) (work in progress)
* [[Documentation/{{documentation/version}}/Extensions/SlicerRT|SlicerRT]] (Csaba Pinter, Andras Lasso, Kevin Wang, Greg Sharp, Steve Pieper)
** [[Documentation/{{documentation/version}}/Modules/DicomRtImport|DICOM-RT import]]
** [[Documentation/{{documentation/version}}/Modules/DicomRtExport|DICOM-RT export]]
** [[Documentation/{{documentation/version}}/Modules/Contours|Contours]]
** [[Documentation/{{documentation/version}}/Modules/DoseVolumeHistogram|Dose volume histogram]]
** [[Documentation/{{documentation/version}}/Modules/DoseAccumulation|Dose accumulation]]
** [[Documentation/{{documentation/version}}/Modules/DoseComparison|Dose comparison]]
** [[Documentation/{{documentation/version}}/Modules/Isodose|Isodose line and surface display]]
** [[Documentation/{{documentation/version}}/Modules/ContourComparison|Contour comparison]]
** [[Documentation/{{documentation/version}}/Modules/ContourMorphology|Contour morphology]]
** [[Documentation/{{documentation/version}}/Modules/PatientHierarchy|Patient hierarchy]]
** Modules from [[Documentation/{{documentation/version}}/Extensions/Plastimatch|Plastimatch]] (Greg Sharp)
*** [[Documentation/{{documentation/version}}/Modules/PlmBSplineDeformableRegistration|Plastimatch Automatic deformable image registration]]
*** [[Documentation/{{documentation/version}}/Modules/PlmLANDWARP|Plastimatch LANDWARP Landmark]]
*** [[Documentation/{{documentation/version}}/Modules/PlmXFORMWARP|Plastimatch XFORMWARP]] [[image:UnderConstruction.png|tumb|10px]]
* [[Documentation/{{documentation/version}}/Extensions/SlicerIGT|SlicerIGT]] (Tamas Ungi, Adam Rankin, Andras Lasso, Junichi Tokuda, Laurent Chauvin)
** [[Documentation/{{documentation/version}}/Modules/CollectFiducials|CollectFiducials]] (Tamas Ungi)
** [[Documentation/{{documentation/version}}/Modules/CreateModels|CreateModels]] (Tamas Ungi, Matthew Holden)
** [[Documentation/{{documentation/version}}/Modules/OpenIGTLinkRemote|OpenIGTLinkRemote]] (Tamas Ungi, Andras Lasso)
** [[Documentation/{{documentation/version}}/Modules/UltrasoundSnapshots|UltrasoundSnapshots]] (Tamas Ungi, Franklin King)
** [[Documentation/{{documentation/version}}/Extensions/VolumeResliceDriver|VolumeResliceDriver]] (Junichi Tokuda, Tamas Ungi, Laurent Chauvin)
* [[Documentation/{{documentation/version}}/Extensions/MatlabBridge|Matlab Bridge]] (Andras Lasso, Jean-Christophe Fillion-Robin, Kevin Wang)
* [[Documentation/{{documentation/version}}/Extensions/iGyne|iGyne]] (Xiaojun Chen and iGyne Team)
* [[Documentation/{{documentation/version}}/Extensions/LongitudinalPETCT|LongitudinalPETCT]] (Paul Mercea, Andrey Fedorov)
* [[Documentation/{{documentation/version}}/Extensions/DTIProcess|DTIProcess]] (Francois Budin)
* [[Documentation/{{documentation/version}}/Extensions/DTIAtlasFiberAnalyzer|DTIAtlasFiberAnalyzer]] (Francois Budin)
* [[Documentation/{{documentation/version}}/Extensions/FiberViewerLight|FiberViewerLight]] (Francois Budin)
* [[Documentation/{{documentation/version}}/Extensions/DTIPrep|DTIPrep]] (Francois Budin)
* [[Documentation/{{documentation/version}}/Extensions/DTIAtlasBuilder|DTIAtlasBuilder]] (Adrien Kaiser)
* [[Documentation/{{documentation/version}}/Extensions/ShapePopulationViewer|ShapePopulationViewer]] (Alexis Girault)
* [[Documentation/{{documentation/version}}/Extensions/TubeTK|TubeTK]] (Stephen Aylward, Jean-Christophe Fillion-Robin, Christopher Mullins, Michael Jeulin-L, Matthew McCormick)
* [[Documentation/{{documentation/version}}/Extensions/UKFTractography|UKFTractography]] (Ryan Eckbo, Yogesh Rathi)
* [[Documentation/{{documentation/version}}/Extensions/TrackerStabilizer|TrackerStabilizer]] (Laurent Chauvin, Jayender Jagadeesan)
* [[Documentation/{{documentation/version}}/Extensions/ChangeTracker|ChangeTracker]] (Andrey Fedorov)
* [[Documentation/{{documentation/version}}/Extensions/SobolevSegmenter|SobolevSegmenter]] (Arie Nakhmani)
* [[Documentation/{{documentation/version}}/Extensions/QuickTools|QuickTools]] (Julien Finet)
** [[Documentation/{{documentation/version}}/Modules/ImageMaker|Image Maker]]
* [[Documentation/{{documentation/version}}/Extensions/XNATSlicer|XNATSlicer]]
* [[Documentation/{{documentation/version}}/Extensions/ErodeDilateLabel|ErodeDilateLabel]] (Junichi)
* [[Documentation/{{documentation/version}}/Extensions/ThingiverseBrowser|ThingiverseBrowser]] (Nigel Goh)
* [[Documentation/{{documentation/version}}/Extensions/VirtualFractureReconstruction|Virtual Fracture Reconstruction]] (Karl Fritscher, Peter Karasev)
* [[Documentation/{{documentation/version}}/Extensions/AirwaySegmentation|AirwaySegmentation]] (Pietro Nardelli)
* [[Documentation/{{documentation/version}}/Extensions/ModelClip|ModelClip]] (Jun Lin, Xiaojun Chen)
* [[Documentation/{{documentation/version}}/Extensions/SurfaceMirror|SurfaceMirror]] (Jiaxi Luo, Ruqing Ye, Xiaojun Chen)
* [[Documentation/{{documentation/version}}/Extensions/Scoliosis|Scoliosis]] (Franklin King, Tamas Ungi)
**[[Documentation/{{documentation/version}}/Modules/SpinalCurvatureMeasurement|Spinal Curvature Measurement]] (Franklin King, Tamas Ungi)
* [[Documentation/{{documentation/version}}/Extensions/PortPlacement|Port Placement]] (Andinet Enquobahrie, Luis G. Torres)
* [[Documentation/{{documentation/version}}/Extensions/PlusRemote|Plus Remote]] (Franklin King, Tamas Ungi)
* [[Documentation/{{documentation/version}}/Extensions/TransformVisualizer|Transform Visualizer]] (Franklin King, Andras Lasso, Csaba Pinter)
* [[Documentation/{{documentation/version}}/Extensions/WindowLevelEffect|WindowLevelEffect]] (Andrey Fedorov, Steve Pieper)
* [[Documentation/{{documentation/version}}/Extensions/PerkTutor|PerkTutor]] (Tamas Ungi, Matthew Holden)
** [[Documentation/{{documentation/version}}/Modules/PerkEvaluator|PerkEvaluator]]
** [[Documentation/{{documentation/version}}/Modules/TransformRecorder|TransformRecorder]]
** [[Documentation/{{documentation/version}}/Modules/WorkflowSegmentation|WorkflowSegmentation]]
* [[Documentation/{{documentation/version}}/Modules/SlicerToKiwiExporter|SlicerToKiwiExporter]] (Jean-Christophe Fillion-Robin)
* [[Documentation/{{documentation/version}}/Modules/GelDosimetry|GelDosimetry]] (Csaba Pinter)

==Cat 3==
* [[Documentation/{{documentation/version}}/Extensions/LesionSegmentation|LesionSegmentation]] (Mark Scully)
**[[Documentation/{{documentation/version}}/Modules/TrainModel|LesionSegmentation->TrainModel]] (Mark Scully)
**[[Documentation/{{documentation/version}}/Modules/PredictLesions|LesionSegmentation->PredictLesions]] (Mark Scully)
* [[Documentation/{{documentation/version}}/Extensions/IASEM|IASEM]] (Bradley Lowekamp)
<noinclude>
{{:Documentation/{{documentation/version}}/FAQ/Extensions|Extensions}}
</noinclude>