Difference between revisions of "BRAINSCut"

From NAMIC Wiki
Jump to: navigation, search
 
(8 intermediate revisions by the same user not shown)
Line 1: Line 1:
BRAINSCut is a software package for segmentation of structures using artificial neural networks. Currently this tool supports the segmentation of the following structures: caudate, putamen, thalamus, hippocampus, anterior cerebellum, interior posterior cerebellum, superior posterior cerebellum, corpus medullary. Future regions will include the globus pallidus, amygdala, and nucleus accumbens. The command line uses the Slicer3 execution model framework.
+
Back to [[NA-MIC Brains Collaboration]]
  
  
 +
===Summary===
  
'''Progress:'''
+
BRAINSCut is a software package for segmentation of structures using artificial neural networks. Currently this tool supports the segmentation of the following structures: brain, caudate, putamen, thalamus, hippocampus, anterior cerebellum, interior posterior cerebellum, superior posterior cerebellum, corpus medullary. Future regions will include the globus pallidus, amygdala, and nucleus accumbens. The command line uses the Slicer3 execution model framework.
 +
 
 +
 
 +
 
 +
===Progress===
 
#Integration with a high dimensional registration to the atlas probability map
 
#Integration with a high dimensional registration to the atlas probability map
 
#Improved thresholding of the output activation maps
 
#Improved thresholding of the output activation maps
 +
#Code added to NITRC
 +
#Coupled Neural network with MUSH Brain to generate a brain mask without requiring tissue classification
  
  
'''To Do:'''
+
===To Do===
#Link to a BSD style Neural network library
+
#Complete integration with the FANN library
 +
#Link to a BSD style neural network library
 
#Look at the ability to use for segmentation of cortical regions
 
#Look at the ability to use for segmentation of cortical regions
  
  
'''Key Investigators:'''
+
===Key Investigators===
 
* University of Iowa: Hans Johnson, Ronald Pierson, Kent Williams, Greg Harris, Vincent Magnotta
 
* University of Iowa: Hans Johnson, Ronald Pierson, Kent Williams, Greg Harris, Vincent Magnotta
  
'''Figures:'''
 
  
 +
===Figures===
 +
<gallery Caption="BRAINSCut" widths="300px" heights="300px" perrow="2">
 +
Image:BRAINS-ANN-Brain-Subject1-T1.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T1 for Subject 1
 +
Image:BRAINS-ANN-Brain-Subject1-T2.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T2 for Subject 1
 +
 +
Image:BRAINS-ANN-Brain-Subject2-T1.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T1 for Subject 2
 +
Image:BRAINS-ANN-Brain-Subject2-T2.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T2 for Subject 2
  
 +
Image:BRAINS-ANN-Brain-Subject3-T1.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T1 for Subject 3
 +
Image:BRAINS-ANN-Brain-Subject3-T2.png|Brain Mask generated using BRAINSMush image and BRAINSCut overlaid on T2 for Subject 3
 +
</gallery>
  
'''Usage:'''
+
===Usage===
 +
  BRAINSCut  [--processinformationaddress <std::string>] [--xml] [--echo]
 +
              [--applyModel] [--trainModel] [--createVectors]
 +
              [--generateProbability] [--trainModelStartIndex <int>]
 +
              [--netConfiguration <std::string>] [--] [--version] [-h]
 +
 +
  Description: Automatic Segmentation using neural networks
 
    
 
    
 +
  Author(s): Vince Magnotta, Hans Johnson, Greg Harris, Kent Williams
 +
 +
Where:
 +
 +
  --processinformationaddress <std::string>
 +
    Address of a structure to store process information (progress, abort,
 +
    etc.). (default: 0)
 +
 +
  --xml
 +
    Produce xml description of command line arguments (default: 0)
 +
 +
  --echo
 +
    Echo the command line arguments (default: 0)
 +
 +
  --applyModel
 +
    apply the neural net (default: 0)
 +
 +
  --trainModel
 +
    train the neural net (default: 0)
 +
 +
  --createVectors
 +
    create vectors for training neural net (default: 0)
 +
 +
  --generateProbability
 +
    Generate probability map (default: 0)
 +
 +
  --trainModelStartIndex <int>
 +
    Starting iteration for training (default: 0)
 +
 +
  --netConfiguration <std::string>
 +
    XML File defining AutoSegmentation parameters
 +
 +
  --,  --ignore_rest
 +
    Ignores the rest of the labeled arguments following this flag.
 +
 +
  --version
 +
    Displays version information and exits.
 +
 +
  -h,  --help
 +
    Displays usage information and exits.
 +
 +
 
    
 
    
 
+
===Links===
'''Links:'''
 
 
*[http://www.psychiatry.uiowa.edu University of Iowa Department of Psychiatry]
 
*[http://www.psychiatry.uiowa.edu University of Iowa Department of Psychiatry]
 
*[http://mri.radiology.uiowa.edu University of Iowa MRI Center]
 
*[http://mri.radiology.uiowa.edu University of Iowa MRI Center]
  
  
'''Papers:'''
+
===Papers===
 
*Powell S, Magnotta VA, Johnson H, Jammalamadaka VK, Pierson R, Andreasen NC. [http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6WNP-4PGGP30-3&_user=440026&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000020939&_version=1&_urlVersion=0&_userid=440026&md5=c783cac6caa49b7253ab0d08c9da068b Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures].  Neuroimage. 39(1):238-47, 2008.
 
*Powell S, Magnotta VA, Johnson H, Jammalamadaka VK, Pierson R, Andreasen NC. [http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6WNP-4PGGP30-3&_user=440026&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000020939&_version=1&_urlVersion=0&_userid=440026&md5=c783cac6caa49b7253ab0d08c9da068b Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures].  Neuroimage. 39(1):238-47, 2008.
 
*Magnotta VA, Heckel D, Andreasen NC, Cizadlo T, Corson PW, Ehrhardt JC, Yuh WT. [http://radiology.rsnajnls.org/cgi/content/full/211/3/781 Measurement of brain structures with artificial neural networks: two- and three-dimensional applications].  Radiology. 211(3):781-90, 1999.
 
*Magnotta VA, Heckel D, Andreasen NC, Cizadlo T, Corson PW, Ehrhardt JC, Yuh WT. [http://radiology.rsnajnls.org/cgi/content/full/211/3/781 Measurement of brain structures with artificial neural networks: two- and three-dimensional applications].  Radiology. 211(3):781-90, 1999.

Latest revision as of 21:53, 10 December 2008

Home < BRAINSCut

Back to NA-MIC Brains Collaboration


Summary

BRAINSCut is a software package for segmentation of structures using artificial neural networks. Currently this tool supports the segmentation of the following structures: brain, caudate, putamen, thalamus, hippocampus, anterior cerebellum, interior posterior cerebellum, superior posterior cerebellum, corpus medullary. Future regions will include the globus pallidus, amygdala, and nucleus accumbens. The command line uses the Slicer3 execution model framework.


Progress

  1. Integration with a high dimensional registration to the atlas probability map
  2. Improved thresholding of the output activation maps
  3. Code added to NITRC
  4. Coupled Neural network with MUSH Brain to generate a brain mask without requiring tissue classification


To Do

  1. Complete integration with the FANN library
  2. Link to a BSD style neural network library
  3. Look at the ability to use for segmentation of cortical regions


Key Investigators

  • University of Iowa: Hans Johnson, Ronald Pierson, Kent Williams, Greg Harris, Vincent Magnotta


Figures

Usage

 BRAINSCut  [--processinformationaddress <std::string>] [--xml] [--echo]
             [--applyModel] [--trainModel] [--createVectors]
             [--generateProbability] [--trainModelStartIndex <int>]
             [--netConfiguration <std::string>] [--] [--version] [-h]

  Description: Automatic Segmentation using neural networks
 
  Author(s): Vince Magnotta, Hans Johnson, Greg Harris, Kent Williams

Where:

  --processinformationaddress <std::string>
    Address of a structure to store process information (progress, abort,
    etc.). (default: 0)

  --xml
    Produce xml description of command line arguments (default: 0)

  --echo
    Echo the command line arguments (default: 0)

  --applyModel
    apply the neural net (default: 0)

  --trainModel
    train the neural net (default: 0)

  --createVectors
    create vectors for training neural net (default: 0)

  --generateProbability
    Generate probability map (default: 0)

  --trainModelStartIndex <int>
    Starting iteration for training (default: 0)

  --netConfiguration <std::string>
    XML File defining AutoSegmentation parameters

  --,  --ignore_rest
    Ignores the rest of the labeled arguments following this flag.

  --version
    Displays version information and exits.

  -h,  --help
    Displays usage information and exits.


 

Links


Papers