Difference between revisions of "BRAINS Automated Pipeline"

From NAMIC Wiki
Jump to: navigation, search
 
(8 intermediate revisions by the same user not shown)
Line 1: Line 1:
 +
Back to [[NA-MIC Brains Collaboration]]
 +
 +
 
'''Objective:'''
 
'''Objective:'''
  
Develop tools to eliminate the need for manual intervention for the analysis of brain morphology using MR images. We currently have a semiautomated pipeline that includes the following steps
+
Develop tools to eliminate the need for manual intervention for the analysis of brain morphology using MR images. We currently have a semiautomated pipeline that includes the following steps:
 
* AC-PC Alignment of T1 Volume
 
* AC-PC Alignment of T1 Volume
 
* Co-registration of T2 weighted images to AC-PC Aligned T1   
 
* Co-registration of T2 weighted images to AC-PC Aligned T1   
Line 10: Line 13:
 
* Surface Generation
 
* Surface Generation
 
* Measurements of Volumetric and Surface Data  
 
* Measurements of Volumetric and Surface Data  
 +
 +
 +
 +
'''Proposed Pipeline:'''
 +
*<font color=blue> Alignment of T2 to raw T1 scan - Use BRAINSFit</font>
 +
*<font color=blue>Brain Extraction - BRAINSMush</font>
 +
*<font color=blue>Tissue Classification - KMeans + Bayesian</font>
 +
*<font color=blue>Bias Field Correction - MRBiasCorrector</font>
 +
*<font color=green>AC-PC Detection T1 - ART</font>
 +
*<font color=red>Resample T1 Image - TBD</font>
 +
*<font color=green>AC-PC Detection T2 - ART</font>
 +
*<font color=green>Alignment of T2 to AC-PC aligned T1 - BrainsFit Initialized with ART results</font>
 +
*<font color=green>Brain Extraction - BRAINSMush + BRAINSCut</font>
 +
*<font color=red>Tissue Classification - TBD</font>
 +
*<font color=red>Talairach Brain Labeling - TBD</font>
 +
*<font color=blue>Neural Network Labeling - BRAINSCut</font>
 +
*<font color=red>Measurements - TBD</font>
 +
*<font color=green>Surface Generation - BrainSurf</font>
 +
*<font color=green>Surface Labeling - TBD</font>
 +
 +
 +
<font color=blue> blue = Complete </font>,
 +
<font color=green> green = In progress </font>,
 +
<font color=red> red = To be done </font>
 +
 +
  
 
'''Progress:'''
 
'''Progress:'''
* A beta version of the automtated workup exists within BRAINS2. We are currently working on building the BRAINS3 command liner interface and the BRAINS2 modules will be ported to BRAINS3 once the TCL commnad line interface exists.
+
*A beta version of the automated workup exists within BRAINS2.  
 +
*BRAINS3 has been created using a TCL command line to connect components from BRAINS2, ITK, and VTK
 +
**Nearly all code is in ITK with a couple of exceptions: ROIs and Talairach Parameters
 +
**Interfaces have been created to seamlessly handle BRAINS and ITK images using ITK filters
 +
**Requires the WrapITK Interface
 +
*Added a few new classes required for wrapping and utilization via the command line
 +
*Added improved interpolation schemes including Sinc and B-Spline
 +
**Will become the standard for images used for tissue classification
 +
 
 +
 
 +
'''To Do:'''
 +
*Refine data types used in WrapITK to decrease the memory footprint
 +
*Improve TCL scripts to verify that memory is being freed appropriately
 +
*Look into loading only certain aspects of ITK when they are needed
 +
*Implement Tissue classification in ITK
 +
*Handle Talairach parameters using VTK structured grids
 +
*Use new ROI format, used by BRAINSTracer, for working with ROIs
 +
*Integrate some features through command line with BRAINSTracer
 +
 
  
 
'''Key Investigators:'''
 
'''Key Investigators:'''
  
* University of Iowa: Vincent Magnotta, Hans Johnson, Nancy Andreasen
+
* University of Iowa: Vincent Magnotta, Hans Johnson, Greg Harris, Wen Li, Steven Dunn, Nancy Andreasen
 
* The MIND Institute: Jeremy Bockholt
 
* The MIND Institute: Jeremy Bockholt
  
Line 26: Line 73:
  
 
'''Papers:'''
 
'''Papers:'''
 +
#Magnotta VA, Harris G, Andreasen NC, O'Leary DS, Yuh WT, Heckel D. [http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6T5K-45CDCB4-1&_user=440026&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000020939&_version=1&_urlVersion=0&_userid=440026&md5=83d35d3c9fad3a23586cbc69bb4a3c01 Structural MR image processing using the BRAINS2 toolbox]. Comput Med Imaging Graph. 26(4):251-64, 2002.
 +
#Harris G, Andreasen NC, Cizadlo T, Bailey JM, Bockholt HJ, Magnotta VA, Arndt S. [http://ovidsp.tx.ovid.com/spb/ovidweb.cgi?QS2=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 Improving tissue classification in MRI: a three-dimensional multispectral discriminant analysis method with automated training class selection]. J Comput Assist Tomogr. 23(1):144-54, 1999.
 +
#Magnotta VA, Andreasen NC, Schultz SK, Harris G, Cizadlo T, Heckel D, Nopoulos P, Flaum M. [http://cercor.oxfordjournals.org/cgi/content/full/9/2/151 Quantitative in vivo measurement of gyrification in the human brain: changes associated with aging]. Cereb Cortex. 9(2):151-60, 1999.
 +
#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.

Latest revision as of 21:18, 10 December 2008

Home < BRAINS Automated Pipeline

Back to NA-MIC Brains Collaboration


Objective:

Develop tools to eliminate the need for manual intervention for the analysis of brain morphology using MR images. We currently have a semiautomated pipeline that includes the following steps:

  • AC-PC Alignment of T1 Volume
  • Co-registration of T2 weighted images to AC-PC Aligned T1
  • Bias Field Correction
  • Tissue Classification
  • Talairach Atlas Segmentation
  • Neural Network Segmentation
  • Surface Generation
  • Measurements of Volumetric and Surface Data


Proposed Pipeline:

  • Alignment of T2 to raw T1 scan - Use BRAINSFit
  • Brain Extraction - BRAINSMush
  • Tissue Classification - KMeans + Bayesian
  • Bias Field Correction - MRBiasCorrector
  • AC-PC Detection T1 - ART
  • Resample T1 Image - TBD
  • AC-PC Detection T2 - ART
  • Alignment of T2 to AC-PC aligned T1 - BrainsFit Initialized with ART results
  • Brain Extraction - BRAINSMush + BRAINSCut
  • Tissue Classification - TBD
  • Talairach Brain Labeling - TBD
  • Neural Network Labeling - BRAINSCut
  • Measurements - TBD
  • Surface Generation - BrainSurf
  • Surface Labeling - TBD


blue = Complete , green = In progress , red = To be done


Progress:

  • A beta version of the automated workup exists within BRAINS2.
  • BRAINS3 has been created using a TCL command line to connect components from BRAINS2, ITK, and VTK
    • Nearly all code is in ITK with a couple of exceptions: ROIs and Talairach Parameters
    • Interfaces have been created to seamlessly handle BRAINS and ITK images using ITK filters
    • Requires the WrapITK Interface
  • Added a few new classes required for wrapping and utilization via the command line
  • Added improved interpolation schemes including Sinc and B-Spline
    • Will become the standard for images used for tissue classification


To Do:

  • Refine data types used in WrapITK to decrease the memory footprint
  • Improve TCL scripts to verify that memory is being freed appropriately
  • Look into loading only certain aspects of ITK when they are needed
  • Implement Tissue classification in ITK
  • Handle Talairach parameters using VTK structured grids
  • Use new ROI format, used by BRAINSTracer, for working with ROIs
  • Integrate some features through command line with BRAINSTracer


Key Investigators:

  • University of Iowa: Vincent Magnotta, Hans Johnson, Greg Harris, Wen Li, Steven Dunn, Nancy Andreasen
  • The MIND Institute: Jeremy Bockholt


Links:

Papers:

  1. Magnotta VA, Harris G, Andreasen NC, O'Leary DS, Yuh WT, Heckel D. Structural MR image processing using the BRAINS2 toolbox. Comput Med Imaging Graph. 26(4):251-64, 2002.
  2. Harris G, Andreasen NC, Cizadlo T, Bailey JM, Bockholt HJ, Magnotta VA, Arndt S. Improving tissue classification in MRI: a three-dimensional multispectral discriminant analysis method with automated training class selection. J Comput Assist Tomogr. 23(1):144-54, 1999.
  3. Magnotta VA, Andreasen NC, Schultz SK, Harris G, Cizadlo T, Heckel D, Nopoulos P, Flaum M. Quantitative in vivo measurement of gyrification in the human brain: changes associated with aging. Cereb Cortex. 9(2):151-60, 1999.
  4. Powell S, Magnotta VA, Johnson H, Jammalamadaka VK, Pierson R, Andreasen NC. Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures. Neuroimage. 39(1):238-47, 2008.
  5. Magnotta VA, Heckel D, Andreasen NC, Cizadlo T, Corson PW, Ehrhardt JC, Yuh WT. Measurement of brain structures with artificial neural networks: two- and three-dimensional applications. Radiology. 211(3):781-90, 1999.