Difference between revisions of "Projects:KnowledgeBasedBayesianSegmentation"

From NAMIC Wiki
Jump to: navigation, search
m (Update from Wiki)
 
 
(27 intermediate revisions by 3 users not shown)
Line 1: Line 1:
  Back to [[NA-MIC_Collaborations|NA-MIC_Collaborations]]
+
  Back to [[NA-MIC_Internal_Collaborations:StructuralImageAnalysis|NA-MIC Collaborations]], [[Algorithm:Stony Brook|Stony Brook University Algorithms]], [[Engineering:Kitware|Kitware Engineering]]
 
+
__NOTOC__
'''Objective:'''
+
= Knowledge Based Bayesian Segmentation =
  
 
This ITK filter is a segmentation algorithm which utilizes Bayes's Rule along with an affine-invarient anisotropic smoothing filter.
 
This ITK filter is a segmentation algorithm which utilizes Bayes's Rule along with an affine-invarient anisotropic smoothing filter.
  
'''Progress:'''
+
= Description =
  
 
''Use Case''
 
''Use Case''
Line 13: Line 13:
 
''Data''
 
''Data''
  
We are using the Harvard structural datasets.
+
We have applied this algorithm to 20 normal brain MRI data-sets. We used publicly available data-sets from
 +
the Internet Brain Segmentation Repository (IBSR) offered by the Massachusetts General Hospital, Center for
 +
Morphometric Analysis. The IBSR data-sets are T1-weighted, 3D coronal brain scans after having been
 +
positionally normalized. Manual expert segmentations for these data-sets are publicly available and represent
 +
the ground truth used in this work.
  
 
''Algorithm''
 
''Algorithm''
 +
 +
This algorithm can be cast in either a static or dynamic framework.  In the static framework, the following is the algorithm:
  
 
# The user sets the number of distinct classes for segmentation: 'N'
 
# The user sets the number of distinct classes for segmentation: 'N'
Line 24: Line 30:
 
# Smooth the posterior images for 'm' iterations using an affine-invarient anisotropic smoothing filter and renormalize after each iteration (default, m = 5) <br />
 
# Smooth the posterior images for 'm' iterations using an affine-invarient anisotropic smoothing filter and renormalize after each iteration (default, m = 5) <br />
 
# Apply maximum a posteriori rule to apply labeling and finalize segmentation
 
# Apply maximum a posteriori rule to apply labeling and finalize segmentation
 +
 +
In the dynamic framework, the following image depicts the adaptation of the static framework to the dynamic formulation:
 +
 +
[[Image:Flowchart-classification.png| Dynamic Tissue Tracking Algorithm | center]]
 +
 +
<br/>
  
 
''The ITK filter design''
 
''The ITK filter design''
  
[[Image:Flowchart.png|[[Image:Flowchart.png| Flowchart]]]]
+
<br/>
 +
 
 +
[[Image:Flowchart.png| Flowchart]]
  
 
''Some Results''
 
''Some Results''
  
* [[Image:Case14raw-crop.png|[[Image:Case14raw-crop.png|RawImage]]]] Raw Image
+
* [[Image:Plot white.png | White Matter Performance on the 20 ISBR datasets | 600px]] WM Algorithm Comparisons
* [[Image:Case14manual-crop.png|[[Image:Case14manual-crop.png|ManualLabels]]]] Manual Labels
+
* [[Image:Plot gray.png | Gray Matter Performance on the 20 ISBR datasets | 600px]] GM Algorithm Comparisons
* [[Image:Case14seg-crop.png|[[Image:Case14seg-crop.png|FilterOutput]]]] Filter Output
+
* [[Image:Fig67.png | Visual Results | 600px]] Visual Results on ISBR data
  
 
''Project Status''
 
''Project Status''
Line 41: Line 55:
 
* The working ITK code has been committed to the [http://www.na-mic.org:8000/svn/NAMICSandBox/BayesianSegmentationModule/ SandBox]
 
* The working ITK code has been committed to the [http://www.na-mic.org:8000/svn/NAMICSandBox/BayesianSegmentationModule/ SandBox]
  
''References:''
+
= Key Investigators =
  
* J. Melonakos, K. Krishnan, and A. Tannenbaum. An ITK Filter for Bayesian Segmentation: itkBayesianClassifierImageFilter. Insight Journal, 2006.
+
* Georgia Tech Algorithms: John Melonakos, Yi Gao, Allen Tannenbaum
* J. Melonakos, R. Al-Hakim, J. Fallon, and A. Tannenbaum. Knowledge-Based Segmentation of Brain MRI Scans Using the Insight Toolkit. Insight Journal, 2005.
+
* Kitware Engineering: Luis Ibanez, Karthik Krishnan
  
'''Key Investigators:'''
+
= Publications =
  
* [[User:Melonakos|John Melonakos]] @ Georgia Tech
+
''In Print''
* Luis Ibanez @ Kitware
+
* [http://www.na-mic.org/publications/pages/display?search=KnowledgeBasedBayesianSegmentation&submit=Search&words=all&title=checked&keywords=checked&authors=checked&abstract=checked&searchbytag=checked&sponsors=checked| NA-MIC Publications Database on Knowledge-Based Bayesian Segmentation]
* Karthik Krishnan @ Kitware
 
  
'''Links:'''
 
  
* [[Algorithm:GATech|Georgia Tech Algorithms]]
+
[[Category: Segmentation]] [[Category:MRI]] [[Category:Slicer]]
* [[NA-MIC_Collaborations|NA-MIC Collaborations]]
 

Latest revision as of 00:56, 16 November 2013

Home < Projects:KnowledgeBasedBayesianSegmentation
Back to NA-MIC Collaborations, Stony Brook University Algorithms, Kitware Engineering

Knowledge Based Bayesian Segmentation

This ITK filter is a segmentation algorithm which utilizes Bayes's Rule along with an affine-invarient anisotropic smoothing filter.

Description

Use Case

I'd like to segment a volume or sub-volume into 'N' classes in a very general manner. I will provide the data and the number of classes that I expect and the algorithm will output a labelmap with 'N' classes.

Data

We have applied this algorithm to 20 normal brain MRI data-sets. We used publicly available data-sets from the Internet Brain Segmentation Repository (IBSR) offered by the Massachusetts General Hospital, Center for Morphometric Analysis. The IBSR data-sets are T1-weighted, 3D coronal brain scans after having been positionally normalized. Manual expert segmentations for these data-sets are publicly available and represent the ground truth used in this work.

Algorithm

This algorithm can be cast in either a static or dynamic framework. In the static framework, the following is the algorithm:

  1. The user sets the number of distinct classes for segmentation: 'N'
  2. Generate 'N' prior images (default, 'N' uniform prior images)
  3. Generate 'N' statistical distributions (default, 'N' normal distributions)
  4. Generate 'N' membership images by applying the statistical distributions to the raw data
  5. Generate 'N' posterior images by applying Bayes' rule to the prior and membership images
  6. Smooth the posterior images for 'm' iterations using an affine-invarient anisotropic smoothing filter and renormalize after each iteration (default, m = 5)
  7. Apply maximum a posteriori rule to apply labeling and finalize segmentation

In the dynamic framework, the following image depicts the adaptation of the static framework to the dynamic formulation:

Dynamic Tissue Tracking Algorithm


The ITK filter design


Flowchart

Some Results

  • White Matter Performance on the 20 ISBR datasets WM Algorithm Comparisons
  • Gray Matter Performance on the 20 ISBR datasets GM Algorithm Comparisons
  • Visual Results Visual Results on ISBR data

Project Status

  • Fully incorporated into itkBayesianClassificationImageFilter and itkBayesianClassificationInitializationImageFilter in ITK CVS.
  • Fully wrapped in VTK for use in Slicer.
  • The working ITK code has been committed to the SandBox

Key Investigators

  • Georgia Tech Algorithms: John Melonakos, Yi Gao, Allen Tannenbaum
  • Kitware Engineering: Luis Ibanez, Karthik Krishnan

Publications

In Print