Difference between revisions of "MedianTexture"

From NAMIC Wiki
Jump to: navigation, search
 
(2 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
__NOTOC__
 
__NOTOC__
 
<gallery>
 
<gallery>
−
Image:PW-MIT2010.png|[[2010_Summer_Project_Week#Projects|Projects List]]
+
Image:2TS0005_stack0001frame0005.png|Original PCNA-GFP fluorescence confocal microscope image for cell cycle marker studies.
−
Image:genuFAp.jpg|Scatter plot of the original FA data through the genu of the corpus callosum of a normal brain.
+
Image:FGPAC_mask_101iter_stack0001frame0005.png|Multiphase GPAC segmentation mask.
−
Image:genuFA.jpg|Regression of FA data; solid line represents the mean and dotted lines the standard deviation.
+
Image:Masked-bkg mbp+2.png|Distribution of MBPs shown with each pattern mapped to a unique color.
 
</gallery>
 
</gallery>
−
 
+
<gallery>
−
==Instructions for Use of this Template==
+
Image:MBP_2TS0005_5U.png|MBP Uniform pattern 5.
−
#Please create a new wiki page with an appropriate title for your project using the convention Project/<Project Name>
+
Image:MBP_2TS0005_6U.png|MBP Uniform pattern 6.
−
#Copy the entire text of this page into the page created above
+
Image:MBP_2TS0005_7U.png|MBP Uniform pattern 7.
−
#Link the created page into the list of projects for the project event
+
</gallery>
−
#Delete this section from the created page
+
<gallery>
−
#Send an email to tkapur at bwh.harvard.edu if you are stuck
+
Image:MBP_2TS0005_8U.png|MBP Uniform pattern 8.
 +
Image:MBP_2TS0005_13U.png|MBP Uniform pattern 13.
 +
Image:MBP_2TS0005_14U.png|MBP Uniform pattern 14.
 +
</gallery>
 +
<gallery>
 +
Image:MBP_2TS0005_15U.png|MBP Uniform pattern 15.
 +
Image:MBP_2TS0005_16U.png|MBP Uniform pattern 16.
 +
Image:MBP_2TS0005_17U.png|MBP Uniform pattern 17.
 +
</gallery>
 +
<gallery>
 +
Image:Mask_2TS0005_-1NU.png|MBP Non-Uniform pattern class.
 +
</gallery>
 +
[[File:MBP-definition.jpg|400px|thumb|left|Definition of MBP]]
  
 
==Key Investigators==
 
==Key Investigators==
−
* UNC: Isabelle Corouge, Casey Goodlett, Guido Gerig
+
* ENSI-Bourges, France: Lucas Menand, Sarah Portugais, Adel Hafiane
−
* Utah: Tom Fletcher, Ross Whitaker
+
* Air Force Research Lab: Guna Seetharaman
 +
* University of Missouri: Filiz Bunyak, K. Palaniappan
 +
* Harvard: Sean Megason
  
 
<div style="margin: 20px;">
 
<div style="margin: 20px;">
−
<div style="width: 27%; float: left; padding-right: 3%;">
+
<div style="width: 40%; float: left; padding-right: 3%;">
  
 
<h3>Objective</h3>
 
<h3>Objective</h3>
−
We are developing methods for analyzing diffusion tensor data along fiber tracts. The goal is to be able to make statistical group comparisons with fiber tracts as a common reference frame for comparison.
+
Median binary patterns (MBP) are robust feature descriptors for characterizing natural and biological textures. MBPs can be used for cell segmentation, characterizing nuclei and membrane textures and for cell classification.
−
 
 
−
 
 
−
 
 
−
 
 
−
 
 
  
 
</div>
 
</div>
  
−
<div style="width: 27%; float: left; padding-right: 3%;">
+
<div style="width: 40%; float: left; padding-right: 3%;">
  
 
<h3>Approach, Plan</h3>
 
<h3>Approach, Plan</h3>
−
 
+
MBPs is a robust alternative to the local binary pattern (LBP) texture descriptors that uses the local median instead of the central pixel intensity as the reference value to create a binary pattern. MBPs (and LBPs) have the attractive properties of noise-resistance, rotation invariance and shift-invariance and provide a powerful feature set for cell segmentation and classification. Using a 3x3 median window there are nine special median uniform patterns and a set of non-uniform patterns that we assign to a separate category.
−
Our approach for analyzing diffusion tensors is summarized in the IPMI 2007 reference below.  The main challenge to this approach is <foo>.
 
−
 
 
−
Our plan for the project week is to first try out <bar>,...
 
  
 
</div>
 
</div>
Line 43: Line 49:
  
 
<h3>Progress</h3>
 
<h3>Progress</h3>
−
Software for the fiber tracking and statistical analysis along the tracts has been implemented. The statistical methods for diffusion tensors are implemented as ITK code as part of the [[NA-MIC/Projects/Diffusion_Image_Analysis/DTI_Software_and_Algorithm_Infrastructure|DTI Software Infrastructure]] project. The methods have been validated on a repeated scan of a healthy individual. This work has been published as a conference paper (MICCAI 2005) and a journal version (MEDIA 2006). Our recent IPMI 2007 paper includes a nonparametric regression method for analyzing data along a fiber tract.
+
We have completed C++ and Matlab implementation of 2D median binary patterns and have a preliminary ITK version that needs to be tested and evaluated for correctness.  
  
 +
</div>
 +
 +
<h3>NA-MIC Week Progress</h3>
 +
* Completed ITK implementation of MBP.
 +
* Histograms of MBPs can be plotted using VTK widgets.
 +
* Remaining work is to build test cases for ITK and write a ITK Journal article.
  
−
</div>
 
 
</div>
 
</div>
  
Line 53: Line 64:
 
==Delivery Mechanism==
 
==Delivery Mechanism==
  
−
This work will be delivered to the NA-MIC Kit as a (please select the appropriate options by noting YES against them below)
+
This work will be delivered to the NA-MIC Kit as an:
−
 
 
 
#ITK Module
 
#ITK Module
−
#Slicer Module
 
−
##Built-in
 
−
##Extension -- commandline
 
−
##Extension -- loadable
 
−
#Other (Please specify)
 
  
 
==References==
 
==References==
−
*Fletcher P, Tao R, Jeong W, Whitaker R. [http://www.na-mic.org/publications/item/view/634 A volumetric approach to quantifying region-to-region white matter connectivity in diffusion tensor MRI.] Inf Process Med Imaging. 2007;20:346-358. PMID: 17633712.
+
*A. Hafiane, G. Seetharaman, K. Palaniappan, B. Zavidovique, “Rotationally invariant hashing of median patterns for texture classification”, Lecture Notes in Computer Science (ICIAR), Vol. 5112, 2008, pp. 619-629. <http://www.ncbi.nlm.nih.gov/pubmed/19116672>
−
* Corouge I, Fletcher P, Joshi S, Gouttard S, Gerig G. [http://www.na-mic.org/publications/item/view/292 Fiber tract-oriented statistics for quantitative diffusion tensor MRI analysis.] Med Image Anal. 2006 Oct;10(5):786-98. PMID: 16926104.
+
 
−
* Corouge I, Fletcher P, Joshi S, Gilmore J, Gerig G. [http://www.na-mic.org/publications/item/view/1122 Fiber tract-oriented statistics for quantitative diffusion tensor MRI analysis.] Int Conf Med Image Comput Comput Assist Interv. 2005;8(Pt 1):131-9. PMID: 16685838.
+
*A. Hafiane, Seetharaman, G., Zavidovique, B.: Median binary pattern for textures classification. Lecture Notes in Computer Science CIAR, 2007, pp. 387–398.
−
* Goodlett C, Corouge I, Jomier M, Gerig G, A Quantitative DTI Fiber Tract Analysis Suite, The Insight Journal, vol. ISC/NAMIC/ MICCAI Workshop on Open-Source Software, 2005, Online publication: http://hdl.handle.net/1926/39 .
+
 
 +
*T. Ojala, Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7), 2002, pp. 971–987.
  
 
</div>
 
</div>

Latest revision as of 23:32, 24 June 2010

Home < MedianTexture

  • Original PCNA-GFP fluorescence confocal microscope image for cell cycle marker studies.

  • Multiphase GPAC segmentation mask.

  • Distribution of MBPs shown with each pattern mapped to a unique color.

  • MBP Uniform pattern 5.

  • MBP Uniform pattern 6.

  • MBP Uniform pattern 7.

  • MBP Uniform pattern 8.

  • MBP Uniform pattern 13.

  • MBP Uniform pattern 14.

  • MBP Uniform pattern 15.

  • MBP Uniform pattern 16.

  • MBP Uniform pattern 17.

  • MBP Non-Uniform pattern class.

Definition of MBP

Key Investigators

  • ENSI-Bourges, France: Lucas Menand, Sarah Portugais, Adel Hafiane
  • Air Force Research Lab: Guna Seetharaman
  • University of Missouri: Filiz Bunyak, K. Palaniappan
  • Harvard: Sean Megason

Objective

Median binary patterns (MBP) are robust feature descriptors for characterizing natural and biological textures. MBPs can be used for cell segmentation, characterizing nuclei and membrane textures and for cell classification.

Approach, Plan

MBPs is a robust alternative to the local binary pattern (LBP) texture descriptors that uses the local median instead of the central pixel intensity as the reference value to create a binary pattern. MBPs (and LBPs) have the attractive properties of noise-resistance, rotation invariance and shift-invariance and provide a powerful feature set for cell segmentation and classification. Using a 3x3 median window there are nine special median uniform patterns and a set of non-uniform patterns that we assign to a separate category.

Progress

We have completed C++ and Matlab implementation of 2D median binary patterns and have a preliminary ITK version that needs to be tested and evaluated for correctness.

NA-MIC Week Progress

  • Completed ITK implementation of MBP.
  • Histograms of MBPs can be plotted using VTK widgets.
  • Remaining work is to build test cases for ITK and write a ITK Journal article.

Delivery Mechanism

This work will be delivered to the NA-MIC Kit as an:

  1. ITK Module

References

  • A. Hafiane, G. Seetharaman, K. Palaniappan, B. Zavidovique, “Rotationally invariant hashing of median patterns for texture classification”, Lecture Notes in Computer Science (ICIAR), Vol. 5112, 2008, pp. 619-629. <http://www.ncbi.nlm.nih.gov/pubmed/19116672>
  • A. Hafiane, Seetharaman, G., Zavidovique, B.: Median binary pattern for textures classification. Lecture Notes in Computer Science CIAR, 2007, pp. 387–398.
  • T. Ojala, Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7), 2002, pp. 971–987.
Retrieved from "https://www.na-mic.org/w/index.php?title=MedianTexture&oldid=55143"