Difference between revisions of "2014 Summer Project Week:Tumor Heterogeneity Analysis"

From NAMIC Wiki
Jump to: navigation, search
(Created page with '__NOTOC__ <gallery> Image:PW-MIT2014.png|Projects List </gallery> ==Key Investigators== *Vivek Narayan *Jayender Jagadeesan ==Project Desc…')
 
Line 15: Line 15:
 
*Create a Slicer module to analyze a segmented tumor and its parameters maps (i.e. k-trans values from DCE-MRI).
 
*Create a Slicer module to analyze a segmented tumor and its parameters maps (i.e. k-trans values from DCE-MRI).
 
*Implement known metrics to extract feature data
 
*Implement known metrics to extract feature data
*Draft a framework to export, visualize, and compare information among cases and identify correlations between tumor phenotypes and image features.
+
*Draft a framework to export, visualize, and compare information among cases
 
</div>
 
</div>
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">

Revision as of 19:47, 20 June 2014

Home < 2014 Summer Project Week:Tumor Heterogeneity Analysis

Key Investigators

  • Vivek Narayan
  • Jayender Jagadeesan

Project Description

HeterogeneityCAD module for Slicer (openCAD Extension): Quantify the heterogeneity of Breast tumors and their parameter maps through several classes of metrics.

Objective

  • Create a Slicer module to analyze a segmented tumor and its parameters maps (i.e. k-trans values from DCE-MRI).
  • Implement known metrics to extract feature data
  • Draft a framework to export, visualize, and compare information among cases

Approach, Plan

  • Design a Slicer module using python and numpy
  • Research and implement various classes of metrics and features: i.e., first-order statistics, morphology/shape, fractal dimensions, geometrical measures, texture-based features
  • Research spatial patterns in Breast tumor phenotypes and gene expression profiles.

Progress

  • Implementing geometric measures and features derived from texture matrices, while researching new metrics.