Difference between revisions of "2009 Summer Project Week Project Segmentation of Muscoskeletal Images"

From NAMIC Wiki
Jump to: navigation, search
Line 23: Line 23:
  
 
<h3>Approach, Plan</h3>
 
<h3>Approach, Plan</h3>
−
We focus on developing library of atlases for specific joints (eg: the knee) and evaluating EM Segmenter Algorithms. The main challenge during this process is the study of techniques for registration of a patient MRI image to a given patient MRI image (for which we already have atlas). Our approach to achieve this is to conduct parameter exploration study using the module '''Register Images Batchmake''' in Slicer 3.4
+
We are working on understanding the capabilities of RegisterImage module in Slicer to apply to knee datasets. Currently we are conducting parameter exploration studies to evaluate the sensitivity of registered images to different input parameters associated with the algorithms. We are also developing a module to apply python ICP-based registration algorithms to directly morph a surface model to a target image geometry.
−
 
 
−
We are also investigating another technique where we try to register a given knee model to a patient MRI Image using '''Python ICP Registration'''.
 
  
 
Our plan for the project week is to  
 
Our plan for the project week is to  

Revision as of 17:10, 29 May 2009

Home < 2009 Summer Project Week Project Segmentation of Muscoskeletal Images

  • Knee MRI Image

  • Pre-Segmented Femur/Patella/Tibia Model.

  • EM Segmented Output.


Key Investigators

  • Stanford: Harish Doddi, Saikat Pal, Scott Delp
  • Harvard: Ron Kikinis
  • Steve Pieper, Isomics, Inc.

Objective

The aim of this project is to develop an automatic/semi-automatic methodology to convert whole body imaging datasets into three-dimensional models for neuromuscular biomechanics and finite element simulations.

Approach, Plan

We are working on understanding the capabilities of RegisterImage module in Slicer to apply to knee datasets. Currently we are conducting parameter exploration studies to evaluate the sensitivity of registered images to different input parameters associated with the algorithms. We are also developing a module to apply python ICP-based registration algorithms to directly morph a surface model to a target image geometry.

Our plan for the project week is to 

 a. Perform and evaluate results from an extensive 
 parameter space exploration study of 
 RegisterImages Batchmake module on knee dataset.
 b. Resolve issues in building Python modules from 
 slicer source code.
 c. Demonstrate proof of concept on registering an 
 existing atlas (.vtk, .stl) to a target image 
 using Python ICP Registration module.

Progress


Retrieved from "https://www.na-mic.org/w/index.php?title=2009_Summer_Project_Week_Project_Segmentation_of_Muscoskeletal_Images&oldid=37877"