Difference between revisions of "2014 Project Week:CardiacCongenitalSegmentation"

From NAMIC Wiki
Jump to: navigation, search
 
(2 intermediate revisions by the same user not shown)
Line 3: Line 3:
 
Image:PW-SLC2014.png|[[2014_Winter_Project_Week#Projects|Projects List]]
 
Image:PW-SLC2014.png|[[2014_Winter_Project_Week#Projects|Projects List]]
 
Image:Normal_vs_DORV_lrg.gif|Double outlet right ventricle
 
Image:Normal_vs_DORV_lrg.gif|Double outlet right ventricle
 +
Image:carreraScribbles.png|Example input to Carrera on axial slice
 +
Image:carreraOutput.png|Carrera output after manual interaction
 
</gallery>
 
</gallery>
  
Line 30: Line 32:
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Progress</h3>
 
<h3>Progress</h3>
*  
+
* Focused on blood pool segmentation in one test case.  Tried:
 +
** CARMA tools: isolated connected / connected threshold operators
 +
** Editor level tracing effect
 +
** Editor Fast Marching effect
 +
** Editor Grow Cuts effect
 +
** Carrera interactive segmentation
 +
** Robust statistic active contour segmentation
 +
* Best tool = Carrera interactive segmentation
 +
** Main difficulty = small chamber/vessel walls assigned as blood pool, but these can be fixed within Carrera somewhat easily
 +
* Also tried affine registrations across my 5 subjects, using BRAINSFIT
 +
** Works very roughly, as expected
 +
* Next steps:
 +
** Try Carrera on additional datasets for blood pool segmentation
 +
** Myocardium segmentation is still a challenge
 +
* Thanks to: Josh Cates, Salma Bengali, Yi Gao, Ivan Kolesov for your help and suggestions!
 
</div>
 
</div>
 
</div>
 
</div>

Latest revision as of 15:15, 10 January 2014

Home < 2014 Project Week:CardiacCongenitalSegmentation

Key Investigators

Danielle Pace, MIT

Polina Golland, MIT

Project Description

Objective

  • Develop a semi-automatic segmentation algorithm for cardiac MR images of patients with congenital heart defects.
  • Goal is to build a surface model showing the endocardial and epicardial boundaries, for surgical planning.
  • Challenges:
    • Very large inter-subject variability due to heart defects
    • Intensity inhomogeneities within myocardium and blood pool
    • Similar intensity distributions within adjacent tissues (e.g. liver, chest muscle)

Approach, Plan

  • Try existing open-source tools for segmentation and registration on the five datasets that we have so far.
  • See where these methods fail, to focus our efforts for developing algorithms for segmenting hearts with congenital defects.

Progress

  • Focused on blood pool segmentation in one test case. Tried:
    • CARMA tools: isolated connected / connected threshold operators
    • Editor level tracing effect
    • Editor Fast Marching effect
    • Editor Grow Cuts effect
    • Carrera interactive segmentation
    • Robust statistic active contour segmentation
  • Best tool = Carrera interactive segmentation
    • Main difficulty = small chamber/vessel walls assigned as blood pool, but these can be fixed within Carrera somewhat easily
  • Also tried affine registrations across my 5 subjects, using BRAINSFIT
    • Works very roughly, as expected
  • Next steps:
    • Try Carrera on additional datasets for blood pool segmentation
    • Myocardium segmentation is still a challenge
  • Thanks to: Josh Cates, Salma Bengali, Yi Gao, Ivan Kolesov for your help and suggestions!