Difference between revisions of "2014 Summer Project Week:Cardiac-Congenital"

From NAMIC Wiki
Jump to: navigation, search
 
(2 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
<gallery>
 
<gallery>
 
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
 
Image:PW-MIT2014.png|[[2014_Summer_Project_Week#Projects|Projects List]]
Image:WMH_T1.png|Clinical Stroke Image
+
Image:CongenitalHeartModelsSlicer.png|Results of patch-based segmentation
Image:WMH_T1.png|Clinical Stroke Image
+
Image:CongenitalHeartModels.png|Patient-specific heart model
Image:WMH_T1.png|Clinical Stroke Image
+
Image:CongenitalHeartModels2.png|Printed model
  
 
</gallery>
 
</gallery>
Line 36: Line 36:
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<div style="width: 27%; float: left; padding-right: 3%;">
 
<h3>Progress</h3>
 
<h3>Progress</h3>
*
+
* Did manual initial segmentations and and ran patch-based segmentation on additional datasets.
 
</div>
 
</div>
 
</div>
 
</div>

Latest revision as of 04:32, 27 June 2014

Home < 2014 Summer Project Week:Cardiac-Congenital

Key Investigators

  • Danielle Pace, MIT
  • Adrian Dalca, MIT
  • Polina Golland, MIT

Project Description

This project involves semi-automatic segmentation of gated 3D magnetic resonance images of hearts with congenital heart defects. Our aim is to create patient-specific heart models for surgical planning, which can be viewed either graphically on a computer, or with a 3D printer to create a physical model for surgeons.

We have had initial success in significantly reducing segmentation time with the following pipeline: 1) User manually segments ~10 axial slices 2) Segment the remaining slices using patch-based majority voting.

Objective

  • Continue testing the patch based methods on an additional five datasets.
  • Address main remaining challenge: segmenting thin interior heart walls.

Approach, Plan

  • Manually segment ~10 axial slices for each of the five additional datasets.
  • Explore remaining parameters for the patch-based segmentation: e.g. weighted voting, varying k in k-nearest neighbors patch lookup

Progress

  • Did manual initial segmentations and and ran patch-based segmentation on additional datasets.