Difference between revisions of "2016 Winter Project Week/Projects/CongenitalHeart"
From NAMIC Wiki
| (One intermediate revision by the same user not shown) | |||
| Line 24: | Line 24: | ||
| | | | ||
<!-- Approach and Plan bullet points --> | <!-- Approach and Plan bullet points --> | ||
| − | * | + | * Continue investigating algorithm modifications to enhance / correctly segment the thin walls. |
| | | | ||
<!-- Progress and Next steps bullet points (fill out at the end of project week --> | <!-- Progress and Next steps bullet points (fill out at the end of project week --> | ||
| − | * | + | * Worked on integrating new "thin wall" features to improve thin wall detection |
|} | |} | ||
==Background and References== | ==Background and References== | ||
* [http://link.springer.com/chapter/10.1007/978-3-319-24574-4_10 Pace et al,, Interactive Whole-Heart Segmentation in Congenital Heart Disease, MICCAI 2015] | * [http://link.springer.com/chapter/10.1007/978-3-319-24574-4_10 Pace et al,, Interactive Whole-Heart Segmentation in Congenital Heart Disease, MICCAI 2015] | ||
Latest revision as of 15:01, 8 January 2016
Home < 2016 Winter Project Week < Projects < CongenitalHeart
Results after user manually segments 3, 8 or 14 slices
Key Investigators
- Danielle Pace (MIT)
- Adrian Dalca (MIT)
- Polina Golland (MIT)
Project Description
- We have developed an interactive segmentation algorithm for cardiac MR images from patients with severe congenital heart disease, in which the user manually segments a few short-axis slices and the remainder is segmented automatically using patch-based segmentation (Pace et al, MICCAI 2015)
| Objective | Approach and Plan | Progress and Next Steps |
|---|---|---|
|
|
|
