Interactive Whole-Heart Segmentation in Congenital Heart Disease
We present an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease. Accurate whole-heart segmentation is necessary to create patient-specific 3D heart models for surgical pl...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
2015
|
| Online Access: | http://hdl.handle.net/1721.1/98882 https://orcid.org/0000-0002-8422-0136 https://orcid.org/0000-0002-5428-9538 https://orcid.org/0000-0003-2516-731X |
| _version_ | 1826214721761574912 |
|---|---|
| author | Pace, Danielle Frances Dalca, Adrian Vasile Geva, Tal Powell, Andrew J. Moghari, Mehdi H. Golland, Polina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Pace, Danielle Frances Dalca, Adrian Vasile Geva, Tal Powell, Andrew J. Moghari, Mehdi H. Golland, Polina |
| author_sort | Pace, Danielle Frances |
| collection | MIT |
| description | We present an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease. Accurate whole-heart segmentation is necessary to create patient-specific 3D heart models for surgical planning in the presence of complex heart defects. Anatomical variability due to congenital defects precludes fully automatic atlas-based segmentation. Our interactive segmentation method exploits expert segmentations of a small set of short-axis slice regions to automatically delineate the remaining volume using patch-based segmentation. We also investigate the potential of active learning to automatically solicit user input in areas where segmentation error is likely to be high. Validation is performed on four subjects with double outlet right ventricle, a severe congenital heart defect. We show that strategies asking the user to manually segment regions of interest within short-axis slices yield higher accuracy with less user input than those querying entire short-axis slice |
| first_indexed | 2024-09-23T16:10:06Z |
| format | Article |
| id | mit-1721.1/98882 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:10:06Z |
| publishDate | 2015 |
| record_format | dspace |
| spelling | mit-1721.1/988822022-10-02T06:47:50Z Interactive Whole-Heart Segmentation in Congenital Heart Disease Pace, Danielle Frances Dalca, Adrian Vasile Geva, Tal Powell, Andrew J. Moghari, Mehdi H. Golland, Polina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Pace, Danielle Frances Pace, Danielle Frances Dalca, Adrian Vasile Golland, Polina We present an interactive algorithm to segment the heart chambers and epicardial surfaces, including the great vessel walls, in pediatric cardiac MRI of congenital heart disease. Accurate whole-heart segmentation is necessary to create patient-specific 3D heart models for surgical planning in the presence of complex heart defects. Anatomical variability due to congenital defects precludes fully automatic atlas-based segmentation. Our interactive segmentation method exploits expert segmentations of a small set of short-axis slice regions to automatically delineate the remaining volume using patch-based segmentation. We also investigate the potential of active learning to automatically solicit user input in areas where segmentation error is likely to be high. Validation is performed on four subjects with double outlet right ventricle, a severe congenital heart defect. We show that strategies asking the user to manually segment regions of interest within short-axis slices yield higher accuracy with less user input than those querying entire short-axis slice Natural Sciences and Engineering Research Council of Canada (Alexander Graham Bell Canada Graduate Scholarships-Doctoral Program (CGS D)) Wistron Corporation National Institute for Biomedical Imaging and Bioengineering (U.S.) (NAMIC U54-EB005149) Boston Children's Hospital (Translational Research Program Fellowship) Boston Children's Hospital. Office of Faculty Development Harvard Catalyst 2015-09-24T13:33:41Z 2015-09-24T13:33:41Z 2015-10 Article http://purl.org/eprint/type/ConferencePaper http://hdl.handle.net/1721.1/98882 Pace, Danielle F., Adrian V. Dalca, Tal Geva, Andrew J. Powell, Mehdi H. Moghari, and Polina Golland. "Interactive Whole-Heart Segmentation in Congenital Heart Disease." 18th International Conference on Medical Image Computing and Computer Assisted Interventions (October 2015). https://orcid.org/0000-0002-8422-0136 https://orcid.org/0000-0002-5428-9538 https://orcid.org/0000-0003-2516-731X en_US http://miccai2015.org/frontend/file.php?id=2351&hash=af9b5 forthcoming in Proceedings of the 18th International Conference on Medical Image Computing and Computer Assisted Interventions Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Pace |
| spellingShingle | Pace, Danielle Frances Dalca, Adrian Vasile Geva, Tal Powell, Andrew J. Moghari, Mehdi H. Golland, Polina Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title | Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title_full | Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title_fullStr | Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title_full_unstemmed | Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title_short | Interactive Whole-Heart Segmentation in Congenital Heart Disease |
| title_sort | interactive whole heart segmentation in congenital heart disease |
| url | http://hdl.handle.net/1721.1/98882 https://orcid.org/0000-0002-8422-0136 https://orcid.org/0000-0002-5428-9538 https://orcid.org/0000-0003-2516-731X |
| work_keys_str_mv | AT pacedaniellefrances interactivewholeheartsegmentationincongenitalheartdisease AT dalcaadrianvasile interactivewholeheartsegmentationincongenitalheartdisease AT gevatal interactivewholeheartsegmentationincongenitalheartdisease AT powellandrewj interactivewholeheartsegmentationincongenitalheartdisease AT mogharimehdih interactivewholeheartsegmentationincongenitalheartdisease AT gollandpolina interactivewholeheartsegmentationincongenitalheartdisease |