Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI
Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. However, a fundamental bottleneck in MRI studies of the hippoc...
| Main Authors: | , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Wiley-Blackwell Pubishers
2012
|
| Online Access: | http://hdl.handle.net/1721.1/71591 https://orcid.org/0000-0003-2516-731X |
| _version_ | 1826197916072542208 |
|---|---|
| author | Van Leemput, Koen Bakkour, Akram Benner, Thomas Wiggins, Graham Wald, Lawrence Augustinack, Jean Dickerson, Bradford C. Golland, Polina Fischl, Bruce |
| author2 | Harvard University--MIT Division of Health Sciences and Technology |
| author_facet | Harvard University--MIT Division of Health Sciences and Technology Van Leemput, Koen Bakkour, Akram Benner, Thomas Wiggins, Graham Wald, Lawrence Augustinack, Jean Dickerson, Bradford C. Golland, Polina Fischl, Bruce |
| author_sort | Van Leemput, Koen |
| collection | MIT |
| description | Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. However, a fundamental bottleneck in MRI studies of the hippocampus at the subfield level is that they currently depend on manual segmentation, a laborious process that severely limits the amount of data that can be analyzed. In this article, we present a computational method for segmenting the hippocampal subfields in ultra-high resolution MRI data in a fully automated fashion. Using Bayesian inference, we use a statistical model of image formation around the hippocampal area to obtain automated segmentations. We validate the proposed technique by comparing its segmentations to corresponding manual delineations in ultra-high resolution MRI scans of 10 individuals, and show that automated volume measurements of the larger subfields correlate well with manual volume estimates. Unlike manual segmentations, our automated technique is fully reproducible, and fast enough to enable routine analysis of the hippocampal subfields in large imaging studies. |
| first_indexed | 2024-09-23T10:55:36Z |
| format | Article |
| id | mit-1721.1/71591 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:55:36Z |
| publishDate | 2012 |
| publisher | Wiley-Blackwell Pubishers |
| record_format | dspace |
| spelling | mit-1721.1/715912022-09-30T23:59:52Z Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI Van Leemput, Koen Bakkour, Akram Benner, Thomas Wiggins, Graham Wald, Lawrence Augustinack, Jean Dickerson, Bradford C. Golland, Polina Fischl, Bruce Harvard University--MIT Division of Health Sciences and Technology Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Golland, Polina Van Leemput, Koen Wald, Lawrence Fischl, Bruce Golland, Polina Recent developments in MRI data acquisition technology are starting to yield images that show anatomical features of the hippocampal formation at an unprecedented level of detail, providing the basis for hippocampal subfield measurement. However, a fundamental bottleneck in MRI studies of the hippocampus at the subfield level is that they currently depend on manual segmentation, a laborious process that severely limits the amount of data that can be analyzed. In this article, we present a computational method for segmenting the hippocampal subfields in ultra-high resolution MRI data in a fully automated fashion. Using Bayesian inference, we use a statistical model of image formation around the hippocampal area to obtain automated segmentations. We validate the proposed technique by comparing its segmentations to corresponding manual delineations in ultra-high resolution MRI scans of 10 individuals, and show that automated volume measurements of the larger subfields correlate well with manual volume estimates. Unlike manual segmentations, our automated technique is fully reproducible, and fast enough to enable routine analysis of the hippocampal subfields in large imaging studies. National Institutes of Health (U.S.) (NIH NCRR; Grant number: P41-RR14075) National Institutes of Health (U.S.) (Grant R01 RR16594-01A1) National Institutes of Health (U.S.) (Grant NAC P41-RR13218) Biomedical Informatics Research Network (BIRN002) Biomedical Informatics Research Network (U24 RR021382) National Institute of Biomedical Imaging and Bioengineering (U.S.) (R01 EB001550) National Institute of Biomedical Imaging and Bioengineering (U.S.) (R01EB006758) National Institute of Biomedical Imaging and Bioengineering (U.S.) (NAMIC U54-EB005149) National Institute of Neurological Disorders and Stroke (U.S.) (R01 NS052585-01) National Institute of Neurological Disorders and Stroke (U.S.) (R01 NS051826) Mental Illness and Neuroscience Discovery (MIND) Institute Ellison Medical Foundation (Autism & Dyslexia Project) 2012-07-12T15:25:40Z 2012-07-12T15:25:40Z 2009-05 2009-03 Article http://purl.org/eprint/type/JournalArticle 1050-9631 1098-1063 http://hdl.handle.net/1721.1/71591 Van Leemput, Koen et al. “Automated Segmentation of Hippocampal Subfields from Ultra-high Resolution in Vivo MRI.” Hippocampus 19.6 (2009): 549–557. https://orcid.org/0000-0003-2516-731X en_US http://dx.doi.org/ 10.1002/hipo.20615 Hippocampus Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Wiley-Blackwell Pubishers PubMed Central |
| spellingShingle | Van Leemput, Koen Bakkour, Akram Benner, Thomas Wiggins, Graham Wald, Lawrence Augustinack, Jean Dickerson, Bradford C. Golland, Polina Fischl, Bruce Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title | Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title_full | Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title_fullStr | Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title_full_unstemmed | Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title_short | Automated Segmentation of Hippocampal Subfields From Ultra-High Resolution In Vivo MRI |
| title_sort | automated segmentation of hippocampal subfields from ultra high resolution in vivo mri |
| url | http://hdl.handle.net/1721.1/71591 https://orcid.org/0000-0003-2516-731X |
| work_keys_str_mv | AT vanleemputkoen automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT bakkourakram automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT bennerthomas automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT wigginsgraham automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT waldlawrence automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT augustinackjean automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT dickersonbradfordc automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT gollandpolina automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri AT fischlbruce automatedsegmentationofhippocampalsubfieldsfromultrahighresolutioninvivomri |