Segmentation of image ensembles via latent atlases
Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of intere...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Elsevier
2015
|
| Online Access: | http://hdl.handle.net/1721.1/100236 https://orcid.org/0000-0003-2516-731X |
| _version_ | 1811089258283270144 |
|---|---|
| author | Riklin-Raviv, Tammy Van Leemput, Koen Menze, Bjoern H. Golland, Polina Wells, William M. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Riklin-Raviv, Tammy Van Leemput, Koen Menze, Bjoern H. Golland, Polina Wells, William M. |
| author_sort | Riklin-Raviv, Tammy |
| collection | MIT |
| description | Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented. |
| first_indexed | 2024-09-23T14:16:21Z |
| format | Article |
| id | mit-1721.1/100236 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:16:21Z |
| publishDate | 2015 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | mit-1721.1/1002362022-09-28T19:39:03Z Segmentation of image ensembles via latent atlases Riklin-Raviv, Tammy Van Leemput, Koen Menze, Bjoern H. Golland, Polina Wells, William M. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Riklin-Raviv, Tammy Van Leemput, Koen Menze, Bjoern H. Wells, William M. Golland, Polina Spatial priors, such as probabilistic atlases, play an important role in MRI segmentation. However, the availability of comprehensive, reliable and suitable manual segmentations for atlas construction is limited. We therefore propose a method for joint segmentation of corresponding regions of interest in a collection of aligned images that does not require labeled training data. Instead, a latent atlas, initialized by at most a single manual segmentation, is inferred from the evolving segmentations of the ensemble. The algorithm is based on probabilistic principles but is solved using partial differential equations (PDEs) and energy minimization criteria. We evaluate the method on two datasets, segmenting subcortical and cortical structures in a multi-subject study and extracting brain tumors in a single-subject multi-modal longitudinal experiment. We compare the segmentation results to manual segmentations, when those exist, and to the results of a state-of-the-art atlas-based segmentation method. The quality of the results supports the latent atlas as a promising alternative when existing atlases are not compatible with the images to be segmented. National Institutes of Health (U.S.) (National Institute for Biomedical Imaging and Bioengineering (U.S.)/National Alliance for Medical Image Computing (U.S.) U54-EB005149) National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Neuroimaging Analysis Center (U.S.) P41-RR13218) National Institutes of Health (U.S.) (National Institute of Neurological Disorders and Stroke (U.S.) R01-NS051826) National Institutes of Health (U.S.) (National Center for Research Resources (U.S.)/Biomedical Informatics Research Network U24-RR021382) National Science Foundation (U.S.) (CAREER Award 0642971) German Academy of Sciences Leopoldina (Fellowship LPDS 2009-10) Academy of Finland (Grant 133611) 2015-12-14T13:41:42Z 2015-12-14T13:41:42Z 2010-06 Article http://purl.org/eprint/type/JournalArticle 13618415 http://hdl.handle.net/1721.1/100236 Riklin-Raviv, Tammy, Koen Van Leemput, Bjoern H. Menze, William M. Wells III, and Polina Golland. “Segmentation of Image Ensembles via Latent Atlases.” Medical Image Analysis 14, no. 5 (October 2010): 654–665. https://orcid.org/0000-0003-2516-731X en_US http://dx.doi.org/10.1016/j.media.2010.05.004 Medical Image Analysis Creative Commons Attribution-NonCommercial-NoDerivs License http://creativecommons.org/licenses/by-nc-nd/4.0/ application/pdf Elsevier PMC |
| spellingShingle | Riklin-Raviv, Tammy Van Leemput, Koen Menze, Bjoern H. Golland, Polina Wells, William M. Segmentation of image ensembles via latent atlases |
| title | Segmentation of image ensembles via latent atlases |
| title_full | Segmentation of image ensembles via latent atlases |
| title_fullStr | Segmentation of image ensembles via latent atlases |
| title_full_unstemmed | Segmentation of image ensembles via latent atlases |
| title_short | Segmentation of image ensembles via latent atlases |
| title_sort | segmentation of image ensembles via latent atlases |
| url | http://hdl.handle.net/1721.1/100236 https://orcid.org/0000-0003-2516-731X |
| work_keys_str_mv | AT riklinravivtammy segmentationofimageensemblesvialatentatlases AT vanleemputkoen segmentationofimageensemblesvialatentatlases AT menzebjoernh segmentationofimageensemblesvialatentatlases AT gollandpolina segmentationofimageensemblesvialatentatlases AT wellswilliamm segmentationofimageensemblesvialatentatlases |