The Publication Database hosted by SPL
|
All Publications
Upload
Advanced Search
Gallery View
Download Statistics
Help
Import
Log in
Segmentation of Image Ensembles via Latent Atlases
|
|
Institution: |
1Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA. tammy@csail.mit.edu 2Surgical Planning Laboratory, Brigham and Women’s Hospital, Harvard Medical School, USA |
Publisher: |
Elsevier Science |
Publication Date: |
Oct-2010 |
Journal: |
Med Image Anal |
Volume Number: |
14 |
Issue Number: |
5 |
Pages: |
654-65 |
Citation: |
Med Image Anal. 2010 Oct;14(5):654-65. |
PubMed ID: |
20580305 |
PMCID: |
PMC2932709 |
Keywords: |
Latent atlas, Segmentation, MRI, Level-sets, Projects:LatentAtlasSegmentation |
Appears in Collections: |
NAC, NA-MIC, SPL |
Sponsors: |
P41 RR13218 (RR) funded by NCRR NIH HHS R01 NS051826 (NS) funded by NINDS NIH HHS U24 RR021382 (RR) funded by NCRR NIH HHS U54 EB005149 (EB) funded by NIBIB NIH HHS |
Generated Citation: |
Riklin-Raviv T., Van Leemput K., Menze B.H., Wells III W.M., Golland P. Segmentation of Image Ensembles via Latent Atlases. Med Image Anal. 2010 Oct;14(5):654-65. PMID: 20580305. PMCID: PMC2932709. |
| Downloaded: | 86 times. [view map] |
| Paper: | Download, View online |
| Export citation: |
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.
Additional Material
1 File (112.093kB)
Riklin-Raviv-MedIA2010-fig4.jpg (112.093kB)