The Publication Database hosted by SPL
|
All Publications
Upload
Advanced Search
Gallery View
Download Statistics
Help
Import
Log in
Keypoint Transfer Segmentation
|
|
Institution: |
1Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA. 2Surgical Planning Laboratory, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA. |
Publisher: |
IPMI 2015 |
Publication Date: |
Jun-2015 |
Journal: |
Inf Process Med Imaging |
Volume Number: |
24 |
Pages: |
233-45 |
Citation: |
Inf Process Med Imaging. 2015 Jun;24:233-45. |
PubMed ID: |
26221677 |
PMCID: |
PMC4526159 |
Appears in Collections: |
NAC, NA-MIC, NCIGT, SPL |
Sponsors: |
P41 EB015898/EB/NIBIB NIH HHS/United States P41 EB015902/EB/NIBIB NIH HHS/United States U54 EB005149/EB/NIBIB NIH HHS/United States |
Generated Citation: |
Wachinger C., Toews M., Langs G., Wells III W.M., Golland P. Keypoint Transfer Segmentation. Inf Process Med Imaging. 2015 Jun;24:233-45. PMID: 26221677. PMCID: PMC4526159. |
| Downloaded: | 487 times. [view map] |
| Paper: | Download, View online |
| Export citation: | |
| Google Scholar: | link |
We present an image segmentation method that transfers label maps of entire organs from the training images to the novel image to be segmented. The transfer is based on sparse correspondences between keypoints that represent automatically identified distinctive image locations. Our segmentation algorithm consists of three steps: (i) keypoint matching, (ii) voting-based keypoint labeling, and (iii) keypoint-based probabilistic transfer of organ label maps. We introduce generative models for the inference of keypoint labels and for image segmentation, where keypoint matches are treated as a latent random variable and are marginalized out as part of the algorithm. We report segmentation results for abdominal organs in whole-body CT and in contrast-enhanced CT images. The accuracy of our method compares favorably to common multi-atlas segmentation while offering a speed-up of about three orders of magnitude. Furthermore, keypoint transfer requires no training phase or registration to an atlas. The algorithm's robustness enables the segmentation of scans with highly variable field-of-view.
Additional Material
1 File (53.73kB)
Wachinger-IPMI2015b-fig4.jpg (53.73kB)