Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/146168
DC Field | Value | |
---|---|---|
dc.title | Tree-metrics graph cuts for brain MRI segmentation with tree cutting | |
dc.contributor.author | Fang R. | |
dc.contributor.author | Chen Y.-H.J. | |
dc.contributor.author | Zabih R. | |
dc.contributor.author | Chen T. | |
dc.date.accessioned | 2018-08-21T05:00:25Z | |
dc.date.available | 2018-08-21T05:00:25Z | |
dc.date.issued | 2010 | |
dc.identifier.citation | Fang R., Chen Y.-H.J., Zabih R., Chen T. (2010). Tree-metrics graph cuts for brain MRI segmentation with tree cutting. 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings : 10-13. ScholarBank@NUS Repository. | |
dc.identifier.isbn | 9781424493005 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/146168 | |
dc.description.abstract | We tackle the problem of brain MRI image segmentation using the tree-metric graph cuts (TM) algorithm, a novel image segmentation algorithm, and introduce a "tree-cutting" method to interpret the labeling returned by the TM algorithm as tissue classification for the input brain MRI image. The approach has three steps: 1) pre-processing, which generates a tree of labels as input to the TM algorithm; 2) a sweep of the TM algorithm, which returns a globally optimal labeling with respect to the tree of labels; 3) post-processing, which involves running the "tree-cutting" method to generate a mapping from labels to tissue classes (GM, WM, CSF), producing a meaningful brain MRI segmentation. The TM algorithm produces a globally optimal labeling on tree metrics in one sweep, unlike conventional methods such as EMS and EM-style geo-cuts, which iterate the expectation maximization algorithm to find hidden patterns and produce only locally optimal labelings. When used with the "tree-cutting" method, the TM algorithm produces brain MRI segmentations that are as good as the Unified Segmentation algorithm used by SPM8, using a much weaker prior. Comparison with the current approaches shows that our method is faster and that our overall segmentation accuracy is better. | |
dc.source | Scopus | |
dc.subject | Brain MRI segmentation | |
dc.subject | Global optimal labeling | |
dc.subject | Tree cutting | |
dc.subject | Tree-metrics graph cuts | |
dc.type | Conference Paper | |
dc.contributor.department | OFFICE OF THE PROVOST | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.sourcetitle | 2010 Western New York Image Processing Workshop, WNYIPW 2010 - Proceedings | |
dc.description.page | 10-13 | |
dc.published.state | published | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.