
Fast 3D Brain Segmentation Using Dual-Front Active Contours with Optional User-Interaction
Li, Hua; Yezzi, Anthony; Cohen, Laurent D. (2005), Fast 3D Brain Segmentation Using Dual-Front Active Contours with Optional User-Interaction, in Liu, Yanxi; Jiang, Tianzi; Zhang, Changshui, Computer Vision for Biomedical Image Applications First International Workshop, CVBIA 2005, Beijing, China, October 21, 2005. Proceedings, Springer : Berlin, p. 335-345. http://dx.doi.org/10.1007/11569541_34
View/ Open
Type
Communication / ConférenceDate
2005Conference title
Computer Vision for Biomedical Image Applications First International Workshop, CVBIA 2005Conference date
2005-10Conference city
BeijingConference country
ChineBook title
Computer Vision for Biomedical Image Applications First International Workshop, CVBIA 2005, Beijing, China, October 21, 2005. ProceedingsBook author
Liu, Yanxi; Jiang, Tianzi; Zhang, ChangshuiPublisher
Springer
Series title
Lecture Notes in Computer ScienceSeries number
3765Published in
Berlin
ISBN
978-3-540-29411-5
Number of pages
563Pages
335-345
Publication identifier
Metadata
Show full item recordAbstract (EN)
Important attributes of 3D brain segmentation algorithms include robustness, accuracy, computational efficiency, and facilitation of user interaction, yet few algorithms incorporate all of these traits. Manual segmentation is highly accurate but tedious and laborious. Most automatic techniques, while less demanding on the user, are much less accurate. It would be useful to employ a fast automatic segmentation procedure to do most of the work but still allow an expert user to interactively guide the segmentation to ensure an accurate final result. We propose a novel 3D brain cortex segmentation procedure utilizing dual-front active contours, which minimize image-based energies in a manner that yields more global minimizers compared to standard active contours. The resulting scheme is not only more robust but much faster and allows the user to guide the final segmentation through simple mouse clicks which add extra seed points. Due to the global nature of the evolution model, single mouse clicks yield corrections to the segmentation that extend far beyond their initial locations, thus minimizing the user effort. Results on 15 simulated and 20 real 3D brain images demonstrate the robustness, accuracy, and speed of our scheme compared with other methods.Subjects / Keywords
3D brain segmentation algorithmsRelated items
Showing items related by title and author.
-
Li, Hua; Yezzi, Anthony; Cohen, Laurent D. (2006) Article accepté pour publication ou publié
-
Chen, Da; Spencer, Jack; Mirebeau, Jean-Marie; Chen, Ke; Shu, Minglei; Cohen, Laurent D. (2021) Article accepté pour publication ou publié
-
Ardon, Roberto; Cohen, Laurent D.; Yezzi, Anthony (2006) Article accepté pour publication ou publié
-
Cohen, Laurent D.; Yezzi, Anthony; Li, Hua (2009) Communication / Conférence
-
Liu, Li; Chen, Da; Cohen, Laurent D.; Wu, Jiasong; Paques, Michel; Shu, Huazhong (2020) Article accepté pour publication ou publié