Abstract
This paper proposes a temporally-consistent and spatially-adaptive longitudinal MR brain image segmentation algorithm, referred to as CLASSIC, which aims at obtaining accurate measurements of rates of change of regional and global brain volumes from serial MR images. The algorithm incorporates image-adaptive clustering, spatiotemporal smoothness constraints, and image warping to jointly segment a series of 3-D MR brain images of the same subject that might be undergoing changes due to development, aging or disease. Morphological changes, such as growth or atrophy, are also estimated as part of the algorithm. Experimental results on simulated and real longitudinal MR brain images show both segmentation accuracy and longitudinal consistency.
Original language | English (US) |
---|---|
Title of host publication | Lecture Notes in Computer Science |
Editors | G.E. Christensen, M. Sonka |
Pages | 101-113 |
Number of pages | 13 |
Volume | 3565 |
State | Published - 2005 |
Event | 19th International Conference on Information Processing in Medical Imaging, IPMI 2005 - Glenwood Springs, CO, United States Duration: Jul 10 2005 → Jul 15 2005 |
Other
Other | 19th International Conference on Information Processing in Medical Imaging, IPMI 2005 |
---|---|
Country/Territory | United States |
City | Glenwood Springs, CO |
Period | 7/10/05 → 7/15/05 |
ASJC Scopus subject areas
- Computer Science (miscellaneous)