DMCA
CLASSIC: consistent longitudinal alignment and segmentation for serial image computing (2006)
Cached
Download Links
- [www.med.unc.edu]
- [www.med.unc.edu]
- [www.med.unc.edu]
- [www.med.unc.edu]
- [www.med.unc.edu]
- [www.med.unc.edu]
- [www.med.unc.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | NeuroImage |
| Citations: | 38 - 15 self |
BibTeX
@ARTICLE{Xue06classic:consistent,
author = {Zhong Xue and Dinggang Shen and Christos Davatzikos},
title = {CLASSIC: consistent longitudinal alignment and segmentation for serial image computing},
journal = {NeuroImage},
year = {2006},
pages = {388--399}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. This paper proposes a temporally-consistent and spatiallyadaptive 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. 1
Keyphrases
consistent longitudinal alignment serial image global brain volume image-adaptive clustering 3-d mr brain image accurate measurement longitudinal consistency image warping morphological change spatiotemporal smoothness constraint serial mr image segmentation accuracy experimental result real longitudinal mr brain image undergoing change
