CLASSIC: Consistent longitudinal alignment and segmentation for serial image computing

Zhong Xue, Dinggang Shen, Christos Davatzikos

Research output: Contribution to journalConference articlepeer-review

7 Citations (Scopus)


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 languageEnglish
Pages (from-to)101-113
Number of pages13
JournalLecture Notes in Computer Science
Publication statusPublished - 2005
Externally publishedYes
Event19th International Conference on Information Processing in Medical Imaging, IPMI 2005 - Glenwood Springs, CO, United States
Duration: 2005 Jul 102005 Jul 15

Bibliographical note

Funding Information:
This work was supported in part by grants R01AG14971, N01-AG32124-09. We thank Dr. Dzung Pham and Dr. Jerry Prince from Johns Hopkins University for providing the software of the FANTASM algorithm and Dr. Susan Resnick from NIH for access to the BLSA data.

Copyright 2020 Elsevier B.V., All rights reserved.

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'CLASSIC: Consistent longitudinal alignment and segmentation for serial image computing'. Together they form a unique fingerprint.

Cite this