TY - GEN
T1 - Tissue probability map constrained CLASSIC for increased accuracy and robustness in serial image segmentation
AU - Xue, Zhong
AU - Shen, Dinggang
AU - Wong, Stephen T.C.
PY - 2009
Y1 - 2009
N2 - Traditional fuzzy clustering algorithms have been successfully applied in MR image segmentation for quantitative morphological analysis. However, the clustering results might be biased due to the variability of tissue intensities and anatomical structures. For example, clustering-based algorithms tend to over-segment white matter tissues of MR brain images. To solve this problem, we introduce a tissue probability map constrained clustering algorithm and apply it to serialMR brain image segmentation for longitudinal study of human brains. The tissue probability maps consist of segmentation priors obtained from a population and reflect the probability of different tissue types. More accurate image segmentation can be achieved by using these segmentation priors in the clustering algorithm. Experimental results of both simulated longitudinal MR brain data and the Alzheimer's Disease Neuroimaging Initiative (ADNI) data using the new serial image segmentation algorithm in the framework of CLASSIC show more accurate and robust longitudinal measures.
AB - Traditional fuzzy clustering algorithms have been successfully applied in MR image segmentation for quantitative morphological analysis. However, the clustering results might be biased due to the variability of tissue intensities and anatomical structures. For example, clustering-based algorithms tend to over-segment white matter tissues of MR brain images. To solve this problem, we introduce a tissue probability map constrained clustering algorithm and apply it to serialMR brain image segmentation for longitudinal study of human brains. The tissue probability maps consist of segmentation priors obtained from a population and reflect the probability of different tissue types. More accurate image segmentation can be achieved by using these segmentation priors in the clustering algorithm. Experimental results of both simulated longitudinal MR brain data and the Alzheimer's Disease Neuroimaging Initiative (ADNI) data using the new serial image segmentation algorithm in the framework of CLASSIC show more accurate and robust longitudinal measures.
UR - http://www.scopus.com/inward/record.url?scp=71649105331&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=71649105331&partnerID=8YFLogxK
U2 - 10.1117/12.812940
DO - 10.1117/12.812940
M3 - Conference contribution
AN - SCOPUS:71649105331
SN - 9780819475107
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2009 - Image Processing
T2 - Medical Imaging 2009 - Image Processing
Y2 - 8 February 2009 through 10 February 2009
ER -