TY - JOUR
T1 - Consistent segmentation using a Rician classifier
AU - Roy, Snehashis
AU - Carass, Aaron
AU - Bazin, Pierre Louis
AU - Resnick, Susan
AU - Prince, Jerry L.
N1 - Funding Information:
This research was supported in part by the Intramural Research Program of the NIH, National Institute on Aging. We are grateful to all the participants of the Baltimore Longitudinal Study on Aging (BLSA), as well as the neuroimaging staff for their dedication to these studies. This work was also supported by the NIH/NINDS under Grant 5R01NS037747 .
PY - 2012/2
Y1 - 2012/2
N2 - Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called Rician Classifier using EM (RiCE). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.
AB - Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentation. It is suggested and shown in this paper that a Rician mixture model fits the observed data better than a Gaussian model. Accordingly, a Rician mixture model is formulated and used within an expectation maximization (EM) framework to yield a new tissue classification algorithm called Rician Classifier using EM (RiCE). It is shown using both simulated and real data that RiCE yields comparable or better performance to that of algorithms based on the finite Gaussian mixture model. As well, we show that RiCE yields more consistent segmentation results when used on images of the same individual acquired with different T1-weighted pulse sequences. Therefore, RiCE has the potential to stabilize segmentation results in brain studies involving heterogeneous acquisition sources as is typically found in both multi-center and longitudinal studies.
KW - Biomedical imaging
KW - Medical image segmentation
KW - Rician distribution
KW - Tissue classification
UR - http://www.scopus.com/inward/record.url?scp=84856209241&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84856209241&partnerID=8YFLogxK
U2 - 10.1016/j.media.2011.12.001
DO - 10.1016/j.media.2011.12.001
M3 - Article
C2 - 22204754
AN - SCOPUS:84856209241
SN - 1361-8415
VL - 16
SP - 524
EP - 535
JO - Medical image analysis
JF - Medical image analysis
IS - 2
ER -