A deformable cosegmentation algorithm for brain MR images
Tong Zhang, Yong Xia, Dagan D. Feng · 2012
Cosegmentation aims to simultaneously segment the common parts in a pair of images, and has recently attracted increasing research attention in the field of computer vision. In this paper, we propose a novel deformable cosegmentation (D-C) algorithm to solve the brain MR image segmentation problem by cosegmenting the image and a co-registered atlas. In this manner, the prior heuristic information about brain anatomy that is embedded in the atlas can be transformed into the constraints that control the segmentation of brain MR images. Based on the multiphase Chan-Vese model, the proposed D-C algorithm is implemented using level set techniques. Then, it is compared to the protocol algorithm and the state-of-the-art GA-EM algorithm in T1-weighted brain MR images corrupted by different levels of Gaussian noise and intensity non-uniformity. Our results show that the proposed D-C algorithm can differentiate major brain structures more accuratly and produce more robust segmentation of brain MR images.