INTEGRATED FRAMEWORK FOR SIMULTANEOUS SEGMENTATION AND REGISTRATION OF CARPAL BONES

A novel framework is presented in this paper for simultaneous multi-label segmentation and registration of carpal bones which leads to efficient statistical model building. It combines the Grow Cut segmentation algorithm with rigid image registration for propagating the segmentation of bones to new poses or different individuals. The proposed framework compares favourably to the conventional segmentation and nonrigid registration methods, in terms of flexibility and computational time, for our CT data of carpal bones. The segmentation code was implemented in a GPU, running about 15 times faster than CPU code.