An Insight Toolkit (ITK) filter for image segmentation with applications to brain MRI scans is presented in this paper. Previously, we showed how ITK could be used to implement our algorithm. This paper presents our new ITK filter for Bayesian segmentation along with results on brain MRI scans. Our algorithm is a refinement of the work of Teo, Saprio, and Wandall. The basic idea is to incorporate prior knowledge into the segmentation through Bayes rule. Image noise is removed via an affine invariant anisotropic smoothing of the posteriors as in Haker et. al. Specifically, we present the implementation of our Bayesian segmentation algorithm applied to brain MRI scans.
Affine Invariant Image Segmentation