Abstract

We present a fully automated algorithm for tissue segmentation of noisy, low contrast magnetic resonance (MR) images of the brain. We use a mixture model composed of a large number of Gaussians to represent the brain image. Each tissue is represented by a large number of the Gaussian components in order to capture the complex tissue spatial layout. The intensity of a tissue is considered a global feature and is incorporated into the model through parameter tying. The intensity parameter is shared by all the Gaussians that are related to the same tissue. The EM algorithm is utilized to learn the parameter-tied Gaussian mixture model. A new initialization method is applied to guarantee the convergence of the EM algorithm to the global maximum likelihood. Segmentation of the brain image is achieved by the affiliation of each pixel to a selected tissue class. The presented algorithm is used to segment 2D, T1–weighted, simulated and real MR images of the brain into three different tissues, under varying noise conditions. Quantitative results are compared with other segmentation results reported in the literature