Local Feature Extraction and Information Bottleneck-Based Segmentation of Brain Magnetic Resonance (MR) Images

Automated tissue segmentation of brain magnetic resonance (MR) images has attracted extensive research attention. Many segmentation algorithms have been proposed for this issue. However, due to the existence of noise and intensity inhomogeneity in brain MR images, the accuracy of the segmentation results is usually unsatisfactory. In this paper, a high-accuracy brain MR image segmentation algorithm based on the information bottleneck (IB) method is presented. In this approach, the MR image is first mapped into a "local-feature space", then the IB method segments the brain MR image through an information theoretic formulation in this local-feature space. It automatically segments the image into several clusters of voxels, by taking the intensity information and spatial information of voxels into account. Then, after the IB-based clustering, each cluster of voxels is classified into one type of brain tissue by threshold methods. The performance of the algorithm is studied based on both simulated and real T1-weighted 3D brain MR images. Our results show that, compared with other well-known brain image segmentation algorithms, the proposed algorithm can improve the accuracy of the segmentation results substantially.