Segmentation of medical images through competitive learning

A novel approach to medical image segmentation that combines local contrast as well as global feature information is presented. The method adaptively learns useful features and regions through the use of a normalized contrast function as a measure of local information and a competitive learning-based method to update region segmentation incorporating global information about the gray-level distribution of the image. The framework of such a self-organizing feature map is presented, and the results on simulated as well as real medical images are shown