Integrating adaptive probabilistic neural network with level set methods for MR image segmentation

This paper presents a new approach based on adaptive probabilistic neural network (APNN) and level set method for brain segmentation with magnetic resonance imaging (MRI). The APNN is employed to classify the input MR image, and to extract the initial contours. Based on the extracted contours as the initial zero level set contours, the modified level set evolution is performed to accomplish the segmentation. The experimental results demonstrate the effectiveness and robustness of the proposed approach.