Corpus Callosum Segmentation from Brain MRI Images Based on Level Set Method

Abstract

Corpus callosum integrates left and right hemispheres of human brain. There are several methods for segmenting corpus callosum, but the existing algorithms need several steps to segment images. Therefore, we propose a simple method using level set method to segment corpus callosum. We use level set method as it can handle the structure of the brain easily. This method provides a numerical solution for processing changes in topological contours by representing a curve or surface as a zero level to a higher hyper-dimensional surface. This experiment shows that by implementing level set method to segment the corpus callosum produces Dice Similarity Coefficient (DSC) value of 85.14%.