Brain Tumor Segmentation Using Fuzzy Affinity and Community Structure Detection

The segmentation of brain tumor in MR images is very essential in computer aided diagnosing, which has become a focus in medical research. In this paper, a new segmentation approach of brain tumor which combines the fuzzy affinity technology with the community structure detection technique based on the node similarity is proposed. The presented method consists of the standardization step, the requirement step of the fuzzy affinity, the detection step of the community structure, and a manual verification step, and which can be used in a computer aided diagnosing system. Qualitative and quantitative experiment results show that the proposed algorithm is robust, rapid and accurate.