Brain Tumor Segmentation of MRI Image using Gustaffson-Kessel (G-K) Fuzzy Clustering Algorithm

Abstract

Image segmentation plays a major role and an important role in the medical field due to its variety of applications especially in Brain tumor analysis. Brain tumor is an abnormal and uncontrolled growth of cells. It takes up space within the skull. It can compress, shift and harm healthy brain tissue and nerves. Also usually it obstruct with normal brain function. Tumors can be benign (non-cancerous) or malignant (cancerous), can happen in different parts of the brain. Brain tumor classification and identification from Magnetic Resonance (MR) data is an essential. But it takes time and manual task completed by medical specialists. Computerizing this task is a challenging because of the high variety in the look of tumor tissues among different patients and in many cases similarity with the normal tissues. In this work, brain tumor image has been segmented using proposed Gustafson-Kessel (G-K) fuzzy clustering algorithm. The performance of G-K segmentation method is compared with those of watershed and FCM algorithms.