Enhanced Fuzzy C-Means Based Segmentation Technique for Brain Magnetic Resonance Images

Brain tumor is most vital disease which commonly penetrates in the human beings. Studies based on brain tumor confirm that people affected by brain tumors die due to their erroneous detection. In this paper, an enhanced Fuzzy CMeans segmentation (FCM) technique is proposed for detecting brain tumor. To justify the performance of the proposed method, a comparative analysis is being carried out with conventional methods. This technique is an Enhanced version of FCM (EFCM) which incorporates neutrosophic (Ns) set, which is applied in image domain and define some concepts and operations. The input image (G) is transformed into Ns domain, which is described using three subsets namely, True,Intermediate and False (T, I and F). The entropy in neutrosophic set is defined and employed to evaluate the indetermination. FCM clustering is applied to the transformed Ns domain set (Advanced than Fuzzy set). The experimental results demonstrate that the proposed approach detects the tumor region in automatic and effective manner compared to the conventional methods. This EFCM method improves the accuracy rate and reduces error rate of MRI brain tumor.