A Novel Distributed Matching Global and Local Fuzzy Clustering (DMGLFC) for 3D Brain Image Segmentation for Tumor Detection

In this paper, we proposed a novel Distribution Matching Global and Local Fuzzy Clustering (DMGLFC) for image segmentation. The proposed DMGLFC targeted 3D MRI brain images for tumor detection. The DMGLFC is involved in the estimation of uncertainties with consideration of different classes. The number of uncertainties is estimated based on the consideration of global entropy and local entropy. The identified voxel in 3D brain MRI images is measured with a fuzzy weighted membership function for the estimation of global entropy. The local entropy measurement utilizes spatial likelihood estimation of fuzzifier weighted membership function. The proposed DMGLFC is involved in the effective segmentation of MRI tumors based on fuzzy objective function entropy measurement. Depending upon the weighted parameters, the tumors present in the 3D images are classified regarding the global and local entropy. The performance of the proposed algorithm is measured in terms of Dice similarity coefficient (DSC), accuracy (Acc), sensitivity (true positive rate), specificity (true negative rate), and Bit Error Rate (BER). Comparative analysis of results expressed that the proposed DMGLFC approach exhibits significant performance rather than the existing technique.