Segmentation of Brain Subjects in MR Images using Hybrid Segmentation Technique

• Published in: International journal of engineering and advanced technology Vol. 9; no. 1s4; pp. 724 - 728
• Main Authors: Kumar, P. Rajesh, Prasath, T. Arun, Rajasekaran, M. Pallikonda, Vishnuvarathanan, G.
• Format: Journal Article
• Language: English
• Published: 30.12.2019
• ISSN: 2249-8958; 2249-8958
• DOI: 10.35940/ijeat.A1131.1291S419

Image segmentation takes place a vital role in the area of biomedical applications. Magnetic resonance brain images with and without Alzheimer’s disease have been preferred for the detection and staging the AD. Clustering is one of the extensively implemented image segmentation principle which differentiates group in such a way that samples of the relevant group are related to each other than samples associated to various groups. There has been significant concern recently in the utilization of fuzzy clustering methods, which keep additional information from the input image than the clustering principle. Modified Fuzzy C Means (MFCM) algorithm is extensively preferable because of its flexibility which leads the pixels to exist to various classes with changing the degrees of membership. Cluster initialization process has been done with MFCM and the performance of the segmentation algorithm has enhanced with Binary Gravitational search algorithm. Various brain subjects such as White Matter (WM), Grey matter (GM), hippocampus region, Cerebrospinal Fluid (CSF) are segmented for the detection of AD. The BGSA with MFCM algorithm has achieved better outcomes and it is compared with various existing techniques. The accuracy of the proposed technique is about 93.3%.