A Fuzzy Consensus Clustering Algorithm for MRI Brain Tissue Segmentation

Brain tissue segmentation is an important component of the clinical diagnosis brain diseases using multi-modal magnetic resonance imaging (MR). has been developed by many unsupervised methods in literature. The most commonly used are K-Means, Expectation-Maximization, and Fuzzy Clustering. clustering offer considerable benefits compared with aforementioned as they capable handling images that complex, largely uncertain, imprecise. However, this approach suffers from intrinsic noise intensity inhomogeneity (IIH) data resulting acquisition process. To resolve these issues, we propose a fuzzy consensus algorithm defines membership function voting schema to cluster pixels. In particular, first pre-process MRI employ several techniques based on traditional sets intuitionistic sets. Then, adopted fuse results applied methods. Finally, evaluate proposed method, well-known performance measures (boundary measure, overlap volume measure) two publicly available datasets (OASIS IBSR18). experimental show superior method comparison recent state art. also presented real-world Autism Spectrum Disorder Detection problem better accuracy other existing