Automated White Matter Lesions Segmentation of MRIs for Multiple Sclerosis Detection Using Fuzzy-Entropy Algorithm

Brain magnetic resonance imaging (MRI) scans of patients with multiple sclerosis (MS) are analyzed in this study. Using the fuzzy-entropy algorithm, areas of damaged nerve cells, called lesions, are identified and extracted from the MRI scans. The effectiveness of the proposed method is assessed relative to state-of-the-art image segmentation methods, including improved k-means clustering, fast k-means clustering, modified fuzzy c-means, and adaptive fuzzy clustering. Performance evaluation metrics such as the mean-squared error, peak signal-to-noise ratio, Dice similarity coefficient, Jaccard similarity coefficient, and correlation coefficient demonstrate thffectiveness of the proposed method for segmenting MS lesions from brain MRIs.