WML Detection of Brain Images Using Fuzzy and Possibilistic Approach in Feature Space

White matter lesions are small areas of dead cells found in parts of the brain that act as connectors are detected using magnetic resonance imaging (MRI) which has increasingly been an active and challenging research area in computational neuroscience. This paper presents new image segmentation models for automated detection of white matter changes of the brain in an elderly population. The main focus is on unsupervised clustering algorithms. Clustering is a method for dividing scattered groups of data into several groups. It is commonly viewed as an instance of unsupervised learning. In machine learning, unsupervised learning refers to the problem of trying to find hidden structures in unlabeled data. Unsupervised clustering models, Fuzzy c-means clustering, Geostatistical Fuzzy c-means clustering and Geostatistical Possibilistic clustering algorithms partition the dataset into clusters according to some defined distance measure. The Region of Interest (ROI) is then extracted on the membership map. Much more accurate results are obtained by GFCM, which better localized the large regions of WMLs when compared to FCM. Key-Words: Fuzzy clustering, geostatistics, image segmentation, magnetic resonance imaging, possibilistic clustering, white matter changes