Segmentation of multiple sclerosis plagues by robust fuzzy clustering with spatial information

In this study, a fuzzy clustering method has been proposed in order to segment brain tissues affected by the multiple sclerosis (MS). In traditional fuzzy clustering, the neighboring relations between pixels have not been taken account of. Additionally, the performance of the clustering reduces drastically because of the pixels having close gray levels due to noise. Therefore, in this study, a novel robust fuzzy clustering algorithm which uses spatial information has been proposed for segmentation of MS plagues. In addition to spatial information, standard deviation dependent filtering is incorporated to the algorithm to achieve better noise immunity. Also, fuzzy clustering is adjusted to be more selective on vertical elliptic objects instead of circular objects since most of the plagues are in this shape.