Abstract
Multiple sclerosis is a chronic inflammatory disease of the central nervous system. Lesions detected by Magnetic resonance (MR) sequences not only confirme the diagnosis of MS, but let monitor them to determine the evolutionary state of the disease and to evaluate the therapeutic efficiency. Thus, the change in lesion load is a criterion determining the degree of progress of the disease in volume, shape and location. For this purpose, a segmentation of these lesions becomes paramount. Some recent methods of semiautomatic and automatic segmentation have been proposed to get rid of complex and laborious manual segmentation. Subsequently, the variability inter and intra-experts will be reduced.
The purpose of this study is to accomplish a brief review of MS lesions segmentation methods proposed in the literature.