Segmentation of Hyperintense Regions Applied to Multiple Sclerosis Lesions

摘要

Multiple Sclerosis (MS) is a neurodegenerative disease that is associated with brain tissue damage primarily observed as white matter abnormalities referred to as lesions. MS lesions appear as hyperintense (bright) regions in brain magnetic resonance imaging (MRI). In this study, an automated method for MS lesions segmentation is presented. The proposed method consists of automatic hyper-intense brain tissue segmentation based on the fluid attenuated inversion recovery (FLAIR) image. This work is as a starting stage to describe features and then classify them using learning systems. Therefore, the segmentation method must be highly sensitive. The accuracy of the proposed approach was further validated by comparing lesion volumes computed using the automated approach and lesions manually segmented by an expert radiologist. The results yield a value of sensitivity higher than 95%.