Characterization of Multiple Sclerosis on the Brain Magnetic Resonance Images Using Texture Analysis

Abstract

Multiple Sclerosis (MS) is a chronic autoimmune inflammatory disease of the central nervous system, which can be diagnosed by magnetic resonace imaging (MRI) by evidence of multiple patches wight of scar tissue in different parts of the central nervous system on flair and T2 waightet images.This study is an analytical study, which conducted at Antalia hospital in a period from September 2016 to December 2016 with sample of 50 MR brain images for patient having multiple sclerosis and 50 MR brain images for patient having small vascular disease. the aim of this study was to characterize MS plaques in MR images using Texture analysis which facilitate patteren recognition that might not visible to human eye. The results reveal that the MS areas were very different from the rest of the tissues on FLAIR images with accuracy of 91.2% and on T2 images with classification accuracy of 89.5 %, as well classifiction of MS plaques and SVD were very seperable, with classifiction accuracy of 100% (between both of them) on FLAIR images.