IOSR Journal of Dental and Medical Sciences (IOSR-JDMS) e-ISSN: 2279-0853, p-ISSN: 2279-0861.Volume 15, Issue 11 Ver. IV (November. 2016), PP 105-109 www.iosrjournals.org DOI: 10.9790/0853-151104105109 www.iosrjournals.org 105 | Page Characterization of Multiple Sclerosis Lesionin MR Imaging Using Texture Analysis *Simaa Hamid, Mohamed E. M. Gar-Elnabi, Suhaib Alameen College Of Medical Radiological Sciences, Sudan University Of Science and Technology,Khartoum, Sudan Abstract:In this paper we classify of brain tissue using Gray Level Run Length Matrix (GLRLM) to extract classification features from MR images. The techniques used here included elven features to define Multi Sclerosis, White Matter, Grey Matter and CSF were classified further using linear discriminate analysis. The results of the classification showed that the Multi sclerosis tissue classified well from the rest of the tissue although it has characteristics mostly similar to surrounding tissue, several texture features were introduced using Higher Order Statistic. The GLRLM and its features seem very useful in texture classification, and the classification accuracy of multi sclerosis 96.9 %, white matter 93.8 %, grey matter 92.6% and the CSF 100%. Texture parameter from FLAIR images can assess brain inflammatory activity with sufficient accuracy to be considered as a potential alternative to enhancement MR images. Keywords:Multi Sclerosis, White matter, Grey matter, GLRLM, Higher Order Statistics, I. Introduction Multiple sclerosis (MS) is the most common autoimmune disease of the central nervous system, with complex pathophysiology, including inflammation, demyelination, axonal degeneration, and neuronal loss. Within individuals, the clinical manifestations are unpredictable, particularly with regard to the development of disability [1]. And it’s one of the most common causes of neurological disability in young adults. However, different observations in perfusion imaging studies in MS have challenged the interpretation of abnormal perfusion as a reactive phenomenon to inflammation. The occurrence of demyelinating lesions is not inevitably coupled to the presence of a local preceding inflammatory reaction [2,3]. The use of magnetic resonance imaging (MRI) to study the disease has much improved the noninvasive detection of pathology and the study of disease progression, especially in following the evolution of MR-visible white matter (WM) lesions, most of which are clinically silent. Conventional T2-weighted images have been used to assist diagnosis and follow the course of MS, as WM lesions are particularly conspicuous on these images. However, WM lesions do not appear to account for much of the disability associated with MS and pathological changes [4] and quantitative MR abnormalities [5,6] including decreased magnetization transfer ratio (MTR) have been seen in normal-appearing brain tissue (NABT), both in white (NAWM) and gray (NAGM) matter. Texture analysis refers to a set of processes applied to charact erize spatial variations of pixel’s gray levels in an image. Texture analysis which is used to quantify pathological changes that may be undetectable by conventional MRI techniques, has the potential to detect the subtle changes in tissues & supports early diagnosis of MS. Conventional MR examination usually includes fluid attenuated inversion recovery (FLAIR) and T2- weighted (T2-W) imaging for lesion load delineation, together with contrast enhanced (CE) T1-weighted (T1- W) imaging to detect foci of brain blood barrier (BBB) disruption due to local inflammation. Diffusion- weighted imaging (DWI), from which mapping of the apparent diffusion coefficient (ADC) is derived, may give additional information about cell loss and/or ultrastructural disorganization within diseased parenchyma. Though diffuse involvement of the CNS with the MS disease process has been highlighted by histopathological studies, acute inflammatory foci occur, which may be assessed either by the a posteriori demonstration of lesion size enlargement and/or de novo lesion appearance on serial T2-W images at the chronic phase, or by contemporary contrast-enhancement on T1-W images of a single examination at acute phase [7]. The visual texture of ROIs was analyzed using the run length matrix (RLM) [8,9] , eleven texture parameters describing the distribution of runs of gray levels in the image were estimated with the same computation parameters. The RLM method [10,11] quantifies image texture. Basically, a gray level run dictates the number of times two or more pixels having the same value in a preset direction, and the RLM is the matrix of run-length frequency occurring in an image in each (generally 4) direction considered. Features derived from RLM represent fine (long runs) or coarse texture (short runs) of an image.