Texture Characteristic Analysis of MRI for Exploratory Study on Early Diagnosis of Multiple Sclerosis

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system, which leads to focal plaques of demyelination and axonal impairment in the central nervous system. Multiple sclerosis occurred in brain tissue, optic nerve and spinal cord, mainly in brain tissue, which leads to severe progressive neurological dysfunction, such as blindness, paralysis and death. There are about 65,000 patients with MS in China, and recently the incidence rate of MS is increasing, which is the most familiar factor for non-traumatic deformity in the third or fourth decade of life. In this paper, regions of interesting were chosen in MRI T2WI as research object; we used a new neighborhood difference method to analyze the texture features of MRI for patients with MS. Four parameters were extracted from the region of interests by neighborhood difference method. Via screening statistical significant parameters, we found two eigenvectors to represent the sample. We discussed the microcosmic variety of brain white matter throughout extracted texture parameters and found there was significant difference between normal brain white matter and normal appearing white matter, which was proved by the statistical analysis. This study will be beneficial to the research of early diagnosis and treatment estimate of MS.