Imaging Evaluation of Central Nervous Autoimmune Diseases

Multiple sclerosis (MS) is the most common demyelinating disease of the central nervous system and the most common cause of non traumatic disability in young and middle-aged people. Neuromyelitis optica spectrum disease (nmosd) is an independent disease different from Ms. the pathogenesis and the mode of brain and spinal cord injury are different from MS, and the prognosis and optimal treatment are different. It is difficult to distinguish the two diseases in the early stage. Early diagnosis and treatment of the two diseases can greatly improve the quality of life of patients. Therefore, it is an urgent problem to clarify the difference between MS and nmosd injury patterns and to find sensitive imaging markers for early clinical intervention. With the continuous progress of computer aided diagnosis (CAD), it is more and more widely used in medicine, which is expected to help solve the above problems. The purpose of this study is to create a neuroimmune disease evaluation database based on image data. By combining brain and spinal cord imaging, and based on Zhang quantum space learning computer-aided technology, we can achieve accurate segmentation of MS and nmosd brain and spinal cord lesions, analyze the evolution characteristics of the disease at different time points, and screen the imaging indexes related to clinical scores combined with clinical and laboratory indexes Objective: to determine the different prognosis and its influencing factors at the clinical, imaging and molecular levels, and establish the model for predicting disease progression and prognosis, so as to provide the basis for early identification and assistance in guiding treatment and judging prognosis. Clinical information was collected: age, gender, course of disease, MMSE, EDSS disability score, nine hole test, 25 foot walking test. Assess the patient's information processing ability. Blood samples were collected. Imaging examination was performed. The patients were followed up regularly.