 This paper proposes a deep learning model to distinguish between multiple sclerosis, MS, and neuromyelitis-optica spectrum disorder, NMOSD. The model was trained on five channel images from three D-flare MRI scans, which were selected from five different slices of each scan. The model achieved an accuracy of 76.1%, with a sensitivity of 77.3%, and a specificity of 74.8%. The positive and negative predictive values were 76.9%, and 78.6%, respectively, with an area under the curve of 0.85%. Additionally, the model identified white matter lesions as the main classifier. This model could be used to assist in the differential diagnosis of MS and NMOSD in clinical practice. This article was authored by Jin Myeong-suk, Won Jin-choo, Young Haek-chung, and others.