Abstract
Multiple sclerosis (MS) is a chronic autoimmune disease of the central nervous system that leads to neurodegeneration and functional disability. Because recent advances in retinal imaging have revealed that the retina is a non-invasive window into the brain, offering valuable biomarkers for MS diagnosis and progression tracking, we explored the integration of artificial intelligence (AI), particularly deep learning (DL), in the analysis of fundus-based imaging techniques such as Optical Coherence Tomography (OCT), fundus photography, and Scanning Laser Ophthalmoscopy (SLO). These investigations allow for the detection of subtle retinal changes, such as thinning of the retinal nerve fiber layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL), which are closely associated with MS pathology with the help of AI-driven models, including convolutional neural networks (CNNs), generative adversarial networks (GANs), and explainable AI approaches and they have demonstrated high accuracy in classifying MS patients, even at early stages, and predicting disease severity. The review also discusses the challenges and future directions of applying AI in ophthalmic diagnostics, including data standardization, model interpretability, and clinical integration. Overall, AI-enhanced retinal imaging is emerging as a powerful, non-invasive tool that can complement traditional neurological assessments and support earlier, more personalized MS care.