Abstract:In recent years, the application of artificial intelligence(AI)in ophthalmology has been continuously expanding. AI-assisted analysis of color fundus photography(CFP)and optical coherence tomography(OCT)enables the acquisition of more quantitative data on retinal vasculature, providing assistance in evaluating the systemic vascular status. Although single-modal AI systems(based solely on fundus analysis or OCT images)have achieved certain success, they are unable to simulate the comprehensive judgment process of clinicians who integrate multi-source information. Multimodal AI, which combines structural information from CFP with interlayer information from OCT, can uncover complementary features across different modalities, thereby enhancing diagnostic accuracy and predictive capabilities.This paper provides a systematic review of the application progress of multimodal AI based on CFP and OCT in blinding eye diseases. It outlines the technical foundations, current applications, and clinical value of multimodal AI in conditions such as diabetic retinopathy, age-related macular degeneration, glaucoma, and pathological myopia. Furthermore, the challenges and future directions of multimodal AI are discussed, offering references for ophthalmologists and promoting the development of ophthalmic diagnosis and therapeutic technologies.
