Artificial Intelligence in Multimodal Retinal Imaging: A Systematic Review of Diagnostic Applications in Ocular and Systemic Diseases

Abstract

Progress in Artificial Intelligence (AI) has transformed medical imaging, with retinal imaging becoming a crucial diagnostic tool for ocular and systemic illnesses. This systematic review examines the incorporation of AI in multimodal retinal imaging, which includes fundus photography, Optical Coherence Tomography (OCT), OCT angiography, and fluorescein angiography, along with its diagnostic applications for conditions such as diabetic retinopathy, age-related macular degeneration, glaucoma, and systemic diseases like cardiovascular and neurodegenerative disorders. A thorough examination of contemporary AI models reveals elevated sensitivity and specificity, frequently matching or surpassing that of experienced ophthalmologists. The paper emphasises AI’s ability to automate illness detection, improve early diagnosis, and facilitate scalable screening in resource-constrained environments. Nevertheless, obstacles persist, such as restricted dataset heterogeneity, absence of multicentre validation, and complications with clinical integration and algorithm transparency. Future investigations should prioritise the creation of different datasets, the standardisation of validation methodologies, and the development of interpretable AI systems that integrate effortlessly into clinical processes. AI-enhanced multimodal retinal imaging offers substantial potential for revolutionising precision diagnoses in ophthalmology and systemic medicine..

Keywords:Artificial intelligence; Multimodal retinal imaging; Diabetic retinopathy; Systemic diseases; Deep learning