Artificial Intelligence in Retinal Imaging for Early Alzheimer’s Disease Detection: A Systematic Review

Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder that necessitates early, accessible, and non-invasive diagnostic methods. This review explores the potential of AI-driven retinal imaging as a transformative tool for early AD detection. Advancements in optical coherence tomography (OCT), retinal fundus imaging (RFI), and OCT angiography (OCTA) are examined, highlighting their ability to capture structural and vascular biomarkers such as retinal nerve fiber layer (RNFL) thinning and microvascular alterations. AI models—including convolutional neural networks (CNNs), Vision Transformers (ViTs), and hybrid architectures—are critically evaluated for their accuracy in retinal biomarker analysis. Benchmark datasets, including ROSE , ADNI and UK Biobank, are analyzed to underscore their role in AI-driven AD research. Despite notable advancements, challenges such as data heterogeneity, computational complexity, and model interpretability persist. Emerging trends, including multimodal data integration and federated learning, offer promising solutions for enhancing diagnostic accuracy and privacy. This review synthesizes recent advancements, challenges, and future directions, emphasizing the potential of AI-driven retinal imaging in facilitating early AD diagnosis and improved patient outcomes.