AI-Driven Retinal Imaging for Alzheimer’s Disease Detection

Alzheimer’s disease (AD) is a devastating neurodegenerative disorder that progressively impairs memory, cognitive function, and the ability to perform everyday activities. As populations age, the prevalence of AD is increasing globally, making early detection crucial for improving treatment outcomes and slowing disease progression. However, current diagnostic methods, such as PET scans and cerebrospinal fluid analysis, are costly, invasive, and not widely available, particularly in low-resource settings. This project aims to develop a non-invasive, affordable solution for early Alzheimer’s detection using retinal fundus imaging. As an extension of the central nervous system, the retina reflects pathological changes in the brain, making it a promising biomarker for detecting neurodegenerative diseases. Recent studies have shown correlations between retinal abnormalities and Alzheimer’s, suggesting that retinal imaging could offer a unique opportunity for early detection. The proposed research will leverage artificial intelligence (AI) to analyse retinal images and identify visual patterns linked to Alzheimer’s disease. In the first phase of the project, an AI model will be trained on a large, publicly available dataset of retinal images that include various retinal diseases and healthy controls. In the second phase, domain adaptation techniques will be applied to adapt the model for Alzheimer’s detection, allowing it to generalise from a smaller dataset of retinal images specific to Alzheimer’s patients. The expected outcome is developing a scalable, non-invasive screening tool that can be integrated into routine eye exams, enabling widespread early diagnosis. This tool could significantly reduce healthcare costs, improve patient outcomes through earlier intervention, and offer a practical solution for Alzheimer’s screening, particularly in underserved communities. By advancing research on retinal biomarkers for neurodegeneration, this project also holds the potential for future breakthroughs in the understanding and treatment of Alzheimer’s disease.

Funder: University of New England
Award Value: $10,000