AI-Powered Retinal Maps Reveal New Disease Insights

A WEHI-led study has produced high-resolution retinal maps using artificial intelligence (AI) technology, revealing new insights into how retinal thickness is linked to diseases such as type 2 diabetes, dementia, and multiple sclerosis.

Analyzing data from over 50,000 eyes, this study is one of the largest of its kind globally. The findings, published in Nature Communications under the title "Multi-omic spatial effects on high-resolution AI-derived retinal thickness", pave the way for using routine retinal imaging as a diagnostic tool, much like mammograms for breast cancer screening.

Retinal Imaging: A Window to the Brain

The retina is part of the central nervous system (CNS), which also includes the brain and spinal cord. Many neurological and metabolic diseases are associated with CNS degeneration, making retinal imaging a valuable tool for early disease detection and management.

Globally, neurological conditions are a leading cause of disability, affecting over 3 billion people, or 43% of the world’s population.

Dr. Vicki Jackson, lead researcher at WEHI, emphasized the significance of these findings:

"We've shown that retinal imaging can act as a window to the brain, by detecting associations with neurological disorders like multiple sclerosis and many other conditions.”

The study also identified new genetic factors influencing retinal thickness, providing insights into retinal growth and development and its role in disease progression.

"Our maps' fine-scale measurements reveal critical new details about connections between retinal thinning and a range of common conditions," Dr. Jackson added.

These findings suggest that retinal thickness could serve as a biomarker to aid in early disease detection and monitoring.

AI-Powered Insights Into Retinal Structure and Disease Links

The research team leveraged AI-driven methods to analyze big population data from retinal imaging, correlating genetic and health information to uncover previously unknown disease links.

Key findings include:

• 50,000 high-resolution retinal maps with measurements at over 29,000 locations across the retina.

• Identification of 294 genes linked to retinal thinning, many of which play a crucial role in disease progression.

The Role of AI in Revolutionizing Retinal Diagnostics

Professor Melanie Bahlo AM, study lead and bioinformatician, highlighted the impact of AI in transforming retinal imaging into a powerful diagnostic tool:

"Technologies like AI fuel discovery, and when fused with brilliant minds, there is an extraordinary ability to transform big population data into far-reaching insights. There has never been a time in history where this powerful combination—technology, big data, and brilliant minds—has come together to advance human health."

Retinal Imaging and the Future of Oculomics

This research reinforces the growing field of oculomics, where retinal imaging is used to diagnose systemic health conditions. As a non-invasive and highly effective approach, oculomics has the potential to revolutionize predictive medicine, allowing clinicians to detect and monitor neurological and metabolic diseases through a simple eye scan.

Conclusion

By harnessing high-resolution AI-powered retinal maps, this study marks a major step forward in retinal imaging as a diagnostic tool. With its ability to reveal disease associations early, retinal thickness measurement could soon become a critical part of routine healthcare, enabling early intervention and improved patient outcomes.

Reference:

V. E. Jackson et al, Multi-omic spatial effects on high-resolution AI-derived retinal thickness, Nature Communications (2025). DOI: 10.1038/s41467-024-55635-7