RETFound: New AI model to detect retinal disease biomarkers developed by Moorfields Eye Hospital
The AI retinal scanning model will be free to use for all institutions
Along with retinal disease, the AI model's imaging capabilities can help diagnose other conditions. Image credit: ©ArticMinimal – stock.adobe.com
Moorfields Eye Hospital and University College London (UCL) Institute of Ophthalmology announced in a press release that they have developed a first-in-the-world artificial intelligence (AI) foundation model for ophthalmology, called RETFound, that was trained on 1.6 million retinal images from the Moorfields Eye Hospital in London.1
In addition to identifying sight-threatening eye diseases, this AI model also can predict more general health challenges, including heart attacks, stroke and Parkinson disease.
In the press release, the investigators behind RETFound explained it was developed to detect markers of disease from retinal images and is able to identify some of the most debilitating eye diseases across diverse populations. The model is being released to the public for free to be used by any institution worldwide, and the hope is that over the coming years, it will form the cornerstone of all research into preventing blindness with AI.
The investigators have published their results in Nature.2
Professor Pearse Keane, senior author of the article, commented, “This is another big step towards using AI to reinvent the eye examination for the 21st century, both in the UK and globally. We show several exemplar conditions where RETFound can be used, but it has the potential to be developed further for hundreds of other sight-threatening eye diseases that we haven’t yet explored.”
The investigators reported that RETFound was trained with a curated dataset of 1.6 million images from Moorfields Eye Hospital. This used AI tools and infrastructure provided by INSIGHT, the National Health Service-led health data research hub for eye health based at Moorfields, and the world’s largest bioresource of ophthalmic data. The hub’s powerful computing and AI capabilities evolved from a 2016 research collaboration between Moorfields and DeepMind, now Google DeepMind.
“If the UK can combine high quality clinical data from the NHS, with top computer science expertise from its universities, it has the true potential to be a world leader in AI-enabled healthcare,” Prof Keane added. “We believe that our work provides a template for how this can be done.”
This project was a collaboration between National Institute for Health and Care Research (NIHR) Moorfields, UCL Hospital and NIHR Birmingham Biomedical Research Centres and brought together the Computer Science and Engineering teams at UCL.
