DeepMind AI matches experts at detecting over 50 eye diseases

Henrietta Strickland
August 15, 2018

DeepMind also noted that its tech could work with other kinds of eye scanners, so as to help greater numbers of people with a wider range of eye problems.

Initial results, published this month in Nature Medicine, show that the deep learning tool developed by DeepMind and Moorfields Eye Hospital can identify, diagnose, and recommend care for common clinical eye conditions as accurately as human clinicians.

The study, which was conducted by Moorfields Eye Hospital NHS Foundation Trust, the University College London Institute of Ophthalmology, and Google-owned AI firm DeepMind Health, used data from about one million "historic de-personalised eye scans".

But due to the use of OCT scanners, the United Kingdom doesn't have enough expert doctors or trained professionals who can interpret the imagery.

"This functionality is critically important, since eyecare professionals are always going to play a key role in deciding the type of care and treatment a patient receives", Suleyman wrote.

Using deep learning, the research team is able to automatically detect relevant eye features in seconds, and can flag patients at high risk of serious complications to bring their cases to the front of the diagnostic queue. One neural network labels features in OCT images associated with eye diseases, while the other diagnoses eye conditions based on these features.Splitting the task means that - unlike an individual network that makes diagnoses directly from medical imagery - DeepMind's AI isn't a black box whose decision-making rationale is completely opaque to human doctors, Keane said.

In many cases blindness can be prevented by the early detection and treatment of eye diseases such as macular degeneration and glaucoma.

The first of these is that the technology can provide eye-health professionals with information - including visual representations of eye disease - created to explain how the system reaches its referral decisions. Dr Pearse Keane, the senior doctor who lead the Moorfields team working on the project, said in an interview that the hospital "did everything we could" to anonymise the 16,000 eye scans it used both to train and test the algorithms DeepMind developed.

To have this positive level of accuracy the system uses two neural networks.

Two years ago, the hospital system and DeepMind Health announced a five-year partnership to explore whether artificial intelligence could help clinicians improve the care for their patients.

There are still strict clinical trials and regulatory approval for the system to get past before it can be used in practice.

The next step for the company is to get approval for clinical trials and, if it passes this process, it would be made available for free in 30 United Kingdom hospitals for five years.

Dr. Keane called the findings "jaw-dropping" and said the system could be in use by the NHS within three years for "direct patient benefit".

"For all of us who have worked on this since we signed our agreement with Moorfields in 2016, this is a hugely exciting milestone, and another indication of what is possible when clinicians and technologists work together". Unlike many online publications, we don't have a paywall or run banner advertising, because we want to keep our journalism open, without influence or the need to chase traffic.

Other reports by Click Lancashire

Discuss This Article

FOLLOW OUR NEWSPAPER