A step closer to an AI-assistant that can detect glaucoma

4 July 2023

Artificial intelligence (AI) can help ophthalmologists recognise glaucoma, the main cause of blindness. Belgian researchers have developed a new AI model and trained it with eye images of patients at UZ Leuven. The algorithm was able to detect glaucoma with high reliability in 13 external datasets from international hospitals, which is very exceptional.

De oogarts maakt foto's van het netvlies om glaucoom vast te stellen

Ophthalmologistogarts prof. dr. Ingeborg Stalmans: “Our study brings us a big step closer to a cost-effective tool that can help doctors worldwide with glaucoma screening in the wide population.  Only a timely diagnosis and treatment can prevent irreversible loss of vision.” (Image: © Shutterstock)

In recent years, many diagnostic AI models for glaucoma detection have been developed worldwide. These often perform well on internal data, but are seldom useable on external data from other centres. This is due to a number of factors, such as the use of different camera's when making the images of the eye, which can lead to variations in exposure. Demographical and ethnic factors also play a role: the dominant glaucoma type in Europe is different from that in Asia.

A different approach

Postdoc researcher Ruben Hemelings: “We chose a different approach and developed a so-called regression-based model based on the cup-to-disc (C/D) ratio, an anatomical measurement of the blind spot in the retina. Higher C/D values are associated with glaucoma. Our new algorithm was trained on a single dataset of about 24,000 pseudonymised retinal images taken at UZ Leuven, but could also detect glaucoma in 13 external datasets with great reliability.”

The model was validated retrospectively on almost 150,000 eye images from six countries, spread over four continents. With a sensitivity of over 85% in two large screening sets, it easily achieved the minimum international criteria.

Only a timely diagnosis and treatment of glaucoma can prevent irreversible loss of vision
Prof. dr. Ingeborg Stalmans, ophthalmologist at UZ Leuven

Next steps

Prof. dr. Ingeborg Stalmans, ophthalmologist at UZ Leuven: “Our study brings us a big step closer to a cost-effective tool that can help doctors worldwide with their glaucoma screening in the wide population. Only a timely diagnosis and treatment can prevent irreversible loss of vision.”

The next hurdle will be a large prospective study, where the AI algorithm will be used to analyse eye images from diverse healthcare centres. That study is of crucial importance to identify and tackle potential technical, logistican and operational challenges before the AI assistant can be widely adopted.

More information

More about "Ophthalmology"

New gene therapy for congenital blindness

16 January 2023
The first gene therapy for hereditary retinal disease, voretigene neparvovec or Luxturna, has recently been approved for use. UZ Leuven doctors have treated a first patient with this new type of gene therapy. If diagnosed in time, Luxturna can prevent further progression of the disorder.
More info
More about "Ophthalmology"

Ophthalmologists, biologists and engineers wage war on Alzheimer's

1 June 2021
Researchers at UZ Leuven, KU Leuven, VITO and imec have published promising results on the use of a hyperspectral camera to detect protein plaques in the eyes of Alzheimer's patients.
More info
More about "Ophthalmology"

Leuven research maps micro-organisms in our eye

5 June 2020
UZ Leuven is currently running one for the first European large-scale trials into the micro-organisms that live on our ocular surface. Researchers hope to get a better insight in specific eye disorders.
More info
Last edit: 15 September 2023