AI-powered glaucoma test takes just 10 seconds

Monday, 15 November, 2021

AI-powered glaucoma test takes just 10 seconds

Researchers from RMIT University have developed an AI-powered rapid screening test that could help advance early detection of glaucoma, a leading cause of irreversible blindness. The test uses infrared sensors to monitor eye movement and is said to produce accurate results within seconds. It has been described in the journal IEEE Access.

About 80 million people worldwide have glaucoma, yet 50% do not know they have it as the loss of sight is usually gradual. The disease is currently diagnosed through a 30-minute eye pressure test delivered by an ophthalmologist; by contrast, RMIT’s AI-powered test takes just 10 seconds, differentiating between glaucoma and healthy eyes by analysing changes in pupil size.

In the researchers’ study, pupils were measured 60 times per second using a low-cost commercial eye tracker. Under ambient light conditions, patients looked at a computer screen while custom software measured and analysed specific changes in their pupil size. The software then compared the results against existing samples of glaucoma and healthy eyes to determine the risk of glaucoma.

“Our software can measure how the pupil adjusts to ambient light and capture minuscule changes in the shape and size of the pupil,” said study co-author Dr Quoc Cuong Ngo.

“Existing AI glaucoma tests require the patient to be perfectly still for up to 10 minutes. Our tech does the job in 10 seconds, without compromising on accuracy.”

Lead researcher Professor Dinesh Kumar added that early detection, diagnosis and treatment of glaucoma could help prevent blindness, so making screening faster and more accessible is critical.

“This research will allow a non-contact, easy-to-use and low-cost test that can performed routinely at general clinics,” Prof Kumar said.

“It could also promote a community-wide screening program, reaching people who might not otherwise seek treatment until it’s too late.”

The researchers are now looking to adapt the technology to work with smartphone cameras instead of the eye tracker used in the study, and are also looking for a commercial partner ahead of a clinical trial planned for 2022. With further research, they believe software could be extended to detect other neurological conditions.

Image credit: ©

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.

Related News

Machine learning helps to determine leukaemia subtypes

ALLSorts software uses RNA sequencing data to identify a patient's subtype of acute...

AI diagnoses prostate cancer as accurately as specialists

AI systems can diagnose prostate cancer biopsies with the same level of accuracy as specialist...

Computer vision system analyses cells in microscopy videos

The system allows automatic analysis of biomedical videos captured by microscopy in order to...

  • All content Copyright © 2022 Westwick-Farrow Pty Ltd