close up photo of retina in eye with glaucoma

Ophthalmoscope view of a retina showing an optical disk (yellow, center) and blood vessels crossing

Science Source

Glaucoma is a surprisingly common condition that can have serious consequences if it goes untreated. Understanding the importance of early detection, a team of engineers and ophthalmologists in Australia has developed a novel approach using AI to diagnose glaucoma that can yield results in just 10 seconds.

Glaucoma is a condition whereby pressure builds in up within the eye, which in turn can put pressure on the optical nerve. If the optical nerve is affected like this for a prolonged period of time, it can result in permanent damage and vision impairment. Glaucoma can be treated with medication, but first it must be detected.

Diagnosing glaucoma typically involves a 30-minute test with an ophthalmologist or a visit to a specialized optometry clinic. However, not everyone has access to such specialists.

In the hopes of finding an easier way to diagnose glaucoma, Dinesh Kumar, a professor at the Royal Melbourne Institute of Technology (RMIT), and his colleagues sought to develop a new approach that relies on AI and the fact that glaucoma alters the way in which a person's pupil responds to light.

They gathered a small group of study participants, 13 of whom were known to have glaucoma, 13 healthy controls, and 13 younger participants. The volunteers' eyes were imaged at 60 frames per second as they focused on a point under ambient light conditions, and then a machine learning algorithm was applied to the data to detect minute changes in pupil dilation of the glaucoma group compared to the healthy controls. From this work, the researchers developed a model for diagnosing glaucoma, which is described in a study published October 22 in IEEE Access.

"Our software can measure how the pupil adjusts to ambient light and capture minuscule changes in the size of the pupil," explains Quoc Cuong Ngo, a research assistant at RMIT involved in the study, in a press release. "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."

The advancement has the potential to help millions of people around the world who are at risk of developing glaucoma, and especially those over the age of 60 who are at higher risk.

"This research will allow a non-contact, easy-to-use and low-cost test that can performed routinely at general clinics," says Kumar. "It could also promote a community-wide screening program, reaching people who might not otherwise seek treatment until it's too late."

Kumar says that, although a specialized eye-tracker was used in this study, he envisions this approach one day being used through a simple app on a smartphone, a possibility that the team plans to explore in the near future. His team is also interested in testing their approach through a clinical trial in the coming year.

The Conversation (1)
Paul Quillen18 Nov, 2021
M

The title of this article should not mention AI since it's clearly machine learning. Machine learning is not AI.

Will AI Steal Submarines’ Stealth?

Better detection will make the oceans transparent—and perhaps doom mutually assured destruction

11 min read
A photo of a submarine in the water under a partly cloudy sky.

The Virginia-class fast attack submarine USS Virginia cruises through the Mediterranean in 2010. Back then, it could effectively disappear just by diving.

U.S. Navy

Submarines are valued primarily for their ability to hide. The assurance that submarines would likely survive the first missile strike in a nuclear war and thus be able to respond by launching missiles in a second strike is key to the strategy of deterrence known as mutually assured destruction. Any new technology that might render the oceans effectively transparent, making it trivial to spot lurking submarines, could thus undermine the peace of the world. For nearly a century, naval engineers have striven to develop ever-faster, ever-quieter submarines. But they have worked just as hard at advancing a wide array of radar, sonar, and other technologies designed to detect, target, and eliminate enemy submarines.

The balance seemed to turn with the emergence of nuclear-powered submarines in the early 1960s. In a 2015 study for the Center for Strategic and Budgetary Assessment, Bryan Clark, a naval specialist now at the Hudson Institute, noted that the ability of these boats to remain submerged for long periods of time made them “nearly impossible to find with radar and active sonar.” But even these stealthy submarines produce subtle, very-low-frequency noises that can be picked up from far away by networks of acoustic hydrophone arrays mounted to the seafloor.

Keep Reading ↓Show less
{"imageShortcodeIds":["30133857"]}