Artificial intelligence (AI) has been used by researchers to support the instant diagnosis of diabetic retinopathy.
Diabetic retinopathy is the leading cause of blindness among adults and is hard to diagnose in its early stages because there are no symptoms initially.
However, diagnosing the condition before it gets worse is crucial to retaining a person’s vision.
It is because of this that a team of Australian-Brazilian researchers from the RMIT University developed technology that uses an image-processing algorithm to detect fluid on the retina, a key sign of the eye condition.
Lead investigator Professor Dinesh Kant Kumar, RMIT, said: “Our AI-driven approach delivers results that are just as accurate as clinical scans but relies on retinal images that can be generated with ordinary optometry equipment.
“Making it quicker and cheaper to detect this incurable disease could be life changing for the millions of people who are currently undiagnosed and risk losing their sight.”
Two types of scans (fluorescein angiography and optical coherence tomography) are currently the most accurate clinical methods for diagnosing diabetic retinopathy, but these are costly to conduct.
Meanwhile, an alternative and cheaper method of retina analysis exists in the form of equipment called fundas cameras, but the process is less reliable.
The researchers are now trying to find ways to make their technique widespread among screening appointments.
“We know that only half of those with diabetes have regular eye exams and one-third have never been checked. But the gold standard methods of diagnosing diabetic retinopathy are invasive or expensive, and often unavailable in remote or developing parts of the world,” added Prof Kumar.
“This results in millions of people developing preventable and treatable complications from diabetes-related diseases. With further development, our technology has the potential to reduce that burden.”
The research team are now discussing potential partners collaborations with manufacturers in a bid to advance the technology.
The findings have been published in the journal Computers in Biology and Medicine.
