Australian AI used to diagnose diabetic retinopathy

The method uses an AI-generated process to examine retinal fundus images for exudate and can detect fluid on the eye with 98% accuracy. The researchers claim the process is instantaneous, eliminating the time-consuming process of manually checking the images.It’s also said to be less expensive than current methods to detect diabetic retinopathy, such as fluorescein angiography and OCT scans.“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,” lead investigator on the project Professor Dinesh Kant Kumar from RMIT University said.{{quote-A:R-W:400-I:2-Q:“Our AI-driven approach delivers results that are just as accurate as clinical scans.” -who:Dinesh Kant Kumar, RMIT}}“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.”Researchers expect the syst will be particularly useful in rote and developing parts of the world, where current methods to detect diabetic retinopathy are either expensive or unavailable.“For every single person in Australia who knows they have diabetes, another is living with diabetes but isn’t diagnosed. In developing countries, the ratio is one diagnosed to four undiagnosed,” Kumar said.“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.”Kumar told Insight that the detection program is fully operational, and that his colleagues are in discussions with fundus camera manufacturers to include the AI technology in their products.Kumar also said he believes that artificial intelligence or deep learning technology is only going to continue to advance in healthcare.“The reality is that we have been working on this topic for the past 20 years ourselves,” Kumar said.“I don’t see any reason why it would turn back, it will keep going forward.”The research has been published in the journal Computers in Biology and Medicine.