Lead author Parham Khojasteh of the Royal Melbourne Institute of Technology (RMIT), Biosignals Laboratory, School of Engineering, Melbourne, Australia, and colleagues explored the role of automatic detection of exudates in the fundus as a potential early indicator that serves to improve the diagnosis of and interventional opportunities for diabetic retinopathy. The authors note that undiagnosed diabetic retinopathy leads to blindness and that its early detection can significantly reduce visual impairment by up to 50%; however, manual detection is time-consuming and its value is limited by the skill of the examiner.
The authors note that “automatic exudate detection would make it possible to perform widespread screening of at-risk populations. This is a very challenging task due to factors such as uneven illumination, poor contrast and variability.” The research team used deep learning and artificial intelligence (AI) techniques to automate the analysis of fundus images and developed algorithms intended to reliably and accurately detect exudate, which is fluid from damaged blood vessels inside the retina.
The research team reported that they hope their method can eventually be used for widespread screening of at-risk populations, and they are currently involved in discussions with manufacturers of fundus cameras about potential collaborations to advance this technology. In a recent interview, Professor Dinesh Kant Kumar describes the method as instantaneous and cost-effective. “We know that only half of those with diabetes have regular eye exams and one-third have never been checked,” Dr. Kumar said.
“But the gold standard methods of diagnosing diabetic retinopathy are invasive or expensive, and often unavailable in remote or developing parts of the world. 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,” said Dr. Kumar.
“Undiagnosed diabetes is a massive health problem here and around the globe and for every single person in Australia who knows they have diabetes, another is living with diabetes but isn’t diagnosed,” Dr. Kumar added. “In developing countries, the ratio is one diagnosed to four undiagnosed. This results in millions of people developing preventable and treatable complications from diabetes-related diseases,” he said. “With further development, our technology has the potential to reduce that burden.”
« Click here to return to Diabetes Update.