A fundus image of a retina, with damaged areas highlighted by the image-processing algorithm. Image: RMIT University
Early detection of diabetic retinopathy with artificial intelligence - technology short science news

Diabetic retinopathy is one of the leading causes of blindness in adults, and early detection has remained difficult, until now.

Scientists have developed a deep learning algorithm that detects fluid on the retina with 98% accuracy. Fluid on the retina is one of the earliest symptoms of retinopathy, when eyesight per se is still intact.

The algorithm relies on retinal images that can be obtained with ordinary optometry equipment. This new method is thus cost-effective, and quick to detect the disease.

Read the full story: RMIT University
Scientific publication: Computers in Biology and Medicine