With 70 million people with diabetes, India has a growing problem with diabetic retinopathy. The disease creates lesions in the back of the retina that can lead to total blindness, and 18 percent of diabetic Indians already have the ailment. With 415 million diabetics at risk for blindness worldwide (the United States, China, and India have the most cases), the disease is a global concern.
The Google team wanted to use deep learning models and was aided by ophthalmologists at Aravind and Sankara Nethralaya to label the retina images. After a few short months, the model was trained to identify key markers of diabetic retinopathy, such as nerve tissue damage, swelling, and hemorrhaging. And with a larger data set, Gulshan was sure they could make the model even more accurate.
The tricky part was creating a data set for the AI model to learn from – a task which involved scoring and labeling all the scans one by one for different grades of severity. Solving that problem would eventually require a large team of ophthalmologists whose scoring of the scans would inform the AI model. [via]