Detection and diagnosing Diabetic Retinopathy (DR) requires capturing an image of the the retina using specialized equipment such as a slit-lamp and fundus camera.  The image is then examined by an ophthalmologist, optometrist or a trained professional to detect abnormalities such as microaneurysms, exudates, hemorrhages, macular edema, etc. to determine if DR is present and its severity and stage of progression.  In general DR can be classified as mild, moderate or vision-threatening, which includes severe non-proliferative DR, proliferative DR (PDR) and diabetic macular edema (DME).  Accurate diagnosis of DR from fundus camera images and grading its severity requires professional expertise and training.

In recent years, many AI systems using deep learning have been very successful in image recognition and classification tasks.  For example, in the Imagenet challenge, requiring identification of objects in a 1000 categories, the best models achieve a classification error rate of less than 5%. – exceeding the best human accuracy levels.

Many of these models, have now  been adapted successfully for use in a variety of medical image diagnosis tasks such as melanoma, breast, lung cancer detection and diabetic retinopathy.

Using a Convolutional Neural Network (CNN) to diagnose Diabetic Retinopathy
Using a Convolutional Neural Network (CNN) to diagnose Diabetic Retinopathy

In particular, a team at Google published results in 2016 of a study for detecting DR working with doctors in India and the US. The results show that their AI model’s performance for DR detection and grading its severity was on-par with that of ophthalmologists. Their model had a combined accuracy score of 0.95, which was slightly better than the median of the 8 ophthalmologists consulted (measured at 0.91). [link to paper]

An integrated system using AI can be deployed at scale and be effective for early detection and screening of DR, a major cause of preventable blindness worldwide.

AI based systems for detection of DR offer the following potential benefits:

● Bridge the shortage of healthcare professionals and provide access to screening where none exists.
● Increase overall efficiency and scalability of current screening methods.
● Provide earlier detection of DR thereby preventing vision loss for millions.
● Decrease overall health-care costs via earlier interventions when it is easier and less expensive to treat these diseases.