Problem / Objective:

Since 2001, Aravind Eye Hospital has been working on diabetic retinopathy detection using different retina cameras. Due to the delay in report generation, the hospital developed a semi-automated system capable of generating reports in an hour. To make this process more efficient, Aravind Hospital partnered with Google in 2013 to develop an algorithm that would help in the early detection of this disease.

Solution / Approach:

In 2017, a complete screening tool was developed using Google’s deep machine learning algorithm. The actual work on the tool began after researchers at Google published a paper in the US stating that their algorithms have achieved an accuracy of 98.6% in detecting diabetic retinopathy, on a par with the performance of ophthalmologists and retinal specialists.

Google created a database of 1,28,000 images from different sight centers around the world. The database was created by grading each image, marking abnormal spots, lesions, and indications of bleeding. The data was assembled into a set of instructions built into a computer program to identify eye complications arising from diabetes. By analyzing millions of retinal scans showing signs of diabetic blindness, a neural network learns to determine the condition on its own. The machine predicts retina conditions and advises on the next steps of action in seconds.

Impact / Implementation:

Seventy-one vision centers are using this tool across rural Tamil Nadu which have been established by Aravind Eye Hospital. These centers are supervised by trained technicians who take pictures of patients’ eyes with retinal cameras and send the digital reports to doctors at Aravind Hospital. 

One of the challenges faced by the technicians and ophthalmologists is the varying quality of retina images from different retina cameras. The hospital is working on minimizing the effects of this challenge before its final deployment.

The hospital has also started supplementing its Diabetic Retinopathy (DR) grading process with Google AI in 10 of its rural teleconsultation centers. Besides, the hospital is in the process of deploying AI-powered solutions for other diseases such as glaucoma and diabetic macular oedema.