Sankara Eye Foundation and Singapore-based Leben Care have developed a retina risk assessment software-as-a-service platform in India called Netra.AI. It is a cloud-based Artificial Intelligence (AI) solution powered by Intel, which identifies retinal conditions in a short span of time using deep learning.
The AI solution is said to match the accuracy of human doctors. Netra.AI will also reduce the screening burden on vitreoretinal surgeons as it will be able to detect diabetic retinopathy (DR) in just few minutes with the help of a few pictures.
“With Netra.AI, Sankara Eye Foundation and Leben Care have leveraged the power of Intel Xeon Scalable processors and built-in Intel Deep Learning (DL) Boost to accurately detect DR and enable timely treatment to effectively combat avoidable vision impairment and blindness in diabetic patients,” Prakash Mallya, Vice president and managing director of Sales, Marketing and Communications Group, Intel India, said in a statement.
How does this work
An image of the patient’s retina will be captured with the help of a fundus camera, which will be operated by technicians. The data collected from the image will be transferred securely and Netra.AI will perform automatic analysis and compare the data from previous visits of the particular patient if any.
The solution uses AI algorithms with a four-step deep convolutional neural network (DCNN). It can detect any damage based on pixel density in the fundus images. After this a report is generated with bio identifiers. The time taken for it to produce detailed reports is just two minutes once the photos are uploaded.
Netra.AI will also be able to diagnose retinal conditions like glaucoma, macular degeneration and other retinal pathologies. The company says that Netra.AI has screened 3,093 patients so far out of which 742 were at risk (25 per cent approximately).
India will have 98 million cases of diabetic retinopathy by the year 2030 as it has one of the largest diabetic populations in the world. The speed and accuracy of the solution are expected to make it easy for doctors to give counsel and stop the damage, especially in areas where there is a lack or absence of retinal specialists.