Intel-powered AI solution to help reduce diabetic vision loss


Sankara Eye Foundation and Singapore-based Leben Care are deploying retina danger evaluation software-as-a-service platform in India. Netra.AI, the cloud-based synthetic intelligence (AI) solution, is powered by Intel expertise and is claimed to be utilizing deep studying to establish retinal circumstances in a brief span of time with the accuracy stage of human docs. The solution can help establish diabetic retinopathy (DR), decreasing the screening burden on vitreoretinal surgeons.
“The use of AI to improve disease detection and prevention is a critical step for the healthcare industry and a giant leap for humankind. India has one of the largest diabetic populations in the world and diabetic retinopathy is the major cause for vision loss and blindness in persons of working age. 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,” mentioned Prakash Mallya, vice chairman and managing director of gross sales, advertising and marketing and communications group, Intel India.
India has one of many largest diabetic populations of any nation on this planet, approaching 98 million circumstances by 2030. Research reveals that DR is a number one reason behind blindness and vision loss in adults, and early detection and therapy is crucial to stopping the harm. However, the shortage of skilled retinal specialists in India — particularly in distant, rural areas — limits efficient screening of asymptomatic sufferers. This leads to sufferers presenting late with superior diabetic eye illness.
Netra.AI analyzes pictures from moveable, technician-operated fundus digicam units, for instant outcomes of referable DR grading through a cloud-based internet portal. The solution makes use of AI algorithms, developed in collaboration with retina consultants, with a four-step deep convolutional neural community (DCNN). This neural community helps in detecting DR stage and annotating lesions primarily based on pixel density within the fundus pictures. The solution could be expanded to different retinal circumstances and glaucoma, serving to to reduce the screening burden on healthcare specialists and focus key sources on sufferers who want instant care and intervention.