Intel-powered AI solution fights diabetic vision loss

Sankara Eye Foundation in India and Singapore Leben treatments deploy a comprehensive retinal risk assessment software platform as a service in India. Netra.AI, the cloud-based artificial intelligence (AI) solution, is powered by Intel® technology and uses deep learning to identify retinal conditions in a short period of time with the level of precision of physicians humans. Netra.AI can accurately identify diabetic retinopathy (DR), dramatically reducing the screening burden for vitreoretinal surgeons.

“Using AI to improve disease detection and prevention is a critical step for the healthcare industry and a giant leap forward for humanity. 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 fast processing to fight effectively against preventable visual impairment and blindness in diabetic patients ”Prakash Mallya, Vice President and General Manager of Sales, Marketing and Communications Group, Intel India.

The Sankara Eye Foundation and Leben Care are deploying Netra.AI, a comprehensive retinal risk assessment software platform as a service, in India. The cloud-based artificial intelligence solution is powered by Intel technology and uses deep learning to identify retinal conditions in a short period of time with the level of precision of human doctors.

Dr Kaushik Murali, President of Medical Administration, Quality and Education, Sankara Eye Foundation India, said: “The current solution, Netra.AI, for which we have played a key role in the design and development with Leben Care, uses robust platforms compatible with AI. from Intel.

Netra.AI analyzes images from portable, technician-operated fundus cameras for immediate results of the referenced DR rating through a cloud-based web portal. The solution uses cutting-edge AI algorithms, developed in collaboration with leading retinal experts, with a four-step Deep Convolutional Neural Network (DCNN). This neural network helps detect the DR stage and annotate lesions based on pixel density in fundus images. The solution can be extended to other retinal conditions and glaucoma, helping to reduce the screening burden on healthcare professionals and focus key resources on patients who need immediate care and intervention.

So far, Netra.AI has screened 3,093 patients in India and identified 742 patients at risk. The solution generates detailed reports within two minutes of uploading images and offers immediate and highly accurate diagnosis to help physicians provide instant advice to patients in need of hospital referral. It is a powerful tool for retinal disease screening in large populations with limited infrastructure and resources and an overburdened health system.

The Netra.AI solution is optimized for Intel Xeon Scalable processors with integrated Intel Deep Learning Boost acceleration and Intel® Advanced Vector Extension 512. Intel® architecture provides robust data protection, fast processing of large volumes of data and flexibility of service without any performance drawbacks. The solution allows users to access Intel-optimized images for TensorFlow, Apache MXNet and PyTorch, in addition to Intel® performance libraries, to further improve application performance.