AI Can Detect 'Diabetes Of Eyes' In Minutes To Successfully Save People¡¯s Eyesight

Diabetes is known to cause an array of ailments in humans that can result in severe lifestyle changes. India is approaching over 98 million cases of diabetes by 2030, according to the Lancet Diabetes and Endocrinology Global Study.

Getty Images

While issues with cardiac health, blood pressure and other such complications, one that often gets ignored is Diabetic Retinopathy or DR. This medical condition if not treated in time can result in vision-related issues, even permanent blindness.

What makes this issue more challenging is the lack of skilled trained retinal specialists in India. This number goes even lower when looking at remote rural regions. This basically means that most asymptomatic patients go undetected and by the time symptoms start surfacing, it¡¯s already too late.

To bridge this gap, researchers at Sankara Eye Foundation and Leben Care have developed Netra.AI -- an Artificial Intelligence system that helps in detecting cases of DR accurately in a matter of minutes and saving the patient¡¯s vision in time.

Netra.AI analyses images from portable technician-operated fundus camera devices. The images are sent to DR grading through a cloud-based web portal. This system then uses AI algorithms that have been developed in collaboration with retinal experts and with the application of a four-step Deep Convolutional Neural Network or DCNN.

What powers Netra.AI solution is Intel¡¯s Xeon Scalable processors with built-in Deep learning Boost and Intel Advanced Vector Extension 512 acceleration that results in faster processing of large data volumes.

This along with the DCNN, helps the AI in detecting the stage of DR and highlighting the lesions based on pixel density in the images. What¡¯s more, is that this application can also be used to screen other retinal conditions like glaucoma. This in-turn helps in reducing the burden on healthcare professionals and allows them to focus on patients who need their immediate care.

As of now, Netra.AI has managed to screen 3,093 patients in India and has identified 742 at-risk patients. The solution is capable of delivering reports in just two minutes after the uploading of images.

Intel/Netra.ai

Dr Kaushik Murali, president of Medical Administration, Quality & Education, Sankara Eye Foundation India said, ¡°Technology and AI are democratizing healthcare access, especially in screening for ailments. Our team at Sankara Eye Foundation has focused on our vision to eliminate needless blindness from India.¡±

He added, ¡°The current solution, Netra.AI ¡ª where we had a key role in the design and development with Leben Care ¡ª uses robust AI-enabled platforms from Intel. It is an example of how like-minded collaborators can create meaningful and impactful solutions for various challenges that face humanity.¡±

Prakash Mallya, VP and MD ¨C Sales, Marketing and Communications Group, Intel India said in a statement, ¡°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."

He added, "The Intel-powered Netra.AI is a cloud-based AI solution that can scale rapidly to enable faster and accurate detection of retinal disorders in large populations with limited healthcare resources. 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.¡± --