A new software to detect and risk categorize diabetic retinopathy (DR) has been developed by the Indian Institute of Technology - Kharagpur.
Titled Computer Vision Approach to Diabetic Retinopathy Screening and developed by Chandan Chakrabarty of IIT-Kharagpur, the project is now being used on a pilot basis at a hospital in the city with encouraging results. It is being funded by IT major IBM India.
"The software uses data analytics capabilities to automatically compare and analyze retina images of the patient. It can tell if the patient has DR and also provides risk categorization ranging from low to medium and high," Chakrabarty said.
DR is an ocular manifestation of systemic disease, which affects up to 80 percent of all patients who have had diabetes for 10 years or more.
The project was initiated March 2011 by the IIT Kharagpur, in association with IBM India and Susrut Eye Foundation and Research Center (SEFRC), Kolkata.
"The solution is being used in our clinic and the results are very encouraging, in fact, the accuracy level is as high as 92 percent," said Anirudh Maity of SEFRC, where the project is being used on a pilot basis.
Chakrabarty said the project will take at least a year more before it can be marketed commercially.
"We are using the results generated by the prototype at the SEFRC to enhance its operations and we hope it will ready within a year. Once operational, the solution will help prevent and cure DR which has been increasingly spreading across the country," Chakrabarty told IANS.