Transfer Learning Approach for Diabetic Retinopathy Detection using Residual Network
R. S. Rajkumar, T Jagathishkumar, Divi Ragul, A. Grace Selvarani
Abstract
Diabetic retinopathy is a disease caused due to Diabetes Mellitus in the diabetic patients. It is the major cause of blindness for several countries. The longer the diabetic retinopathy affected the high chance that the person can go blind. 90% of cases reported that the cause of blindness due to the diabetic retinopathy occur due to the lack of proper treatment and monitoring the retinopathy before severe stage [2]. The doctors can't find a cure to the severe stage of diabetic retinopathy but can be detected in early stage and prevent it. Hence automated computer diagnosis will assist the doctors in finding the Diabetic Retinopathy at early stage with less cost and time. Deep learning is playing a major role in health informatics. Residual Network, a deep learning approach is used to detect the DR and its stages. With the transfer learning approach, Residual Network model detects the stages of diabetic retinopathy with good accuracy.