Image Based Edge Weighted Linked Segmentation Model Using Deep Learning for Detection of Diabetic Retinopathy

Abstract

Diabetic Retinopathy (DR) is the most well-known disease in association with diabetes. Even before DR is diagnosed, many people lose their sight, however, because to the lengthy diagnostic process and the current dearth of ophthalmologists. Early detection of diabetic retinopathy is also recommended. If the condition is not addressed soon, vision loss may ensue. Manual diagnosis of DR retina imaging data by ophthalmologists involves time, effort, and money, and is prone to error, in contrast to computer-aided diagnosis techniques. Recent advances in deep learning have made it one of the most extensively utilized approaches for increasing performance in a variety of industries, including medical image classification and segmentation. Because they function so well, convolutional layers are more often employed in medical image analysis as a deep learning method. This research work implements an effective Image Edge Weighted Linked Segmentation Model using Deep Learning (EWLSM-DL) for accurate and quick detection of diabetic retinopathy using image enhancement and deep learning technologies to prevent the resulting retinal damage. The proposed model is compared with the traditional methods in terms of accuracy in detection and the proposed model exhibits better results.