On Deep Learning based algorithms for Detection of Diabetic Retinopathy

Diabetic retinopathy (DR) is one of the leading causes of avertible blindness worldwide. Early detection of the disease can help to save the vision of diabetic patients. Presence of exudates, hemorrhages, and microaneurysms indicate an unhealthy eye image. Deep learning models have triumphed in image recognition, object detection and biomedical signal classification. Convolution neural network based DR detection techniques are fast evolving and can identify complex features and thus can accurately classify even severe cases. The presented paper investigates the recent work done in diabetic retinopathy detection using deep learning and collating the milestones achieved to guide researchers working in this domain to the future trend.