A Review on CNN-based Approaches for Diabetic Retinopathy

Diabetic retinopathy (DR) is an illness that has the potential to cause vision impairment in people who are diabetic by affecting the retina's blood vessels. The identification of DR using color fundus images typically relies on the expertise of trained medical professionals to manually detect lesions resulting in time-consuming processes. Along with the growing number of individuals affected by diabetes, there has been an escalating need for dependable diabetic retinopathy screening systems. In the field of artificial intelligence, there have been recent advancements in a specific type of advanced computational model called convolutional neural networks. These networks are designed to mimic the way our brains process visual information, making them effective at tasks involving image data. Their potential extends to various applications including the detection of DR. This paper presents a systematic review of DR detection approaches. The approaches are compared based on the dataset used, accuracy, and methodologies.