Advances in Computer-Aided Diagnosis of Diabetic Retinopathy
This is an incremental review paper for researchers working on automated diagnosis of diabetic retinopathy.
This review paper examines computer-aided diagnosis systems for diabetic retinopathy, a chronic eye disease affecting 100 million people worldwide, focusing on machine learning and deep learning algorithms to help researchers identify limitations and future research directions.
Diabetic Retinopathy is a critical health problem influences 100 million individuals worldwide, and these figures are expected to rise, particularly in Asia. Diabetic Retinopathy is a chronic eye disease which can lead to irreversible vision loss. Considering the visual complexity of retinal images, the early-stage diagnosis of Diabetic Retinopathy can be challenging for human experts. However, Early detection of Diabetic Retinopathy can significantly help to avoid permanent vision loss. The capability of computer-aided detection systems to accurately and efficiently detect the diabetic retinopathy had popularized them among researchers. In this review paper, the literature search was conducted on PubMed, Google Scholar, IEEE Explorer with a focus on the computer-aided detection of Diabetic Retinopathy using either of Machine Learning or Deep Learning algorithms. Moreover, this study also explores the typical methodology utilized for the computer-aided diagnosis of Diabetic Retinopathy. This review paper is aimed to direct the researchers about the limitations of current methods and identify the specific areas in the field to boost future research.