# Advances in Computer-Aided Diagnosis of Diabetic Retinopathy

**Authors:** Saket S. Chaturvedi, Kajol Gupta, Vaishali Ninawe, Prakash S. Prasad  
**arXiv:** [1909.09853](https://arxiv.org/abs/1909.09853)  
**Date:** 2019-09-21  
**Summary page:** https://www.summarizepaper.com/en/paper/1909.09853v1/

## Key points

- Diabetic Retinopathy is a critical global health issue affecting 100 million individuals worldwide
- The prevalence of Diabetic Retinopathy is projected to increase, particularly in Asia
- Early detection of Diabetic Retinopathy is crucial to prevent irreversible vision loss
- Computer-aided detection systems using Machine Learning or Deep Learning algorithms have gained popularity for accurately and efficiently detecting Diabetic Retinopathy
- The review paper conducted an extensive literature search on computer-aided detection of Diabetic Retinopathy
- The study explores the typical methodology employed for computer-aided diagnosis of Diabetic Retinopathy
- The review identifies limitations of current methods and areas requiring further research
- Continued research is important to improve early detection and management strategies for Diabetic Retinopathy.

## Summary

Diabetic Retinopathy is a critical global health issue affecting 100 million individuals worldwide and is projected to increase in prevalence, particularly in Asia. This chronic eye disease can lead to irreversible vision loss if not detected early. However, the diagnosis of Diabetic Retinopathy poses challenges for human experts due to the complexity of retinal images. Early detection is essential for preventing permanent vision loss. Computer-aided detection systems have gained popularity among researchers for their ability to accurately and efficiently detect diabetic retinopathy. In this review paper by Saket S. Chaturvedi, Kajol Gupta, Vaishali Ninawe, and Prakash S. Prasad, an extensive literature search was conducted on PubMed, Google Scholar and IEEE Explorer with a focus on computer-aided detection of Diabetic Retinopathy using Machine Learning or Deep Learning algorithms. The study also explores the typical methodology employed for computer-aided diagnosis of Diabetic Retinopathy. By identifying limitations of current methods and specific areas requiring further research, this review aims to guide researchers towards enhancing future advancements in the field. Overall, this comprehensive review provides valuable insights into the advances made in computer-aided diagnosis of Diabetic Retinopathy and highlights the importance of continued research to improve early detection and management strategies for this debilitating condition.