Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading

TL;DR

This paper presents a deep learning system for automatic detection and grading of diabetic retinopathy and macular edema from fundus images, achieving high accuracy with fewer training images and higher resolution.

Contribution

The study introduces a deep learning approach that performs comparably or better than previous methods using significantly less training data and provides detailed grading results for clinical scales.

Findings

Achieved high accuracy with less than 25% of training images.

Provided detailed grading for five diabetic retinopathy scales.

Demonstrated potential for cost-effective screening and finer clinical grading.

Abstract

Diabetes is a globally prevalent disease that can cause visible microvascular complications such as diabetic retinopathy and macular edema in the human eye retina, the images of which are today used for manual disease screening. This labor-intensive task could greatly benefit from automatic detection using deep learning technique. Here we present a deep learning system that identifies referable diabetic retinopathy comparably or better than presented in the previous studies, although we use only a small fraction of images (<1/4) in training but are aided with higher image resolutions. We also provide novel results for five different screening and clinical grading systems for diabetic retinopathy and macular edema classification, including results for accurately classifying images according to clinical five-grade diabetic retinopathy and four-grade diabetic macular edema scales. These results suggest, that a deep learning system could increase the cost-effectiveness of screening while attaining higher than recommended performance, and that the system could be applied in clinical examinations requiring finer grading.