Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading
This work addresses the labor-intensive screening of diabetic eye complications, potentially increasing cost-effectiveness and enabling finer clinical grading, though it appears incremental as it builds on existing deep learning approaches.
The authors tackled automatic grading of diabetic retinopathy and macular edema from fundus images using a deep learning system, achieving performance comparable or better than previous studies while using less than a quarter of the training data and higher image resolutions, with results for multiple grading scales.
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.