Applications of deep learning in fundus images: A review

The use of fundus images for the early screening of eye diseases is of great clinical importance. Due to its powerful performance, deep learning is becoming more and more popular in related applications, such as lesion segmentation, biomarkers segmentation, disease diagnosis and image synthesis. Therefore, it is very necessary to summarize the recent developments in deep learning for fundus images with a review paper. In this review, we introduce 143 application papers with a carefully designed hierarchy. Moreover, 33 publicly available datasets are presented. Summaries and analyses are provided for each task. Finally, limitations common to all tasks are revealed and possible solutions are given. We will also release and regularly update the state-of-the-art results and newly-released datasets at https://github.com/nkicsl/Fundus_Review to adapt to the rapid development of this field. ? 2021 Elsevier B.V. All rights reserved.

Automated summary

The use of deep learning in fundus image analysis is increasingly popular due to its powerful performance in various applications. This review paper introduces 143 application papers and 33 publicly available datasets, providing summaries, analyses, and solutions for common limitations in each task. The authors also promise to regularly update the state-of-the-art results and newly-released datasets on their GitHub page to keep up with the rapid development in the field.