# Self-Supervised Learning from Unlabeled Fundus Photographs Improves Segmentation of the Retina

arXiv: https://arxiv.org/abs/2108.02798 · HTML: https://mlsanity.com/paper/2108.02798/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 64 references that are in the map.
- First posted on arXiv 5 Aug 2021.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Transfusion: Understanding Transfer Learning for Medical Imaging](https://mlsanity.com/paper/1902.07208/) (2019)
- [Revisiting Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1901.09005/) (2019)
- [Models Genesis: Generic Autodidactic Models for 3D Medical Image Analysis](https://mlsanity.com/paper/1908.06912/) (2019)
- [3D Self-Supervised Methods for Medical Imaging](https://mlsanity.com/paper/2006.03829/) (2020)
- [What makes instance discrimination good for transfer learning?](https://mlsanity.com/paper/2006.06606/) (2020)
- [Why rankings of biomedical image analysis competitions should be interpreted with care](https://mlsanity.com/paper/1806.02051/) (2018)
- [DUNet: A deformable network for retinal vessel segmentation](https://mlsanity.com/paper/1811.01206/) (2018)
- [How Useful is Self-Supervised Pretraining for Visual Tasks?](https://mlsanity.com/paper/2003.14323/) (2020)
- [Deep Vessel Segmentation By Learning Graphical Connectivity](https://mlsanity.com/paper/1806.02279/) (2018)
- [Distilling Localization for Self-Supervised Representation Learning](https://mlsanity.com/paper/2004.06638/) (2020)
- [Towards a glaucoma risk index based on simulated hemodynamics from fundus images](https://mlsanity.com/paper/1805.10273/) (2018)
- [Deep image mining for diabetic retinopathy screening](https://mlsanity.com/paper/1610.07086/) (2016)
- [Extending and Analyzing Self-Supervised Learning Across Domains](https://mlsanity.com/paper/2004.11992/) (2020)
- [On the Evaluation and Real-World Usage Scenarios of Deep Vessel Segmentation for Retinography](https://mlsanity.com/paper/1909.03856/) (2019)

## Built on by (most cited first, 2 of 2)

- [Learning Self-Supervised Representations for Label Efficient Cross-Domain Knowledge Transfer on Diabetic Retinopathy Fundus Images](https://mlsanity.com/paper/2304.11168/) (2023)
- [Local-to-Global Self-Supervised Representation Learning for Diabetic Retinopathy Grading](https://mlsanity.com/paper/2410.00779/) (2024)

## Abstract (arXiv)

Fundus photography is the primary method for retinal imaging and essential for diabetic retinopathy prevention. Automated segmentation of fundus photographs would improve the quality, capacity, and cost-effectiveness of eye care screening programs. However, current segmentation methods are not robust towards the diversity in imaging conditions and pathologies typical for real-world clinical applications. To overcome these limitations, we utilized contrastive self-supervised learning to exploit the large variety of unlabeled fundus images in the publicly available EyePACS dataset. We pre-trained an encoder of a U-Net, which we later fine-tuned on several retinal vessel and lesion segmentation datasets. We demonstrate for the first time that by using contrastive self-supervised learning, the pre-trained network can recognize blood vessels, optic disc, fovea, and various lesions without being provided any labels. Furthermore, when fine-tuned on a downstream blood vessel segmentation task, such pre-trained networks achieve state-of-the-art performance on images from different datasets. Additionally, the pre-training also leads to shorter training times and an improved few-shot performance on both blood vessel and lesion segmentation tasks. Altogether, our results showcase the benefits of contrastive self-supervised pre-training which can play a crucial role in real-world clinical applications requiring robust models able to adapt to new devices with only a few annotated samples.