# Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models

arXiv: https://arxiv.org/abs/2305.06813 · HTML: https://mlsanity.com/paper/2305.06813/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 11 May 2023.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 15 of 15)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network](https://mlsanity.com/paper/2101.00535/) (2021)
- [The RETA Benchmark for Retinal Vascular Tree Analysis](https://mlsanity.com/paper/2111.11658/) (2021)
- [A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation](https://mlsanity.com/paper/1907.12296/) (2019)

## Built on by (most cited first, 9 of 9)

- [Probing the Limits and Capabilities of Diffusion Models for the Anatomic Editing of Digital Twins](https://mlsanity.com/paper/2401.00247/) (2023)
- [RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions](https://mlsanity.com/paper/2505.12887/) (2025)
- [LPUWF-LDM: Enhanced Latent Diffusion Model for Precise Late-phase UWF-FA Generation on Limited Dataset](https://mlsanity.com/paper/2409.00726/) (2024)
- [Artificial Intelligence for Biomedical Video Generation](https://mlsanity.com/paper/2411.07619/) (2024)
- [Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories](https://mlsanity.com/paper/2511.00801/) (2025)
- [Diffusion-Guided Mask-Consistent Paired Mixing for Endoscopic Image Segmentation](https://mlsanity.com/paper/2511.03219/) (2025)
- [Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling](https://mlsanity.com/paper/2503.01190/) (2025)
- [VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images](https://mlsanity.com/paper/2510.27646/) (2025)
- [A General B'ezier Tree Encoding Counterfactual Framework for Retinal-Vessel-Mediated Disease Analysis](https://mlsanity.com/paper/2605.13015/) (2026)

## Abstract (arXiv)

We introduce a new technique for generating retinal fundus images that have anatomically accurate vascular structures, using diffusion models. We generate artery/vein masks to create the vascular structure, which we then condition to produce retinal fundus images. The proposed method can generate high-quality images with more realistic vascular structures and can create a diverse range of images based on the strengths of the diffusion model. We present quantitative evaluations that demonstrate the performance improvement using our method for data augmentation on vessel segmentation and artery/vein classification. We also present Turing test results by clinical experts, showing that our generated images are difficult to distinguish with real images. We believe that our method can be applied to construct stand-alone datasets that are irrelevant of patient privacy.