# A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation

arXiv: https://arxiv.org/abs/1907.12296 · HTML: https://mlsanity.com/paper/1907.12296/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2019.

## Built on by (most cited first, 12 of 12)

- [High-Resolution Image Harmonization via Collaborative Dual Transformations](https://mlsanity.com/paper/2109.06671/) (2021)
- [Explaining the Explainers in Graph Neural Networks: a Comparative Study](https://mlsanity.com/paper/2210.15304/) (2022)
- [Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models](https://mlsanity.com/paper/2305.06813/) (2023)
- [A multi-stage GAN for multi-organ chest X-ray image generation and segmentation](https://mlsanity.com/paper/2106.05132/) (2021)
- [RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions](https://mlsanity.com/paper/2505.12887/) (2025)
- [An Analysis of the Influence of Transfer Learning When Measuring the Tortuosity of Blood Vessels](https://mlsanity.com/paper/2111.10255/) (2021)
- [Denoising Diffusion Probabilistic Model for Retinal Image Generation and Segmentation](https://mlsanity.com/paper/2308.08339/) (2023)
- [EAFormer: Scene Text Segmentation with Edge-Aware Transformers](https://mlsanity.com/paper/2407.17020/) (2024)
- [Medical Image Registration and Its Application in Retinal Images: A Review](https://mlsanity.com/paper/2403.16502/) (2024)
- [ClueGAIN: Application of Transfer Learning On Generative Adversarial Imputation Nets (GAIN)](https://mlsanity.com/paper/2302.03140/) (2023)
- [Creating Realistic Anterior Segment Optical Coherence Tomography Images using Generative Adversarial Networks](https://mlsanity.com/paper/2306.14058/) (2023)
- [VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images](https://mlsanity.com/paper/2510.27646/) (2025)

## Abstract (arXiv)

In recent years, the use of deep learning is becoming increasingly popular in computer vision. However, the effective training of deep architectures usually relies on huge sets of annotated data. This is critical in the medical field where it is difficult and expensive to obtain annotated images. In this paper, we use Generative Adversarial Networks (GANs) for synthesizing high quality retinal images, along with the corresponding semantic label-maps, to be used instead of real images during the training process. Differently from other previous proposals, we suggest a two step approach: first, a progressively growing GAN is trained to generate the semantic label-maps, which describe the blood vessel structure (i.e. vasculature); second, an image-to-image translation approach is used to obtain realistic retinal images from the generated vasculature. By using only a handful of training samples, our approach generates realistic high resolution images, that can be effectively used to enlarge small available datasets. Comparable results have been obtained employing the generated images in place of real data during training. The practical viability of the proposed approach has been demonstrated by applying it on two well established benchmark sets for retinal vessel segmentation, both containing a very small number of training samples. Our method obtained better performances with respect to state-of-the-art techniques.