# RetinaLogos: Fine-Grained Synthesis of High-Resolution Retinal Images Through Captions

arXiv: https://arxiv.org/abs/2505.12887 · HTML: https://mlsanity.com/paper/2505.12887/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 17 of 17)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://mlsanity.com/paper/2405.05945/) (2024)
- [Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT](https://mlsanity.com/paper/2406.18583/) (2024)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [Diffusion Probabilistic Models beat GANs on Medical Images](https://mlsanity.com/paper/2212.07501/) (2022)
- [REFUGE2 Challenge: A Treasure Trove for Multi-Dimension Analysis and Evaluation in Glaucoma Screening](https://mlsanity.com/paper/2202.08994/) (2022)
- [AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge](https://mlsanity.com/paper/2302.01738/) (2023)
- [RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports](https://mlsanity.com/paper/2405.14137/) (2024)
- [COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network](https://mlsanity.com/paper/2007.14638/) (2020)
- [A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation](https://mlsanity.com/paper/1907.12296/) (2019)
- [DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images](https://mlsanity.com/paper/1912.04670/) (2019)
- [Ophora: A Large-Scale Data-Driven Text-Guided Ophthalmic Surgical Video Generation Model](https://mlsanity.com/paper/2505.07449/) (2025)
- [Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models](https://mlsanity.com/paper/2305.06813/) (2023)
- [MammoDG: Generalisable Deep Learning Breaks the Limits of Cross-Domain Multi-Center Breast Cancer Screening](https://mlsanity.com/paper/2308.01057/) (2023)
- [Explainable Diabetic Retinopathy Detection and Retinal Image Generation](https://mlsanity.com/paper/2107.00296/) (2021)
- [Unpaired Translation of Chest X-ray Images for Lung Opacity Diagnosis via Adaptive Activation Masks and Cross-Domain Alignment](https://mlsanity.com/paper/2503.19860/) (2025)

## Built on by (most cited first, 5 of 5)

- [UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis](https://mlsanity.com/paper/2510.15710/) (2025)
- [Joint Holistic and Lesion Controllable Mammogram Synthesis via Gated Conditional Diffusion Model](https://mlsanity.com/paper/2507.19201/) (2025)
- [S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision](https://mlsanity.com/paper/2508.06995/) (2025)
- [EventRR: Event Referential Reasoning for Referring Video Object Segmentation](https://mlsanity.com/paper/2508.07171/) (2025)
- [What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization](https://mlsanity.com/paper/2609.24691/) (2026)

## Abstract (arXiv)

The scarcity of high-quality, labelled retinal imaging data, which presents a significant challenge in the development of machine learning models for ophthalmology, hinders progress in the field. Existing methods for synthesising Colour Fundus Photographs (CFPs) largely rely on predefined disease labels, which restricts their ability to generate images that reflect fine-grained anatomical variations, subtle disease stages, and diverse pathological features beyond coarse class categories. To overcome these challenges, we first introduce an innovative pipeline that creates a large-scale, captioned retinal dataset comprising 1.4 million entries, called RetinaLogos-1400k. Specifically, RetinaLogos-1400k uses the visual language model(VLM) to describe retinal conditions and key structures, such as optic disc configuration, vascular distribution, nerve fibre layers, and pathological features. Building on this dataset, we employ a novel three-step training framework, RetinaLogos, which enables fine-grained semantic control over retinal images and accurately captures different stages of disease progression, subtle anatomical variations, and specific lesion types. Through extensive experiments, our method demonstrates superior performance across multiple datasets, with 62.07% of text-driven synthetic CFPs indistinguishable from real ones by ophthalmologists. Moreover, the synthetic data improves accuracy by 5%-10% in diabetic retinopathy grading and glaucoma detection. Codes are available at https://github.com/uni-medical/retina-text2cfp.