# A Survey of Multimodal Ophthalmic Diagnostics: From Task-Specific Approaches to Foundational Models

arXiv: https://arxiv.org/abs/2508.03734 · HTML: https://mlsanity.com/paper/2508.03734/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 184 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs](https://mlsanity.com/paper/1910.03667/) (2019)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model](https://mlsanity.com/paper/2007.05201/) (2020)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [Attention Based Glaucoma Detection: A Large-scale Database and CNN Model](https://mlsanity.com/paper/1903.10831/) (2019)
- [Applications of Deep Learning in Fundus Images: A Review](https://mlsanity.com/paper/2101.09864/) (2021)
- [Self-supervised Feature Learning via Exploiting Multi-modal Data for Retinal Disease Diagnosis](https://mlsanity.com/paper/2007.11067/) (2020)
- [GAMMA Challenge:Glaucoma grAding from Multi-Modality imAges](https://mlsanity.com/paper/2202.06511/) (2022)
- [DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation](https://mlsanity.com/paper/2011.00569/) (2020)
- [OCTID: Optical Coherence Tomography Image Database](https://mlsanity.com/paper/1812.07056/) (2018)
- [OphGLM: Training an Ophthalmology Large Language-and-Vision Assistant based on Instructions and Dialogue](https://mlsanity.com/paper/2306.12174/) (2023)
- [Towards a glaucoma risk index based on simulated hemodynamics from fundus images](https://mlsanity.com/paper/1805.10273/) (2018)
- [RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports](https://mlsanity.com/paper/2405.14137/) (2024)
- [OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining](https://mlsanity.com/paper/2411.15421/) (2024)
- [VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers](https://mlsanity.com/paper/2104.06757/) (2021)
- [ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images](https://mlsanity.com/paper/2202.07983/) (2022)
- [Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation](https://mlsanity.com/paper/2206.01988/) (2022)
- [MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise](https://mlsanity.com/paper/2405.11793/) (2024)
- [EyecareGPT: Boosting Comprehensive Ophthalmology Understanding with Tailored Dataset, Benchmark and Model](https://mlsanity.com/paper/2504.13650/) (2025)
- [VisionUnite: A Vision-Language Foundation Model for Ophthalmology Enhanced with Clinical Knowledge](https://mlsanity.com/paper/2408.02865/) (2024)
- [Uni4Eye: Unified 2D and 3D Self-supervised Pre-training via Masked Image Modeling Transformer for Ophthalmic Image Classification](https://mlsanity.com/paper/2203.04614/) (2022)
- [EyeFound: A Multimodal Generalist Foundation Model for Ophthalmic Imaging](https://mlsanity.com/paper/2405.11338/) (2024)
- [Harvard Glaucoma Detection and Progression: A Multimodal Multitask Dataset and Generalization-Reinforced Semi-Supervised Learning](https://mlsanity.com/paper/2308.13411/) (2023)
- [Contextualized Keyword Representations for Multi-modal Retinal Image Captioning](https://mlsanity.com/paper/2104.12471/) (2021)

## Built on by (most cited first, 4 of 4)

- [Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoning](https://mlsanity.com/paper/2508.16129/) (2025)
- [VOLMO: Versatile and Open Large Models for Ophthalmology](https://mlsanity.com/paper/2603.23953/) (2026)
- [CLEAR-Mamba:Towards Accurate, Adaptive and Trustworthy Multi-Sequence Ophthalmic Angiography Classification](https://mlsanity.com/paper/2601.20601/) (2026)
- [X-PCR: A Benchmark for Cross-modality Progressive Clinical Reasoning in Ophthalmic Diagnosis](https://mlsanity.com/paper/2604.20350/) (2026)

## Abstract (arXiv)

Visual impairment represents a major global health challenge, with multimodal imaging providing complementary information that is essential for accurate ophthalmic diagnosis. This comprehensive survey systematically reviews the latest advances in multimodal deep learning methods in ophthalmology up to the year 2025. The review focuses on two main categories: task-specific multimodal approaches and large-scale multimodal foundation models. Task-specific approaches are designed for particular clinical applications such as lesion detection, disease diagnosis, and image synthesis. These methods utilize a variety of imaging modalities including color fundus photography, optical coherence tomography, and angiography. On the other hand, foundation models combine sophisticated vision-language architectures and large language models pretrained on diverse ophthalmic datasets. These models enable robust cross-modal understanding, automated clinical report generation, and decision support. The survey critically examines important datasets, evaluation metrics, and methodological innovations including self-supervised learning, attention-based fusion, and contrastive alignment. It also discusses ongoing challenges such as variability in data, limited annotations, lack of interpretability, and issues with generalizability across different patient populations. Finally, the survey outlines promising future directions that emphasize the use of ultra-widefield imaging and reinforcement learning-based reasoning frameworks to create intelligent, interpretable, and clinically applicable AI systems for ophthalmology.