Graph-Based Learning for Ophthalmic Image Analysis: Models, Methodologies, and Future Directions

Haina Shi

doi:10.54691/hc1fca15

Authors

Haina Shi

DOI:

https://doi.org/10.54691/hc1fca15

Keywords:

Graph-based Learning, Graph Neural Networks, Ophthalmic Image Analysis, Retinal Imaging, Structural Representation, Medical Image Computing, Clinical Applications, Deep Learning in Ophthalmology.

Abstract

Ophthalmic imaging serves as a cornerstone for the diagnosis and management of ocular diseases, capturing intricate anatomical structures and relational patterns that are not fully characterized by conventional convolutional neural networks operating on Euclidean grids. Graph-based learning offers a powerful paradigm to overcome this limitation by representing images as graphs, where nodes correspond to anatomical units and edges encode structural, spatial, or semantic relationships. This review provides a systematic and critical synthesis of graph-based methodologies applied to ophthalmic image analysis. It examines fundamental graph construction strategies-including node representation, edge formulation, and topological design-tailored to the hierarchical and relational nature of retinal structures. We further survey the evolution of graph learning models, from early graphical approaches to modern graph neural networks (GNNs) and their attention-based, diffusion-aware, and higher-order extensions. The discussion extends to learning strategies optimized for ophthalmic data challenges such as annotation scarcity, class imbalance, and domain shift. Clinically, we summarize representative applications across major imaging modalities, including fundus photography and optical coherence tomography, highlighting how graph-based frameworks advance tasks such as glaucoma assessment, diabetic retinopathy grading, vessel segmentation, and layered tissue analysis. Despite promising progress, critical challenges remain in robust and anatomically consistent graph construction, computational scalability, cross-domain generalization, and clinical interpretability. Future directions emphasize adaptive and uncertainty-aware graph building, scalable GNN architectures, integration of hypergraph representations for group-wise interactions, and unified multi-modal and longitudinal modeling. Through a structured analysis of models, methodologies, and applications, this review aims to guide the translation of graph-based learning into reliable and interpretable clinical tools for precision ophthalmology.

Downloads

Download data is not yet available.

References

[1] Soomro T A, Afifi A J, Zheng L, et al. “Deep Learning Models for Retinal Blood Vessels Segmentation: A Review”, IEEE Access, Vol. 7, pp. 71696–71717, 2019.

[2] Zafar A, Aamir M, Nawi N M, et al. “A Comprehensive Convolutional Neural Network Survey to Detect Glaucoma Disease”, Mobile Information Systems, 2022, pp. 1–10, 2022.

[3] Dash S K, Sethy P K, Das A, et al. “Advancements in Deep Learning for Automated Diagnosis of Ophthalmic Diseases: A Comprehensive Review”, IEEE Access, Vol. 12, pp. 171221–171240, 2024.

[4] Soomro T A, Ubaid F B, Zardari S, et al. “The State of Retinal Image Analysis: Deep Learning Advances and Applications”, IEEE Access, Vol. 13, pp. 65066–65093, 2025.

[5] Mienye I D, Swart T G, Obaido G, et al. “Deep Convolutional Neural Networks in Medical Image Analysis: A Review”, Information, Vol. 16, No. 3, Article 195, 2025.

[6] Urina-Triana M A, Piñeres-Melo M A, Mantilla-Morrón M, et al. “Machine Learning and AI Approaches for Analyzing Diabetic and Hypertensive Retinopathy in Ocular Images: A Literature Review”, IEEE Access, Vol. 12, pp. 54590–54607, 2024.

[7] Li B, Zhang Y, Wang Q, et al. “Gene Expression Prediction from Histology Images via Hypergraph Neural Networks”, Briefings in Bioinformatics, Vol. 25, No. 6, bbae500, 2024.

[8] Somu N, Raman M R G, Kirthivasan K, et al. “Hypergraph Based Feature Selection Technique for Medical Diagnosis”, Journal of Medical Systems, Vol. 40, No. 11, Article 239, 2016.

[9] Quintana-Quintana O J, Aceves-Fernández M A, Pedraza-Ortega J C, et al. “Deep Learning Techniques for Retinal Layer Segmentation to Aid Ocular Disease Diagnosis: A Review”, Computers, Vol. 14, No. 8, Article 298, 2025.

[10] Yusuf A A, Feng C, Mao X, et al. “Graph Neural Networks for Visual Question Answering: A Systematic Review”, Multimedia Tools and Applications, Vol. 83, No. 18, pp. 55471–55508, 2023.

[11] Lan Z, Hu Y, Yang S, et al. “Deep Learning in Ophthalmic Image Analysis: A Task-Driven Review of Segmentation, Diagnosis, and Progress Prediction”, Neurocomputing, Vol. 667, Article 132282, 2026.

[12] Raja H, Hassan T, Hassan B, et al. “A Comprehensive Review of Artificial Intelligence Applications in Major Retinal Conditions”, arXiv:2311.13710, 2023.

[13] Ghadban R, Neima H, Adday G. “Vision and Multimodal Foundation Models in Medical Imaging: A Comprehensive Review of Architectures, Clinical Trends, and Future Directions”, Iraqi Journal of Intelligent Computing and Informatics, Vol. 4, No. 2, pp. 194–211, 2026.

[14] Kandel I, Castelli M. “Transfer Learning with Convolutional Neural Networks for Diabetic Retinopathy Image Classification: A Review”, Applied Sciences, Vol. 10, No. 6, Article 2021, 2020.

[15] Goutam B, Hashmi M F, Geem Z W, et al. “A Comprehensive Review of Deep Learning Strategies in Retinal Disease Diagnosis Using Fundus Images”, IEEE Access, Vol. 10, pp. 57796–57823, 2022.

[16] Nadeem M W, Goh H G, Hussain M, et al. “Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions”, Sensors, Vol. 22, No. 18, Article 6780, 2022.

[17] Stella Mary M C V, Rajsingh E B, Naik G R. “Retinal Fundus Image Analysis for Diagnosis of Glaucoma: A Comprehensive Survey”, IEEE Access, Vol. 4, pp. 4327–4354, 2016.

[18] Gupta M, Gupta S, Palanisamy G, et al. “A Comprehensive Survey on Detection of Ocular and Non-Ocular Diseases Using Color Fundus Images”, IEEE Access, Vol. 12, pp. 194296–194321, 2024.

[19] Prakash V J, Vijay S A A, Sundaram G. “A Multi-Resolution Hypergraph Transformer for Explainable Retinal Disease Prediction”, IEEE Journal of Biomedical and Health Informatics, pp. 1–14, 2025.

[20] Muchuchuti S, Viriri S. “Retinal Disease Detection Using Deep Learning Techniques: A Comprehensive Review”, Journal of Imaging, Vol. 9, No. 4, Article 84, 2023.

[21] Wei L, Hu M. “A Review of Medical Ocular Image Segmentation”, Virtual Reality & Intelligent Hardware, Vol. 6, No. 3, pp. 181–202, 2024.

[22] Paul S G, Saha A, Hasan Md Z, et al. “A Systematic Review of Graph Neural Network in Healthcare-Based Applications”, IEEE Access, Vol. 12, pp. 15145–15170, 2024.

[23] Salam A A, Mahadevappa M, Das A, et al. “RDD-Net: Retinal Disease Diagnosis Network”, The Visual Computer, Vol. 39, No. 10, pp. 4657–4670, 2023.

[24] Arrieta-Rodríguez E, Araque-Gallardo J, Peñaloza Barrios N, et al. “Deep Learning for Glaucoma Classification and Grading”, IEEE Access, Vol. 13, pp. 163699–163730, 2025.

[25] Saeed A Q, Sheikh Abdullah S N H, Che-Hamzah J, et al. “Accuracy of Using Generative Adversarial Networks for Glaucoma Detection”, Journal of Medical Internet Research, Vol. 23, No. 9, e27414, 2021.

[26] Hassan M, Guan H, Melliou A, et al. “Neuro-Symbolic Learning: Principles and Applications in Ophthalmology”, arXiv:2208.00374, 2022.

[27] Anwar S M, Majid M, Qayyum A, et al. “Medical Image Analysis Using Convolutional Neural Networks: A Review”, Journal of Medical Systems, Vol. 42, No. 11, Article 226, 2018.

[28] Xu Y, Quan R, Xu W, et al. “Advances in Medical Image Segmentation”, Bioengineering, Vol. 11, No. 10, Article 1034, 2024.

[29] Yin S, Wang L, Wu S, et al. “Mainstream Artificial Intelligence Technologies in Contemporary Ophthalmology”, Advanced Intelligent Systems, Vol. 7, No. 12, e202500055, 2025.

[30] Tahir M Z, Nasir M, Zhang S. “Advances in Retinal Microaneurysms Detection”, Multimedia Tools and Applications, Vol. 83, No. 30, pp. 74897–74935, 2024.

[31] Ahsan M M, Luna S A, Siddique Z. “Machine-Learning-Based Disease Diagnosis”, Healthcare, Vol. 10, No. 3, Article 541, 2022.

[32] Wang M H, Xing L, Pan Y, et al. “AI-Based Advanced Approaches and Dry Eye Disease Detection”, Big Data Mining and Analytics, Vol. 7, No. 2, pp. 445–484, 2024.

[33] Abbas Q, Qureshi I, Yan J, et al. “Machine Learning Methods for Diagnosis of Eye-Related Diseases”, Archives of Computational Methods in Engineering, Vol. 29, No. 6, pp. 3861–3918, 2022.

[34] Bali A, Mansotra V. “Analysis of Deep Learning Techniques for Prediction of Eye Diseases”, Archives of Computational Methods in Engineering, Vol. 31, No. 1, pp. 487–520, 2024.

[35] Galić I, Habijan M, Leventić H, et al. “Machine Learning Empowering Personalized Medicine”, Electronics, Vol. 12, No. 21, Article 4411, 2023.

[36] Rajarajeshwari G, Selvi G C. “Application of Artificial Intelligence for Diabetic Retinopathy”, IEEE Access, Vol. 12, pp. 172499–172536, 2024.

[37] Sengupta S, Singh A, Leopold H A, et al. “Application of Deep Learning in Fundus Image Processing”, Artificial Intelligence in Medicine, Vol. 102, Article 101758, 2020.

[38] Sushith M, Malligeswari N, Anlin Sahaya Infant Tinu M, et al. “HyperGraph-Based Capsule Temporal Memory Network”, Scientific Reports, Vol. 16, No. 1, Article 607, 2025.

[39] You A, Kim J K, Ryu I H, et al. “Application of GAN for Ophthalmology Image Domains”, Eye and Vision, Vol. 9, No. 1, Article 6, 2022.

[40] Costin H N, Fira M, Goraș L. “Artificial Intelligence in Ophthalmology”, Applied Sciences, Vol. 15, No. 4, Article 1913, 2025.

[41] Mienye I D, Viriri S. “Graph Neural Networks in Medical Imaging”, Information, Vol. 16, No. 12, Article 1051, 2025.

[42] Kankrale R, Kokare M. “Artificial Intelligence in Retinal Image Analysis”, Visual Computing for Industry, Biomedicine, and Art, Vol. 8, No. 1, Article 11, 2025.

[43] Kumar R, Waisberg E, Ong J, et al. “Artificial Intelligence-Based Methodologies”, Brain Sciences, Vol. 14, No. 12, Article 1266, 2024.

[44] Zhang L, Zhao Y, Che T, et al. “Graph Neural Networks for Image-Guided Disease Diagnosis”, iRADIOLOGY, Vol. 1, No. 2, pp. 151–166, 2023.

[45] Mateen M, Wen J, Hassan M, et al. “Automatic Detection of Diabetic Retinopathy”, IEEE Access, Vol. 8, pp. 48784–48811, 2020.

[46] Zhang S, Tong H, Xu J, et al. “Graph Convolutional Networks: A Comprehensive Review”, Computational Social Networks, Vol. 6, No. 1, Article 11, 2019.

[47] Anton N, Doroftei B, Curteanu S, et al. “Comprehensive Review on AI in Ophthalmology”, Diagnostics, Vol. 13, No. 1, Article 100, 2022.