Large vision foundation models have been widely adopted for retinal disease classification without systematic evidence justifying their parameter requirements. In the present work we address two critical questions: First, are large domain-specific foundation models essential, or do compact general-purpose architectures suffice? Second, does specialized retinal pretraining justify its computational cost? To answer this, we benchmark initialization strategies across four retinal imaging classification tasks spanning Optical Coherence Tomography (OCT) and Color Fundus Photography (CFP) modalities: 8-class OCT classification, 3-class diabetic macular edema (DME), 5-class diabetic retinopathy (DR), and 3-class glaucoma (GL) detection. We evaluate 12-13 model configurations per task, including vision transformers (22.8M-86.6M parameters), Swin Transformers (27.6M-28.3M), ConvNeXt (28.6M), and the domain-specific RETFound models (303M), under identical training conditions. Our results challenge prevailing assumptions: First, we demonstrate that pretraining provides universal benefits (5.18-18.41% improvement), scaling with task difficulty. Second, compact architectures (27-29M) dominate Pareto frontiers; SwinV2-tiny achieves top-1 performance on three datasets. Third, RETFound (303M) justifies its computational cost only for challenging DR grading (accuracy of 71.15%), while ImageNet pretraining proves to be sufficient with all other tasks (DME accuracy: 99.24%, OCT accuracy: 97.96%). CFP tasks show larger pretraining accuracy gains (9.13-18.41%) than OCT (5.18%). Thus, the evidence suggests that compact general-purpose models deliver near-optimal performance for most retinal classification tasks; specialized foundation models warranted only for fine-grained discrimination under extreme class imbalance.
OCTCube-M: A 3D multimodal optical coherence tomography foundation model for retinal and systemic diseases with cross-cohort and cross-device validation
UrFound: Towards Universal Retinal Foundation Models via Knowledge-Guided Masked Modeling
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（A*STAR））；Singapore Eye Research Institute, Singapore National Eye Centre（新加坡眼科研究所，新加坡国家眼科中心）
MM-Retinal: Knowledge-Enhanced Foundational Pretraining with Fundus Image-Text Expertise
School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Ministry of Education, China（教育部新一代人工智能技术及其交叉应用重点实验室）；Nanjing University of Science and Technology, Nanjing, China（南京理工大学）；Agency for Science, Technology and Research (A*STAR), Singapore（新加坡科技研究局）
RET-CLIP: A Retinal Image Foundation Model Pre-trained with Clinical Diagnostic Reports
Beijing Institute of Technology（北京理工大学）；Beijing Tongren Hospital（北京同仁医院）；Capital Medical University（首都医科大学）；Beijing Institute of Ophthalmology（北京眼科研究所）
Block Expanded DINORET: Adapting Natural Domain Foundation Models for Retinal Imaging Without Catastrophic Forgetting
Stadtspital Zürich（苏黎世市立医院）；Spross Research Institute（斯普罗斯研究所）；Gutblick Research（古特布里克研究公司）；Balgrist University Hospital（巴尔格里斯特大学医院）；Moorfields Eye Hospital NHS Foundation Trust（摩尔菲尔德眼科医院国民保健服务基金会信托）；Institute of Ophthalmology, University College London（伦敦大学学院眼科研究所）；University College London（伦敦大学学院）；National University of Singapore（新加坡国立大学）；Singapore Eye Research Institute, Singapore National Eye Centre（新加坡国家眼科中心新加坡眼科研究所）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；iScreen 2 Prevent LLC（iScreen 2 Prevent有限责任公司）；Bascom Palmer Eye Institute, University of Miami（迈阿密大学巴斯康帕默眼科研究所）；University of Heidelberg（海德堡大学）；Semmelweis University（塞梅尔魏斯大学）
A Disease-Specific Foundation Model Using Over 100K Fundus Images: Release and Validation for Abnormality and Multi-Disease Classification on Downstream Tasks
Seoul National University（首尔大学）；Seoul National University Hospital（首尔大学附属医院）
Renmin University of China（中国人民大学）；Visionary Intelligence Ltd（远见智能有限公司）；Tongren Hospital（同仁医院）
For retinal image matching (RIM), we propose SuperRetina, the first end-to-end method with jointly trainable keypoint detector and descriptor. SuperRetina is trained in a novel semi-supervised manner. A small set of (nearly 100) images are incompletely labeled and used to supervise the network to detect keypoints on the vascular tree. To attack the incompleteness of manual labeling, we propose Progressive Keypoint Expansion to enrich the keypoint labels at each training epoch. By utilizing a keypoint-based improved triplet loss as its description loss, SuperRetina produces highly discriminativ…
Representation Transfer of Foundation Models for Ultra-Widefield Retinal Imaging
Institute of Ophthalmology, University College London（伦敦大学学院眼科研究所）；Wake Forest University School of Medicine（维克森林大学医学院）；Virginia Tech-Wake Forest University School of Biomedical Engineering and Sciences（弗吉尼亚理工大学-维克森林大学生物医学工程与科学学院）；University of Zagreb Faculty of Electrical Engineering and Computing（萨格勒布大学电气工程与计算机学院）；NIHR Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust（NIHR生物医学研究中心，摩尔菲尔兹眼科医院NHS基金会信托）
Multimodal Deep Learning for Stroke Prediction and Detection using Retinal Imaging and Clinical Data
Division of Engineering, New York University Abu Dhabi（纽约大学阿布扎赫尔分校工程系）；Institute for Healthier Living Abu Dhabi（阿布扎赫尔健康生活研究所）；Eye Institute at Cleveland Clinic Abu Dhabi（阿布扎赫尔克利夫兰医学中心眼科研究所）；Canberra Hospital（堪培拉医院）
Enhancing Diagnostic Reliability of Foundation Model with Uncertainty Estimation in OCT Images
Joint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong（汕头大学香港中文大学联合汕头国际眼科中心）；College of Computer Science, Sichuan University（四川大学计算机学院）；First Affiliated Hospital of Anhui Medical University（安徽医科大学第一附属医院）；School of Biomedical Engineering, Anhui Medical University（安徽医科大学生物医学工程学院）；School of Electronics and Information Engineering, Soochow University（苏州大学电子信息工程学院）；State Key Laboratory of Radiation Medicine and Protection, Soochow University（苏州大学放射医学与防护国家重点实验室）；Beth Israel Deaconess Medical Center, Harvard Medical School（哈佛医学院贝斯以色列女执事医疗中心）；Institute of High Performance Computing (IHPC)（高性能计算研究所）
State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Vision Science, Guangdong Provincial Clinical Research Center for Ocular Diseases（眼科学国家重点实验室、中山眼科中心、中山大学、广东省眼科学重点实验室和视觉科学、广东省眼科临床研究中心）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Hainan International College, Minzu University of China（海南国际学院，中国民族大学）；School of Information Technology, Faculty of Business and Hospitality, Torrens University Australia（澳大利亚托伦斯大学信息科技学院，商业与酒店管理学院）；AIM for Health Lab, Faculty of IT, Monash University, Australia（健康AIM实验室，墨尔本大学IT学院，澳大利亚）；Department of Ophthalmology, Guangzhou First People’s Hospital, the Second Affiliated Hospital of South China University of Technology（广州第一人民医院，华南理工大学第二附属医院）；The Third Xiangya Hospital of Central South University（中南大学湘雅医学院第三医院）
Metadata-enhanced contrastive learning from retinal optical coherence tomography images
Imperial College London（帝国理工学院）；Medical University of Vienna（维也纳医科大学）；University of Michigan（密歇根大学）；King’s College London（伦敦国王学院）；Institute of Molecular and Clinical Ophthalmology Basel（巴塞尔分子与临床眼科研究所）；Universitat Basel（巴塞尔大学）；University College London（伦敦大学学院）；Moorfields Eye Hospital（摩尔菲尔兹眼科医院）；University of Southampton（南安普顿大学）
EyeMVP: OCT-Informed Fundus Representation Learning via Paired CFP--OCT Pretraining
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University（首都医科大学附属北京同仁医院北京同仁眼科中心）；Liangxiang Hospital of Beijing Fangshan District, Capital Medical University（首都医科大学北京市房山区良乡医院）；The Third People's Hospital of Dalian（大连市第三人民医院）；National Clinical Research Center for Endocrine and Metabolic Diseases, The Second Xiangya Hospital of Central South University（中南大学湘雅二医院国家内分泌代谢病临床医学研究中心）；The Central Hospital of Baoji City（宝鸡市中心医院）；Wuxi No.2 People's Hospital, Affiliated Wuxi Clinical College of Nantong University（南通大学附属无锡临床学院无锡市第二人民医院）；Shenzhen Eye Hospital, Southern Medical University（南方医科大学深圳眼科医院）；Beijing Friendship Hospital, Capital Medical University（首都医科大学附属北京友谊医院）
TAPE: A two-stage parameter-efficient adaptation framework for foundation models in OCT-OCTA analysis
National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases（传染病智能追踪与预测国家重点实验室）；Tianjin Key Laboratory of Intelligent Robotic（天津市智能机器人重点实验室）；Institute of Robotics and Automatic Information System, Nankai University（南开大学机器人与自动化信息系统研究所）；Institute of Intelligence Technology and Robotic Systems（智能技术与机器人系统研究所）；Shenzhen Research Institute of Nankai University（南开大学深圳研究院）
Generalist versus Specialist Vision Foundation Models for Ocular Disease and Oculomics
Institute of Ophthalmology, University College London（伦敦大学学院眼科研究所）；Hawkes Institute, University College London（伦敦大学学院霍克斯研究所）；NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust（莫菲尔德眼科医院 NHS 基金会信托 NIHR 生物医学研究中心）；Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院）；Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore（新加坡国立大学杨潞龄医学院创新与精准眼健康中心）；Singapore Eye Research Institute, Singapore National Eye Centre（新加坡国家眼科中心新加坡眼科研究所）；Chinese University of Hong Kong（香港中文大学）；Shanghai Jiao Tong University（上海交通大学）；MOE Key Laboratory of AI, School of Electronic, Information, and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院教育部人工智能重点实验室）；Stadtspital Zürich（苏黎世市立医院）；Spross Research Institute（斯普罗斯研究所）；Tsinghua Medicine, Tsinghua University（清华大学清华医学）；Beijing Visual Science and Translational Eye Research Institute, Beijing Tsinghua Changgung Hospital（北京清华长庚医院北京视觉科学与转化眼科研究所）；University College London（伦敦大学学院）
Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
The Chinese University of Hong Kong（香港中文大学）；The University of Hong Kong（香港大学）；Institute of Medical Intelligence and XR, The Chinese University of Hong Kong（香港中文大学医学智能与扩展现实研究所）
FusionFM: Fusing Eye-specific Foundational Models for Optimized Ophthalmic Diagnosis
Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore（新加坡国立大学 Yong Loo Lin 医学院眼科系）；Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore（新加坡国立大学 Yong Loo Lin 医学院创新与精准眼科健康中心）；Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore（新加坡眼科研究院）；Ophthalmology and Visual Science Academic Clinical Program, Duke-NUS Medical School, Singapore, Singapore（杜克-国立新加坡大学医学学校眼科与视觉科学学术临床项目）；Centre for Medical Image Computing, University College London, London, United Kingdom（伦敦大学学院医学图像计算中心）；Joint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, China（汕尾国际眼科中心，汕尾大学及香港中文大学）；Department of Ophthalmology, Stadtspital Zürich, Zurich, Switzerland（苏黎世州立医院眼科部）；Spross Research Institute, Zurich, Switzerland（苏黎世 Spross 研究院）；Institute of High Performance Computing, A*STAR, Singapore（新加坡 A*STAR 高性能计算研究院）；NIHR Biomedical Research Centre, Moorfields Eye Hospital NHS Foundation Trust, London, United Kingdom（英国国家健康服务基金会 Moorfields 眼科医院生物医学研究中心）；Institute of Ophthalmology, University College London, London, United Kingdom（伦敦大学学院眼科研究院）
Retinal artery/vein (A/V) classification lays the foundation for the quantitative analysis of retinal vessels, which is associated with potential risks of various cardiovascular and cerebral diseases. The topological connection relationship, which has been proved effective in improving the A/V classification performance for the conventional graph based method, has not been exploited by the deep learning based method. In this paper, we propose a Topology Ranking Generative Adversarial Network (TR-GAN) to improve the topology connectivity of the segmented arteries and veins, and further to boost…
Topology-Driven Transferability Estimation for 3D Medical Vision Foundation Models
National Institute of Health Data Science, Peking University（北京大学健康数据科学研究所）；Institute of Medical Technology, Peking University（北京大学医学技术研究所）；Deepwise Co., Ltd.（深度智医科技有限公司）；State Key Laboratory of General Artificial Intelligence, Peking University（北京大学通用人工智能国家重点实验室）；Wangxuan Institute of Computer Technology, Peking University（北京大学王选计算机研究所）
Early Intervention for VFM-based Multimodal Medical Image Classification
Renmin University of China（中国人民大学）；Beijing Key Laboratory for Intelligent Diagnosis of Fundus Diseases and Drug-Device R&D and Translation（眼底疾病智能诊断与药械研发转化北京市重点实验室）
本文提出EI框架，通过早期干预提升多模态影像疾病识别性能，引入MoR方法优化Vision Foundation Models适应，验证了在三个公开数据集上的有效性。
Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection
Faculty of Biomedical Engineering, Technion-IIT（技术学院生物医学工程系）；Taub Faculty of Computer Science, Technion-IIT（技术学院计算机科学系）；Faculty of Mathematics, Technion-IIT（技术学院数学系）；Department of Ophthalmology, Hillel Yaffe Medical Center（希勒尔·亚法医疗中心眼科部）；The Ruth and Rappaport Faculty of Medicine, Technion-IIT（技术学院医学院）；Ophthalmology Department, São Paulo Federal University（圣保罗联邦大学眼科部）；Medical Engineering and Science, Massachusetts Institute of Technology（麻省理工学院医学工程与科学系）；The Adelson School of Medicine, Ariel University（阿里尔大学阿德勒医学学校）
Is an Ultra Large Natural Image-Based Foundation Model Superior to a Retina-Specific Model for Detecting Ocular and Systemic Diseases?
National University of Singapore（新加坡国立大学）；Northeastern University（东北大学）；University College London（伦敦大学学院）；NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust（莫菲尔德眼科医院 NHS 基金会信托 NIHR 生物医学研究中心）；Singapore Eye Research Institute, Singapore National Eye Centre（新加坡眼科研究所，新加坡国家眼科中心）；Institute of High-Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）；The Chinese University of Hong Kong（香港中文大学）；Stadtspital Zürich（苏黎世市立医院）；Spross Research Institute（斯普罗斯研究所）；Semmelweis University（塞梅尔维斯大学）；Shantou University（汕头大学）；Shantou University Medical College（汕头大学医学院）
