ArticleNature communications2025
Enhancing diagnostic accuracy in rare and common fundus diseases with a knowledge-rich vision-language model.
Abstract read
In one paragraph
Article in Nature communications, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 19 papers.
0numbers the graph read from it
0cells of the map it votes in
19citing papers in PubMed
–field-weighted citation impact
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
19 citing papers in PubMed.
- AI-based clinician decision support system for diagnosis of inherited retinal diseases: a multicenter, randomized trial.Nature medicine · 2026Trial
- The Underutilized Ocular Fundus in Emergency Departments: Current Progress and Future Prospect of Imaging and Artificial Intelligence for Patient Care.Ophthalmology science · 2026Review
- A Text-Guided Lesion Mining Vision-Language Ordinal Classification Framework for Diabetic Retinopathy Grading.Journal of imaging · 2026Article
- From generalization to precision: A large domain-specific pretrained model for specialized medical tasks.Cell reports. Medicine · 2026Article
- MRICombo: a deep-learning-based framework for universal volumetric segmentation grading-staging and malignancy detection across heterogeneous MRI.Nature communications · 2026Article
- Learning Ophthalmologist Clinical Reasoning for Glaucoma Diagnosis from Fundus Images.medRxiv : the preprint server for health sciences · 2026Article
- Current Applications of Artificial Intelligence in Neuro-Ophthalmic Imaging: A Narrative Approach.Medical sciences (Basel, Switzerland) · 2026Review
- Medical Vision-Language Models: Existing Technologies, Clinical Applications and Future Directions.Sensors (Basel, Switzerland) · 2026Review
- A gated task-attentive multi-task network for unified retinal image analysis.Scientific reports · 2026Article
- Comparative Analysis of General-Purpose vs. Domain-Specific Multimodal Models for Diabetic Retinopathy Classification.Diagnostics (Basel, Switzerland) · 2026Article
- Centering the marginalized: AI-driven strategies for advancing health equity in rare disease care.Patterns (New York, N.Y.) · 2026Review
- OBUSight: Clinically Aligned Generative AI for Ophthalmic Ultrasound Interpretation and Diagnosis.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Understanding pre-training data effects in retinal foundation models using two large fundus cohorts.Nature communications · 2026Article
- Beyond convolutions and supervised learning with transformers and representation learning for retinal image analysis.Progress in retinal and eye research · 2026Review
- Benchmarking Vision Encoders for Image Classification in Ophthalmology.Computational and structural biotechnology journal · 2026Article
- Compact vision language models enable efficient and interpretable optical coherence tomography through layer-specific multimodal learning.Communications medicine · 2025Article
- AI-driven enhancements in rare disease diagnosis and support system optimization.Intractable & rare diseases research · 2025Article
- Computational toxicology in drug discovery: applications of artificial intelligence in ADMET and toxicity prediction.Briefings in bioinformatics · 2025Review
- A systematic review of vision and vision-language foundation models in ophthalmology.Advances in ophthalmology practice and researchReview
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
49 authors.
Meng Wang *Centre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.ORCID http://orcid.org/0000-0001-7882-1747
Tian Lin *Joint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.ORCID http://orcid.org/0000-0002-6415-5381
Aidi LinJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.ORCID http://orcid.org/0000-0002-2214-7957
Kai YuDepartment of Radiology, University of Pennsylvania, Philadelphia, PA, USA.
Yuanyuan PengSchool of Biomedical Engineering, Anhui Medical University, Hefei, Anhui, China.
Lianyu WangCollege of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, Jiangsu, China.
Cheng ChenDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, China.
Ke ZouNational Key Laboratory of Fundamental Science on Synthetic Vision and the College of Computer Science, Sichuan University, Chengdu, Sichuan, China.
Huiyu LiangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Man ChenJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Xue YaoJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Meiqin ZhangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Binwei HuangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Chaoxin ZhengJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Peixin ZhangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Wei ChenJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Yilong LuoJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Yifan ChenJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Honghe XiaJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Tingkun ShiJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Qi ZhangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Jinming GuoJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Xiaolin ChenJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Jingcheng WangBig Vision Medical Technology Ltd., Suzhou, China.
Yih Chung ThamCentre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.ORCID http://orcid.org/0000-0002-6752-797X
Dianbo LiuCentre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Wendy WongCentre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Sahil ThakurSingapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore.ORCID http://orcid.org/0000-0002-7948-6992
Beau J FennerSingapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore.ORCID http://orcid.org/0000-0002-5356-7604
Danqi FangDepartment of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, China.
Siying LiuShenzhen Longgang E.N.T Hospital, Shenzhen, Guangdong, China.
Qingyun LiuShenzhen Longgang E.N.T Hospital, Shenzhen, Guangdong, China.
Yuqiang HuangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Hongqiang ZengDongguan Songshan Lake Central Hospital, Dongguan, Guangdong, China.
Yanda MengDepartment of Computer Science, University of Exeter, Exeter, UK.
Yukun ZhouCentre for Medical Image Computing, University College London, London, UK.ORCID http://orcid.org/0000-0002-0840-6422
Zehua JiangTsinghua Medicine of Tsinghua University, Beijing, China.
Minghui QiuFoshan Aier Zhuoyue Eye Hospital, Foshan, Guangdong, China.
Changqing ZhangCollege of Intelligence and Computing, Tianjin University, Tianjin, China.
Xinjian ChenSchool of Electronics and Information Engineering, Soochow University, Jiangsu, China.ORCID http://orcid.org/0000-0002-0871-293X
Sophia Y WangByers Eye Institute, Department of Ophthalmology, Stanford University School of Medicine, Palo Alto, CA, USA.ORCID http://orcid.org/0000-0003-0916-9403
Cecilia S LeeDepartment of Ophthalmology, University of Washington, Seattle, WA, USA.ORCID http://orcid.org/0000-0003-1994-7213
Lucia SobrinDepartment of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA, USA.
Carol Y CheungDepartment of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, China.ORCID http://orcid.org/0000-0002-9672-1819
Chi Pui PangJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China.
Pearse A KeaneNIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust, London, UK.ORCID http://orcid.org/0000-0002-9239-745X
Ching-Yu ChengCentre for Innovation and Precision Eye Health, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore. chingyu.cheng@nus.edu.sg.ORCID http://orcid.org/0000-0003-0655-885X
Haoyu ChenJoint Shantou International Eye Center, Shantou University and the Chinese University of Hong Kong, Shantou, Guangdong, China. drchenhaoyu@gmail.com.ORCID http://orcid.org/0000-0003-0676-4610
Huazhu FuInstitute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore, Singapore. hzfu@ieee.org.ORCID http://orcid.org/0000-0002-9702-5524
Funding
Aging eyes and aging brains in studying alzheimer's disease: Modern ophthalmic data collection in the adult changes in thought (ACT) studyR01AG060942 · NIA · WASHINGTON UNIVERSITY · PI Cecilia Sungmin Lee · 2019 to 2026
$39.4MBridge2AI:Salutogenesis Data Generation ProjectOT2OD032644 · OD · WASHINGTON UNIVERSITY · PI AYYAGARI, RADHA, BAHMANI, AMIR · 2022 to 2025
$32.7MNIA NIH HHS R01 AG060942NIH HHS OT2 OD032644
Abstract
Previous foundation models for fundus images were pre-trained with limited disease categories and knowledge base. Here we introduce RetiZero, a vision-language model that incorporates knowledge from over 400 fundus diseases. The model is pre-trained on 341,896 fundus images with accompanying text descriptions gathered from diverse sources across multiple ethnicities and countries. RetiZero demonstrates exceptional performance across various downstream tasks including zero-shot disease recognition, image-to-image retrieval, clinical diagnosis assistance, few-shot fine-tuning, and cross-domain disease identification. In zero-shot scenarios, it achieves Top-5 accuracies of 0.843 for 15 diseases and 0.756 for 52 diseases, while for image-to-image retrieval, it scores 0.950 and 0.886 respectively. Notably, RetiZero's Top-3 zero-shot performance exceeds the average diagnostic accuracy of 19 ophthalmologists from Singapore, China, and the United States. The model particularly enhances clinicians' ability to diagnose rare fundus conditions, highlighting its potential value for integration into clinical settings where diverse eye diseases are encountered.
Indexed as
Fundus OculiRare DiseasesRetinal DiseasesChinaHumansLanguageSingapore
Identifiers
What OpenQuestion holds
Textmetadata
LicenceCC BY-NC-ND
Read underepoch 390
Registered trials
None linked
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.