{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T17:16:33Z","timestamp":1788974193318,"version":"build-2803163510"},"reference-count":85,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"2","funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["PCEFP_3202756"],"award-info":[{"award-number":["PCEFP_3202756"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Comput Struct Biotechnol J"],"published-print":{"date-parts":[[2026,1,1]]},"abstract":"<jats:p>Foundation vision encoders are rapidly emerging as the standard for retinal artificial intelligence. Yet, ophthalmology still lacks a comprehensive benchmark, leaving model selection for basic science and clinical translation as guesswork. Here, we present a large-scale comparison of 34 pretrained encoders on 39 classification tasks covering color fundus photography, optical coherence tomography, scanning laser ophthalmoscopy, and ultrawidefield imaging. Using a unified pipeline, we compare frozen-feature evaluation, linear probing, and end-to-end fine-tuning to determine which models translate into strong downstream performance. We show that ophthalmic transfer is highly task dependent: no single encoder dominates, and model rankings vary across datasets. Contrary to common expectations, retina-specific pretraining does not confer an advantage. Instead, several natural-image and cross-domain medical encoders match or surpass ophthalmology-specialized models, with the histopathology-pretrained Virchow achieving the strongest overall performance. In addition, pathology-pretrained encoders consistently place near the top, revealing the value of cross-domain pretraining for ophthalmic applications. We further show that inexpensive proxy evaluations are unreliable substitutes for full fine-tuning. Across fairness analyses, all encoders exhibit similar age- and sex-associated performance gaps, and larger models appear more sensitive to suboptimal learning rates, whereas smaller encoders are robust. Together, these findings provide an objective reference for encoder selection in ophthalmology and show that reliable retinal artificial intelligence depends not only on model scale or domain-specific pretraining but also on careful, protocol-aware evaluation. By releasing our code, splits, and benchmarking pipeline, we aim to establish a transparent foundation for future ophthalmic foundation-model research.<\/jats:p>","DOI":"10.34133\/csbj.0178","type":"journal-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T09:07:52Z","timestamp":1783501672000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Vision Encoders for Image Classification in Ophthalmology"],"prefix":"10.34133","volume":"35","author":[{"given":"Jay","family":"Zoellin","sequence":"first","affiliation":[{"name":"Institute of Molecular and Clinical Ophthalmology Basel (IOB)","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Colin","family":"Merk","sequence":"additional","affiliation":[{"name":"Institute of Molecular and Clinical Ophthalmology Basel (IOB)","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0766-6246","authenticated-orcid":true,"given":"Bence","family":"Gy\u00f6rgy","sequence":"additional","affiliation":[{"name":"Institute of Molecular and Clinical Ophthalmology Basel (IOB)","place":["Switzerland"]},{"name":"Department of Ophthalmology, \rUniversity of Basel, Basel, Switzerland."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"221","published-online":{"date-parts":[[2026,9,1]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"crossref","unstructured":"M\u00fcller PL Wolf S Dolz-Marco R Tafreshi A Schmitz-Valckenberg S Holz FG. Ophthalmic diagnostic imaging: Retina. In: Bille JF editor. High resolution imaging in microscopy and ophthalmology: New frontiers in biomedical optics. Cham (Switzerland): Springer; 2019. p. 87\u2013106.","DOI":"10.1007\/978-3-030-16638-0_4"},{"issue":"18","key":"e_1_3_4_3_2","doi-asserted-by":"crossref","first-page":"5433","DOI":"10.3390\/jcm11185433","article-title":"Editorial: Imaging in ophthalmology","volume":"11","author":"Ferrara M","year":"2022","unstructured":"Ferrara M, Zheng Y, Romano V. Editorial: Imaging in ophthalmology. J Clin Med. 2022;11(18):5433.","journal-title":"J Clin Med"},{"key":"e_1_3_4_4_2","unstructured":"American Academy of Ophthalmology. What is optical coherence tomography? American Academy of Ophthalmology. 2025. [accessed 12 Aug 2025] https:\/\/www.aao.org\/eye-health\/treatments\/what-is-optical-coherence-tomography"},{"key":"e_1_3_4_5_2","doi-asserted-by":"crossref","unstructured":"Fischer J Otto T Delori F Pace L Staurenghi G Bille JF. Scanning laser ophthalmoscopy (SLO). In: Bille JF editor. High resolution imaging in microscopy and ophthalmology: New frontiers in biomedical optics. Cham (Switzerland): Springer; 2019. p. 15\u201328.","DOI":"10.1007\/978-3-030-16638-0_2"},{"issue":"4","key":"e_1_3_4_6_2","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1159\/000329597","article-title":"Digital ocular fundus imaging: A review","volume":"226","author":"Bernardes R","year":"2011","unstructured":"Bernardes R, Serranho P, Lobo C. Digital ocular fundus imaging: A review. Ophthalmologica. 2011;226(4):161\u2013181.","journal-title":"Ophthalmologica"},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","unstructured":"Jacob S Sivaraj RR. Imaging in diabetic retinopathy. In: Sivaraj RR Dodson PM editors. Diabetic retinopathy: Screening to treatment. Oxford (UK): Oxford University Press; 2020. p. 161\u2013170.","DOI":"10.1093\/med\/9780198834458.003.0018"},{"issue":"5","key":"e_1_3_4_8_2","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1016\/S0161-6420(13)38011-7","article-title":"Early photocoagulation for diabetic retinopathy: ETDRS report number 9","volume":"98","author":"Early Treatment Diabetic Retinopathy Study Research Group","year":"1991","unstructured":"Early Treatment Diabetic Retinopathy Study Research Group. Early photocoagulation for diabetic retinopathy: ETDRS report number 9. Ophthalmology. 1991;98(5):766\u2013785.","journal-title":"Ophthalmology"},{"issue":"20","key":"e_1_3_4_9_2","doi-asserted-by":"crossref","first-page":"1897","DOI":"10.1056\/NEJMoa1102673","article-title":"Ranibizumab and bevacizumab for neovascular age-related macular degeneration","volume":"364","author":"CATT Research Group","year":"2011","unstructured":"CATT Research Group, Martin DF, Maguire MG, Ying GA, Grunwald JE, Fine SL, Jaffe GJ. Ranibizumab and bevacizumab for neovascular age-related macular degeneration. N Engl J Med. 2011;364(20):1897\u20131908.","journal-title":"N Engl J Med"},{"issue":"6","key":"e_1_3_4_10_2","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1007\/s00592-017-0974-1","article-title":"The English National Screening Programme for diabetic retinopathy 2003\u20132016","volume":"54","author":"Scanlon PH","year":"2017","unstructured":"Scanlon PH. The English National Screening Programme for diabetic retinopathy 2003\u20132016. Acta Diabetol. 2017;54(6):515\u2013525.","journal-title":"Acta Diabetol"},{"issue":"4","key":"e_1_3_4_11_2","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/S2213-8587(19)30411-5","article-title":"Screening for diabetic retinopathy: New perspectives and challenges","volume":"8","author":"Vujosevic S","year":"2020","unstructured":"Vujosevic S, Aldington SJ, Silva P, Hern\u00e1ndez C, Scanlon P, Peto T, Sim\u00f3 R. Screening for diabetic retinopathy: New perspectives and challenges. Lancet Diabetes Endocrinol. 2020;8(4):337\u2013347.","journal-title":"Lancet Diabetes Endocrinol"},{"issue":"7981","key":"e_1_3_4_12_2","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou Y","year":"2023","unstructured":"Zhou Y, Chia MA, Wagner SK, Ayhan MS, Williamson DJ, Struyven RR, Liu T, Xu M, Lozano MG, Woodward-Court P, et al. A foundation model for generalizable disease detection from retinal images. Nature. 2023;622(7981):156\u2013163.","journal-title":"Nature"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6"},{"issue":"1","key":"e_1_3_4_14_2","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1038\/s41746-025-01726-8","article-title":"A scoping review of artificial intelligence as a medical device for ophthalmic image analysis in Europe, Australia and America","volume":"8","author":"Ong AY","year":"2025","unstructured":"Ong AY, Taribagil P, Sevgi M, Kale AU, Dow ER, Macdonald T, Kras A, Maniatopoulos G, Liu X, Keane PA, et al. A scoping review of artificial intelligence as a medical device for ophthalmic image analysis in Europe, Australia and America. npj Digit Med. 2025;8(1):323.","journal-title":"npj Digit Med"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2020.3269"},{"issue":"3","key":"e_1_3_4_16_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.aopr.2022.100078","article-title":"Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives","volume":"2","author":"Jin K","year":"2022","unstructured":"Jin K, Ye J. Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives. Adv Ophthalmol Pract Res. 2022;2(3): Article 100078.","journal-title":"Adv Ophthalmol Pract Res"},{"key":"e_1_3_4_17_2","unstructured":"Dosovitskiy A Beyer L Kolesnikov A Weissenborn D Zhai X Unterthiner T Dehghani M Minderer M Heigold G Gelly S et al. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2010.11929"},{"key":"e_1_3_4_18_2","unstructured":"Rajpurkar P Irvin J Zhu K Yang B Mehta H Duan T Ding D Bagul A Langlotz C Shpanskaya K et al. CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1711.05225"},{"key":"e_1_3_4_19_2","unstructured":"Chen S Ma K Zheng Y. Med3D: Transfer learning for 3D medical image analysis. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1904.00625"},{"issue":"12","key":"e_1_3_4_20_2","article-title":"Development and validation of a multimodal multitask vision foundation model for generalist ophthalmic artificial intelligence","volume":"1","author":"Qiu J","year":"2024","unstructured":"Qiu J, Wu J, Wei H, Shi P, Zhang M, Sun Y, Li L, Liu H, Liu H, Hou S, et al. Development and validation of a multimodal multitask vision foundation model for generalist ophthalmic artificial intelligence. NEJM AI. 2024;1(12): Article AIoa2300221.","journal-title":"NEJM AI"},{"key":"e_1_3_4_21_2","unstructured":"Sellergren A Kazemzadeh S Jaroensri T Kiraly A Traverse M Kohlberger T Xu S Jamil F Hughes C Lau C et al. MedGemma: Technical report. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2507.05201"},{"key":"e_1_3_4_22_2","unstructured":"Oquab M Darcet T Moutakanni T Vo H Szafraniec M Khalidov V Fernandez P Haziza D Massa F El-Nouby A et al. DINOv2: Learning robust visual features without supervision. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2304.07193"},{"issue":"10","key":"e_1_3_4_23_2","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1038\/s41591-024-03141-0","article-title":"A foundation model for clinical-grade computational pathology and rare cancers detection","volume":"30","author":"Vorontsov E","year":"2024","unstructured":"Vorontsov E, Bozkurt A, Casson A, Shaikovski G, Zelechowski M, Severson K, Zimmermann E, Hall J, Tenenholtz N, Fusi N, et al. A foundation model for clinical-grade computational pathology and rare cancers detection. Nat Med. 2024;30(10):2924\u20132935.","journal-title":"Nat Med"},{"key":"e_1_3_4_24_2","unstructured":"Zoellin J Merk C Buob M Saad A Giesser S Spitznagel T Turgut F Santos R Zhou Y Wagner S et al. Block expanded DINORET: Adapting natural domain foundation models for retinal imaging without catastrophic forgetting. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2409.17332"},{"key":"e_1_3_4_25_2","doi-asserted-by":"crossref","unstructured":"Du J Guo J Zhang W Yang S Liu H Li H Wang N. RET-CLIP: A retinal image foundation model pre-trained with clinical diagnostic reports. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2405.14137","DOI":"10.1007\/978-3-031-72390-2_66"},{"issue":"1","key":"e_1_3_4_26_2","doi-asserted-by":"crossref","first-page":"5528","DOI":"10.1038\/s41467-025-60577-9","article-title":"Enhancing diagnostic accuracy in rare and common fundus diseases with a knowledge-rich vision-language model","volume":"16","author":"Wang M","year":"2025","unstructured":"Wang M, Lin T, Lin A, Yu K, Peng Y, Wang L, Chen C, Zou K, Liang H, Chen M, et al. Enhancing diagnostic accuracy in rare and common fundus diseases with a knowledge-rich vision-language model. Nat Commun. 2025;16(1):5528.","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_3_4_27_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2025.100923","article-title":"Can a natural image-based foundation model outperform a retina-specific model in detecting ocular and systemic diseases?","volume":"6","author":"Hou Q","year":"2026","unstructured":"Hou Q, Zhou Y, Goh JH, Zou K, Yew SM, Srinivasan S, Wang M, Lo TW, Lei X, Wagner SK, et al. Can a natural image-based foundation model outperform a retina-specific model in detecting ocular and systemic diseases? Ophthalmol Sci. 2026;6(1): Article 100923.","journal-title":"Ophthalmol Sci"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"Kornblith S Shlens J Le QV. Do better ImageNet models transfer better? In: 2019 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). New York (NY): IEEE; 2019. p. 2661\u20132671.","DOI":"10.1109\/CVPR.2019.00277"},{"key":"e_1_3_4_29_2","unstructured":"Cheng Z Li B Altmann A Keane PA Zhou Y. Enhancing contrastive learning for retinal imaging via adjusted augmentation scales. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2501.02451"},{"key":"e_1_3_4_30_2","doi-asserted-by":"crossref","unstructured":"Deng J Dong W Socher R Li L-J Li K Fei-Fei L. ImageNet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. New York (NY): IEEE; 2009. p. 248\u2013255.","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"3","key":"e_1_3_4_31_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky O","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, et al. ImageNet large scale visual recognition challenge. Int J Comput Vis. 2015;115(3):211\u2013252.","journal-title":"Int J Comput Vis"},{"issue":"1","key":"e_1_3_4_32_2","doi-asserted-by":"crossref","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data","volume":"16","author":"Wu C","year":"2025","unstructured":"Wu C, Zhang X, Zhang Y, Hui H, Wang Y, Xie W. Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data. Nat Commun. 2025;16(1):7866.","journal-title":"Nat Commun"},{"issue":"6","key":"e_1_3_4_33_2","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/s41551-025-01516-3","article-title":"Benchmarking foundation models as feature extractors for weakly supervised computational pathology","volume":"10","author":"Neidlinger P","year":"2026","unstructured":"Neidlinger P, El Nahhas OS, Muti HS, Lenz T, Hoffmeister M, Brenner H, Van Treeck M, Langer R, Dislich B, Behrens HM, et al. Benchmarking foundation models as feature extractors for weakly supervised computational pathology. Nat Biomed Eng. 2026;10(6):1113\u20131123.","journal-title":"Nat Biomed Eng"},{"issue":"1","key":"e_1_3_4_34_2","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.1038\/s41467-025-58796-1","article-title":"A clinical benchmark of public self-supervised pathology foundation models","volume":"16","author":"Campanella G","year":"2025","unstructured":"Campanella G, Chen S, Singh M, Verma R, Muehlstedt S, Zeng J, Stock A, Croken M, Veremis B, Elmas A, et al. A clinical benchmark of public self-supervised pathology foundation models. Nat Commun. 2025;16(1):3640.","journal-title":"Nat Commun"},{"key":"e_1_3_4_35_2","doi-asserted-by":"crossref","unstructured":"Li M Wen C Tian Y Shi M Luo Y Huang H Fang Y Wang M. FairFedMed: Benchmarking group fairness in federated medical imaging with FairLoRA. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2508.00873","DOI":"10.1109\/TMI.2025.3622522"},{"key":"e_1_3_4_36_2","unstructured":"Baharoon M Qureshi W Ouyang J Xu Y Aljouie A Peng W. Evaluating general purpose vision foundation models for medical image analysis: An experimental study of DINOv2 on radiology benchmarks. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2312.02366"},{"key":"e_1_3_4_37_2","doi-asserted-by":"crossref","unstructured":"Bareja R Carrillo-Perez F Zheng Y Pizurica M Nandi TN Shen J Madduri R Gevaert O. Evaluating vision and pathology foundation models for computational pathology: A comprehensive benchmark study. medRxiv. 2025. https:\/\/doi.org\/10.1101\/2025.05.08.25327250","DOI":"10.1101\/2025.05.08.25327250"},{"key":"e_1_3_4_38_2","unstructured":"Zhou Y Nderitu P Goh JH Engelmann J Wagner SK Ran A Jiang H Ju L Zou K Srinivasan S et al. Generalist versus specialist vision foundation models for ocular disease and oculomics. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2509.03421"},{"key":"e_1_3_4_39_2","unstructured":"Radford A Kim JW Hallacy C Ramesh A Goh G Agarwal S Sastry G Askell A Mishkin P Clark J et al. Learning transferable visual models from natural language supervision. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2103.00020"},{"key":"e_1_3_4_40_2","doi-asserted-by":"crossref","unstructured":"Huix JP Ganeshan AR Haslum JF S\u00f6derberg M Matsoukas C Smith K. Are natural domain foundation models useful for medical image classification? In: 2024 IEEE\/CVF winter conference on applications of computer vision (WACV). New York (NY): IEEE; 2024. p. 7619\u20137628.","DOI":"10.1109\/WACV57701.2024.00746"},{"key":"e_1_3_4_41_2","unstructured":"Zimmermann E Vorontsov E Viret J Casson A Zelechowski M Shaikovski G Tenenholtz N Hall J Klimstra D Yousfi R et al. Virchow2: Scaling self-supervised mixed magnification models in pathology. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2408.00738"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2025.02.039"},{"issue":"2","key":"e_1_3_4_43_2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"Ting DSW","year":"2019","unstructured":"Ting DSW, Pasquale LR, Peng L, Campbell JP, Lee AY, Raman R, Tan GSW, Schmetterer L, Keane PA, Wong TY. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019;103(2):167\u2013175.","journal-title":"Br J Ophthalmol"},{"key":"e_1_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.03.003"},{"key":"e_1_3_4_45_2","doi-asserted-by":"crossref","unstructured":"Yu K Zhou Y Bai Y Soh ZD Xu X Goh RS Cheng C-Y Liu Y. UrFound: Towards universal retinal foundation models via knowledge-guided masked modeling. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2408.05618","DOI":"10.1007\/978-3-031-72390-2_70"},{"key":"e_1_3_4_46_2","doi-asserted-by":"crossref","unstructured":"Zhai X Mustafa B Kolesnikov A Beyer L. Sigmoid loss for language image pre-training. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.15343","DOI":"10.1109\/ICCV51070.2023.01100"},{"issue":"1","key":"e_1_3_4_47_2","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s42256-024-00965-w","article-title":"Exploring scalable medical image encoders beyond text supervision","volume":"7","author":"P\u00e9rez-Garc\u00eda F","year":"2025","unstructured":"P\u00e9rez-Garc\u00eda F, Sharma H, Bond-Taylor S, Bouzid K, Salvatelli V, Ilse M, Bannur S, Castro DC, Schwaighofer A, Lungren MP, et al. Exploring scalable medical image encoders beyond text supervision. Nat Mach Intell. 2025;7(1):119\u2013130.","journal-title":"Nat Mach Intell"},{"key":"e_1_3_4_48_2","doi-asserted-by":"crossref","unstructured":"He K Zhang X Ren S Sun J. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). New York (NY): IEEE; 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_4_49_2","unstructured":"Darcet T Oquab M Mairal J Bojanowski P. Vision transformers need registers. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2309.16588"},{"issue":"8015","key":"e_1_3_4_50_2","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data","volume":"630","author":"Xu H","year":"2024","unstructured":"Xu H, Usuyama N, Bagga J, Zhang S, Rao R, Naumann T, Wong C, Gero Z, Gonz\u00e1lez J, Gu Y, et al. A whole-slide foundation model for digital pathology from real-world data. Nature. 2024;630(8015):181\u2013188.","journal-title":"Nature"},{"key":"e_1_3_4_51_2","unstructured":"Zhou Y Wang Z Wu Y Ong AY Wagner S Ruffell E Chia M Guan Z Ju L Engelmann J et al. Revealing the impact of pre-training data on medical foundation models. Research Square. 2025. https:\/\/www.researchsquare.com\/article\/rs-6080254\/v1"},{"issue":"1","key":"e_1_3_4_52_2","doi-asserted-by":"crossref","first-page":"6862","DOI":"10.1038\/s41467-025-62123-z","article-title":"Training a high-performance retinal foundation model with half-the-data and 400 times less compute","volume":"16","author":"Engelmann J","year":"2025","unstructured":"Engelmann J, Bernabeu MO. Training a high-performance retinal foundation model with half-the-data and 400 times less compute. Nat Commun. 2025;16(1):6862.","journal-title":"Nat Commun"},{"key":"e_1_3_4_53_2","unstructured":"Tschannen M Gritsenko A Wang X Naeem MF Alabdulmohsin I Parthasarathy N Evans T Beyer L Xia Y Mustafa B et al. SigLIP 2: Multilingual vision-language encoders with improved semantic understanding localization and dense features. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2502.14786"},{"key":"e_1_3_4_54_2","unstructured":"Yang S Du J Guo J Zhang W Liu H Li H Wang N. ViLReF: An expert knowledge enabled vision-language retinal foundation model. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2408.10894"},{"key":"e_1_3_4_55_2","unstructured":"Luo Y Khan MO Tian Y Shi M Dou Z Elze T Fang Y Wang M. FairVision: Equitable deep learning for eye disease screening via fair identity scaling. arXiv. 2024. https:\/\/doi.org\/10.48550\/arXiv.2310.02492"},{"key":"e_1_3_4_56_2","unstructured":"Pachade S Porwal P Thulkar D Kokare M Deshmukh G Sahasrabuddhe V Giancardo L Quellec G Meriaudeau F Retinal Fundus Multi-disease Image Dataset (RFMiD) IEEE DataPort (2020); https:\/\/dx.doi.org\/10.21227\/s3g7-st65"},{"issue":"1","key":"e_1_3_4_57_2","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1038\/s41597-024-04113-2","article-title":"Open ultrawidefield fundus image dataset with disease diagnosis and clinical image quality assessment","volume":"11","author":"He S","year":"2024","unstructured":"He S, Ye X, Xie W, Shen Y, Yang S, Zhong X, Guan H, Zhou X, Wu J, Shen L. Open ultrawidefield fundus image dataset with disease diagnosis and clinical image quality assessment. Sci Data. 2024;11(1):1251.","journal-title":"Sci Data"},{"key":"e_1_3_4_58_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.compeleceng.2019.106532","article-title":"OCTID: Optical coherence tomography image database","volume":"81","author":"Gholami P","year":"2020","unstructured":"Gholami P, Roy P, Parthasarathy MK, Lakshminarayanan V. OCTID: Optical coherence tomography image database. Comput Electr Eng. 2020;81: Article 106532.","journal-title":"Comput Electr Eng"},{"key":"e_1_3_4_59_2","unstructured":"Budai A Odstrcilik J. High Resolution Fundus (HRF) Image Database. FAU. 2013. [accessed 15 May 2025] https:\/\/www5.cs.fau.de\/research\/data\/fundus-images\/"},{"key":"e_1_3_4_60_2","unstructured":"Kermany D Zhang K Goldbaum M Large dataset of labeled optical coherence tomography (OCT) and chest X-ray images version 3 Mendeley Data (2018); https:\/\/doi.org\/10.17632\/rscbjbr9sj.3"},{"key":"e_1_3_4_61_2","unstructured":"Kaggle. APTOS 2019 blindness detection. Kaggle. 2019. [accessed 17 May 2025] https:\/\/kaggle.com\/competitions\/aptos2019-blindness-detection"},{"key":"e_1_3_4_62_2","doi-asserted-by":"crossref","unstructured":"Hou J Xu J Xiao F Zhao R-W Zhang Y Zou H Lu L Xue W Feng R. Cross-field transformer for diabetic retinopathy grading on two-field fundus images. In: 2022 IEEE international conference on bioinformatics and biomedicine (BIBM). New York (NY): IEEE; 2022. p. 985\u2013990.","DOI":"10.1109\/BIBM55620.2022.9995459"},{"key":"e_1_3_4_63_2","unstructured":"Kaggle. Diabetic retinopathy detection. Kaggle. 2015. [accessed 19 May 2025] https:\/\/kaggle.com\/competitions\/diabetic-retinopathy-detection"},{"key":"e_1_3_4_64_2","unstructured":"Porwal P Pachade S Kamble R Kokare M Deshmukh G Sahasrabuddhe V Meriaudeau F Indian Diabetic Retinopathy Image Dataset (IDRiD) IEEE DataPort (2018); https:\/\/dx.doi.org\/10.21227\/H25W98"},{"key":"e_1_3_4_65_2","doi-asserted-by":"crossref","unstructured":"Nakayama LF Goncalves M Ribeiro LZ Santos H Ferraz D Malerbi F Celi LA Regatieri C A Brazilian Multilabel Ophthalmological Dataset (BRSET) version 1.0.1 PhysioNet (2024) rRID:SCR_007345; https:\/\/doi.org\/10.13026\/1pht-2b69","DOI":"10.1101\/2024.01.23.24301660"},{"key":"e_1_3_4_66_2","unstructured":"Nakayama LF Zago Ribeiro L Restrepo D Santos Barboza N Dias Fiterman R Vieira Sousa M Pereira AD Regatieri C Malerbi FK Andrade R mBRSET a Mobile Brazilian Retinal Dataset version 1.0 PhysioNet (2024); https:\/\/doi.org\/10.13026\/qxpd-1y65"},{"issue":"3","key":"e_1_3_4_67_2","doi-asserted-by":"crossref","first-page":"231","DOI":"10.5566\/ias.1155","article-title":"Feedback on a publicly distributed image database: The Messidor database","volume":"33","author":"Decenci\u00e8re E","year":"2014","unstructured":"Decenci\u00e8re E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, et al. Feedback on a publicly distributed image database: The Messidor database. Image Anal Stereol. 2014;33(3):231\u2013234.","journal-title":"Image Anal Stereol"},{"issue":"1","key":"e_1_3_4_68_2","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1038\/s41597-022-01388-1","article-title":"PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment","volume":"9","author":"Kovalyk O","year":"2022","unstructured":"Kovalyk O, Morales-S\u00e1nchez J, Verd\u00fa-Monedero R, Sell\u00e9s-Navarro I, Palaz\u00f3n-Cabanes A, Sancho-G\u00f3mez J-L. PAPILA: Dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment. Sci Data. 2022;9(1):291.","journal-title":"Sci Data"},{"key":"e_1_3_4_69_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.ads4593"},{"key":"e_1_3_4_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3377552"},{"issue":"3","key":"e_1_3_4_71_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2023.100300","article-title":"Characteristics of a large, labeled data set for the training of artificial intelligence for glaucoma screening with fundus photographs","volume":"3","author":"Lemij HG","year":"2023","unstructured":"Lemij HG, Vente C, S\u00e1nchez CI, Vermeer KA. Characteristics of a large, labeled data set for the training of artificial intelligence for glaucoma screening with fundus photographs. Ophthalmol Sci. 2023;3(3): Article 100300.","journal-title":"Ophthalmol Sci"},{"key":"e_1_3_4_72_2","unstructured":"Wang Z Zou H Guo Y Guo S Zhao X Wang Y Sun M Fundus Image Myopia Development (FIMD) dataset version 1 Mendeley Data (2023); https:\/\/data.mendeley.com\/datasets\/jkzsh6pcv4\/1"},{"issue":"1","key":"e_1_3_4_73_2","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1038\/s41597-023-02424-4","article-title":"GRAPE: A multi-modal dataset of longitudinal follow-up visual field and fundus images for glaucoma management","volume":"10","author":"Huang X","year":"2023","unstructured":"Huang X, Kong X, Shen Z, Ouyang J, Li Y, Jin K, Ye J. GRAPE: A multi-modal dataset of longitudinal follow-up visual field and fundus images for glaucoma management. Sci Data. 2023;10(1):520.","journal-title":"Sci Data"},{"issue":"12","key":"e_1_3_4_74_2","doi-asserted-by":"crossref","first-page":"2210","DOI":"10.1038\/s42255-024-01165-x","article-title":"AI-READI: Rethinking AI data collection, preparation and sharing in diabetes research and beyond","volume":"6","author":"AI-READI Consortium","year":"2024","unstructured":"AI-READI Consortium. AI-READI: Rethinking AI data collection, preparation and sharing in diabetes research and beyond. Nat Metab. 2024;6(12):2210\u20132212.","journal-title":"Nat Metab"},{"issue":"9","key":"e_1_3_4_75_2","doi-asserted-by":"crossref","first-page":"1677","DOI":"10.1016\/S0161-6420(03)00475-5","article-title":"Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales","volume":"110","author":"Wilkinson CP","year":"2003","unstructured":"Wilkinson CP, Ferris FL, Klein RE, Lee PP, Agardh CD, Davis M, Dills D, Kampik A, Pararajasegaram R, Verdaguer JT, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology. 2003;110(9):1677\u20131682.","journal-title":"Ophthalmology"},{"issue":"8","key":"e_1_3_4_76_2","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1016\/j.ophtha.2018.01.034","article-title":"Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy","volume":"125","author":"Krause J","year":"2018","unstructured":"Krause J, Gulshan V, Rahimy E, Karth P, Widner K, Corrado GS, Peng L, Webster DR. Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy. Ophthalmology. 2018;125(8):1264\u20131272.","journal-title":"Ophthalmology"},{"key":"e_1_3_4_77_2","unstructured":"Loshchilov I Hutter F. Decoupled weight decay regularization. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1711.05101"},{"key":"e_1_3_4_78_2","unstructured":"Kokhlikyan N Miglani V Martin M Wang E Alsallakh B Reynolds J Melnikov A Kliushkina N Araya C Yan S et al. Captum: A unified and generic model interpretability library for PyTorch. arXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2009.07896"},{"key":"e_1_3_4_79_2","doi-asserted-by":"crossref","first-page":"62600","DOI":"10.1109\/ACCESS.2025.3558506","article-title":"Contrast limited adaptive local histogram equalization method for poor contrast image enhancement","volume":"13","author":"Mohammed IM","year":"2025","unstructured":"Mohammed IM, Isa NAM. Contrast limited adaptive local histogram equalization method for poor contrast image enhancement. IEEE Access. 2025;13:62600\u201362632.","journal-title":"IEEE Access"},{"issue":"5","key":"e_1_3_4_80_2","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany DS","year":"2018","unstructured":"Kermany DS, Goldbaum M, Cai W, Valentim CCS, Liang H, Baxter SL, McKeown A, Yang G, Wu X, Yan F, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell. 2018;172(5):1122\u20131131.e9.","journal-title":"Cell"},{"key":"e_1_3_4_81_2","doi-asserted-by":"crossref","unstructured":"He K Chen X Xie S Li Y Dollar P Girshick R. Masked autoencoders are scalable vision learners. In: 2022 IEEE\/CVF conference on computer vision and pattern recognition (CVPR). New York (NY): IEEE; 2022. p. 15979\u201315988.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_4_82_2","doi-asserted-by":"crossref","unstructured":"Jin R Xu Z Zhong Y Yao Q Dou Q Zhou SK Li X. FairMedFM: Fairness benchmarking for medical imaging foundation models. In: Globerson A Mackey L Belgrave D Fan A Paquet U Tomczak J Zhang C editors. NIPS \u201924: Proceedings of the 38th international conference on neural information processing systems. Vancouver (Canada): Neural Information Processing Systems Foundation Inc. (NeurIPS); 2024. p. 111318\u2013111357. doi:10.52202\/079017-3535.","DOI":"10.52202\/079017-3535"},{"key":"e_1_3_4_83_2","doi-asserted-by":"crossref","unstructured":"Luo Y Shi M Khan MO Afzal MM Huang H Yuan S Tian Y Song L Kouhana A Elze T et al. FairCLIP: Harnessing fairness in vision-language learning. In: 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New York (NY): IEEE; 2024. p. 12289\u201312301.","DOI":"10.1109\/CVPR52733.2024.01168"},{"issue":"1","key":"e_1_3_4_84_2","doi-asserted-by":"crossref","first-page":"6261","DOI":"10.1038\/s41467-023-41974-4","article-title":"Improving model fairness in image-based computer-aided diagnosis","volume":"14","author":"Lin M","year":"2023","unstructured":"Lin M, Li T, Yang Y, Holste G, Ding Y, Van Tassel SH, Kovacs K, Shih G, Wang Z, Lu Z, et al. Improving model fairness in image-based computer-aided diagnosis. Nat Commun. 2023;14(1):6261.","journal-title":"Nat Commun"},{"issue":"1","key":"e_1_3_4_85_2","doi-asserted-by":"crossref","first-page":"576","DOI":"10.1038\/s41746-025-01852-3","article-title":"Multimodal foundation model and benchmark for comprehensive retinal oct image analysis","volume":"8","author":"Morano J","year":"2025","unstructured":"Morano J, Fazekas B, S\u00fckei E, Fecso R, Emre T, Gumpinger M, Faustmann G, Oghbaie M, Schmidt-Erfurth U, Bogunovi\u0107 H. Multimodal foundation model and benchmark for comprehensive retinal oct image analysis. npj Digit Med. 2025;8(1):576.","journal-title":"npj Digit Med"},{"key":"e_1_3_4_86_2","unstructured":"Sim\u00e9oni O Vo HV Seitzer M Baldassarre F Oquab M Jose C Khalidov V Szafraniec M Yi S Ramamonjisoa M et al. DINOv3. arXiv. 2025. https:\/\/doi.org\/10.48550\/arXiv.2508.10104"}],"container-title":["Computational and Structural Biotechnology Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/csbj.0178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T16:56:52Z","timestamp":1788973012000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/csbj.0178"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":85,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,1,1]]}},"alternative-id":["10.34133\/csbj.0178"],"URL":"https:\/\/doi.org\/10.34133\/csbj.0178","relation":{},"ISSN":["2001-0370"],"issn-type":[{"value":"2001-0370","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"assertion":[{"value":"2026-04-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-07","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0178"}}