{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T21:21:46Z","timestamp":1793222506947,"version":"4.5.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-19-LCV2-0005 - ADMIRE project"],"award-info":[{"award-number":["ANR-19-LCV2-0005 - ADMIRE project"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Retinal diseases are among the leading causes of visual impairment worldwide, where timely diagnosis and management are critical to prevent irreversible vision loss and blindness, especially in regions with limited access to ophthalmologists. While artificial intelligence (AI) has shown remarkable potential for screening ocular diseases, many existing models are heavily dependent on the datasets used for their development and often experience significant performance drops when tested on external datasets. These limitations in robustness and generalizability reduce their practical applicability in clinical settings. In this study, we proposed our newly developed deep learning architecture, FlexiVarViT is designed to enhance robustness and generalizability by addressing the unique characteristics of optical coherence tomography (OCT) imaging, such as variable data (e.g., number of slices, resolution), while processing B-scans at their native resolution (i.e., without resizing) to preserve fine anatomical details. Our method was evaluated on three datasets for the accurate detection and classification of multiple retinal pathologies using OCT images. These datasets represent diverse imaging devices (Spectralis and Optovue) and populations from France, Russia, and Iran. The results highlight the versatility, robustness, and generalizability of our model across various patient demographics and imaging systems, demonstrating significant improvements compared to state-of-the-art methods and emphasizing its potential for clinical application.<\/jats:p>","DOI":"10.1038\/s41598-025-19286-y","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T13:35:19Z","timestamp":1760016919000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A robust deep learning classifier for screening multiple retinal diseases on optical coherence tomography"],"prefix":"10.1038","volume":"15","author":[{"given":"Philippe","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gwenole","family":"Quellec","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Matta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Borderie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandre","family":"Le Guilcher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tanguy","family":"Thiery","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B\u00e9atrice","family":"Cochener","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathieu","family":"Lamard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"19286_CR1","unstructured":"GBD 2019 Blindness and Vision Impairment Collaborators & Vision Loss Expert Group of the Global Burden of Disease Study. Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the Right to Sight: an analysis for the Global Burden of Disease Study. Lancet Glob. Health 9, e144\u2013e160 (2021)."},{"key":"19286_CR2","doi-asserted-by":"publisher","first-page":"2129","DOI":"10.1016\/S0140-6736(22)00532-3","volume":"399","author":"A Haakenstad","year":"2022","unstructured":"Haakenstad, A. et al. Measuring the availability of human resources for health and its relationship to universal health coverage for 204 countries and territories from 1990 to 2019: A systematic analysis for the global burden of disease study 2019. The Lancet 399, 2129\u20132154 (2022).","journal-title":"The Lancet"},{"key":"19286_CR3","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1007\/s00417-023-06052-x","volume":"261","author":"M Daich Varela","year":"2023","unstructured":"Daich Varela, M. et al. Artificial intelligence in retinal disease: clinical application, challenges, and future directions. Graefes Arch. Clin. Exp. Ophthalmol. Albrecht Von Graefes Arch. Klin. Exp. Ophthalmol. 261, 3283\u20133297 (2023).","journal-title":"Klin. Exp. Ophthalmol."},{"key":"19286_CR4","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3390\/jimaging9040084","volume":"9","author":"S Muchuchuti","year":"2023","unstructured":"Muchuchuti, S. & Viriri, S. Retinal disease detection using deep learning techniques: a comprehensive review. J. Imag. 9, 84 (2023).","journal-title":"J. Imag."},{"key":"19286_CR5","doi-asserted-by":"publisher","first-page":"26802","DOI":"10.1038\/s41598-024-78515-y","volume":"14","author":"E S\u00fckei","year":"2024","unstructured":"S\u00fckei, E. et al. Multi-modal representation learning in retinal imaging using self-supervised learning for enhanced clinical predictions. Sci. Rep. 14, 26802 (2024).","journal-title":"Sci. Rep."},{"key":"19286_CR6","doi-asserted-by":"publisher","first-page":"11493","DOI":"10.1038\/s41598-023-38610-y","volume":"13","author":"S Matta","year":"2023","unstructured":"Matta, S. et al. Towards population-independent, multi-disease detection in fundus photographs. Sci. Rep. 13, 11493 (2023).","journal-title":"Sci. Rep."},{"key":"19286_CR7","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1186\/s40662-022-00285-3","volume":"9","author":"J Li","year":"2022","unstructured":"Li, J. et al. Automated detection of myopic maculopathy from color fundus photographs using deep convolutional neural networks. Eye Vis. 9, 13 (2022).","journal-title":"Eye Vis."},{"key":"19286_CR8","doi-asserted-by":"publisher","first-page":"10750","DOI":"10.1038\/s41598-019-47181-w","volume":"9","author":"J Sahlsten","year":"2019","unstructured":"Sahlsten, J. et al. Deep learning fundus image analysis for diabetic retinopathy and macular edema grading. Sci. Rep. 9, 10750 (2019).","journal-title":"Sci. Rep."},{"key":"19286_CR9","doi-asserted-by":"publisher","first-page":"16570","DOI":"10.1038\/s41598-021-95205-1","volume":"11","author":"N Rauf","year":"2021","unstructured":"Rauf, N., Gilani, S. O. & Waris, A. Automatic detection of pathological myopia using machine learning. Sci. Rep. 11, 16570 (2021).","journal-title":"Sci. Rep."},{"key":"19286_CR10","doi-asserted-by":"publisher","unstructured":"Zhang, P., Conze, P.-H., Lamard, M., Quellec, G. & Daho, M. E. H. Deep learning-based detection of referable diabetic retinopathy and macular edema using ultra-widefield fundus imaging. preprint at https:\/\/doi.org\/10.48550\/arXiv.2409.12854 (2024).","DOI":"10.48550\/arXiv.2409.12854"},{"key":"19286_CR11","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1001\/jamaophthalmol.2023.6318","volume":"142","author":"PS Silva","year":"2024","unstructured":"Silva, P. S. et al. Automated machine learning for predicting diabetic retinopathy progression from ultra-widefield retinal images. JAMA Ophthalmol. 142, 171 (2024).","journal-title":"JAMA Ophthalmol."},{"key":"19286_CR12","doi-asserted-by":"publisher","first-page":"742","DOI":"10.3390\/diagnostics12030742","volume":"12","author":"S-J Park","year":"2022","unstructured":"Park, S.-J., Ko, T., Park, C.-K., Kim, Y.-C. & Choi, I.-Y. Deep learning model based on 3d optical coherence tomography images for the automated detection of pathologic myopia. Diagnostics 12, 742 (2022).","journal-title":"Diagnostics"},{"key":"19286_CR13","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1001\/jamaophthalmol.2023.4659","volume":"141","author":"ER Dow","year":"2023","unstructured":"Dow, E. R. et al. A deep-learning algorithm to predict short-term progression to geographic atrophy on spectral-domain optical coherence tomography. JAMA Ophthalmol. 141, 1052 (2023).","journal-title":"JAMA Ophthalmol."},{"key":"19286_CR14","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","volume":"172","author":"DS Kermany","year":"2018","unstructured":"Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122-1131.e9 (2018).","journal-title":"Cell"},{"key":"19286_CR15","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","volume":"24","author":"J De Fauw","year":"2018","unstructured":"De Fauw, J. et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 24, 1342\u20131350 (2018).","journal-title":"Nat. Med."},{"key":"19286_CR16","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1186\/s40662-024-00396-z","volume":"11","author":"Y Wang","year":"2024","unstructured":"Wang, Y. et al. Automated early detection of acute retinal necrosis from ultra-widefield color fundus photography using deep learning. Eye Vis. 11, 27 (2024).","journal-title":"Eye Vis."},{"key":"19286_CR17","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1111\/j.1365-2818.2012.03619.x","volume":"247","author":"AG Podoleanu","year":"2012","unstructured":"Podoleanu, A. G. Optical coherence tomography. J. Microsc. 247, 209\u2013219 (2012).","journal-title":"J. Microsc."},{"key":"19286_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2019.103327","volume":"111","author":"J Qiu","year":"2019","unstructured":"Qiu, J. & Sun, Y. Self-supervised iterative refinement learning for macular OCT volumetric data classification. Comput. Biol. Med. 111, 103327 (2019).","journal-title":"Comput. Biol. Med."},{"key":"19286_CR19","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/RBME.2017.2651164","volume":"10","author":"G Quellec","year":"2017","unstructured":"Quellec, G., Cazuguel, G., Cochener, B. & Lamard, M. Multiple-instance learning for medical image and video analysis. IEEE Rev. Biomed. Eng. 10, 213\u2013234 (2017).","journal-title":"IEEE Rev. Biomed. Eng."},{"key":"19286_CR20","doi-asserted-by":"publisher","first-page":"8713","DOI":"10.1038\/s41598-023-35713-4","volume":"13","author":"P Matten","year":"2023","unstructured":"Matten, P. et al. Multiple instance learning based classification of diabetic retinopathy in weakly-labeled widefield OCTA en face images. Sci. Rep. 13, 8713 (2023).","journal-title":"Sci. Rep."},{"key":"19286_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103259","volume":"97","author":"C de Vente","year":"2024","unstructured":"de Vente, C., van Ginneken, B., Hoyng, C. B., Klaver, C. C. W. & S\u00e1nchez, C. I. Uncertainty-aware multiple-instance learning for reliable classification: Application to optical coherence tomography. Med. Image Anal. 97, 103259 (2024).","journal-title":"Med. Image Anal."},{"key":"19286_CR22","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/JBHI.2018.2795545","volume":"23","author":"Y Rong","year":"2019","unstructured":"Rong, Y. et al. Surrogate-assisted retinal OCT Image classification based on convolutional neural networks. IEEE J. Biomed. Health Inform. 23, 253\u2013263 (2019).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"19286_CR23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0219126","volume":"14","author":"S Maetschke","year":"2019","unstructured":"Maetschke, S. et al. A feature agnostic approach for glaucoma detection in OCT volumes. PLoS ONE 14, e0219126 (2019).","journal-title":"PLoS ONE"},{"key":"19286_CR24","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1167\/tvst.11.5.11","volume":"11","author":"E Noury","year":"2022","unstructured":"Noury, E. et al. Deep learning for glaucoma detection and identification of novel diagnostic areas in diverse real-world datasets. Transl. Vis. Sci. Technol. 11, 11 (2022).","journal-title":"Transl. Vis. Sci. Technol."},{"key":"19286_CR25","doi-asserted-by":"publisher","first-page":"11758","DOI":"10.1038\/s41598-024-62411-6","volume":"14","author":"RK Rasel","year":"2024","unstructured":"Rasel, R. K. et al. Assessing the efficacy of 2D and 3D CNN algorithms in OCT-based glaucoma detection. Sci. Rep. 14, 11758 (2024).","journal-title":"Sci. Rep."},{"key":"19286_CR26","doi-asserted-by":"crossref","unstructured":"Oghbaie, M., Araujo, T., Emre, T., Schmidt-Erfurth, U. & Bogunovic, H. Transformer-based end-to-end classification of variable-length volumetric data. preprint at http:\/\/arxiv.org\/abs\/2307.06666 (2023).","DOI":"10.1007\/978-3-031-43987-2_35"},{"key":"19286_CR27","unstructured":"Dosovitskiy, A. et al. An Image is Worth 16x16 Words: Transformers for Image recognition at scale. Preprint at http:\/\/arxiv.org\/abs\/2010.11929 (2021)."},{"key":"19286_CR28","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","volume":"622","author":"Y Zhou","year":"2023","unstructured":"Zhou, Y. et al. A foundation model for generalizable disease detection from retinal images. Nature 622, 156\u2013163 (2023).","journal-title":"Nature"},{"key":"19286_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106512","volume":"154","author":"M Moradi","year":"2023","unstructured":"Moradi, M., Chen, Y., Du, X. & Seddon, J. M. Deep ensemble learning for automated non-advanced AMD classification using optimized retinal layer segmentation and SD-OCT scans. Comput. Biol. Med. 154, 106512 (2023).","journal-title":"Comput. Biol. Med."},{"key":"19286_CR30","first-page":"1","volume-title":"UD-MIL: Uncertainty-driven deep multiple instance learning for OCT Image classification","author":"X Wang","year":"2020","unstructured":"Wang, X. et al. UD-MIL: Uncertainty-driven deep multiple instance learning for OCT Image classification 1 (IEEE J. Biomed, 2020)."},{"key":"19286_CR31","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1038\/s41597-024-03182-7","volume":"11","author":"M Kulyabin","year":"2024","unstructured":"Kulyabin, M. et al. OCTDL: Optical coherence tomography dataset for image-based deep learning methods. Sci. Data 11, 365 (2024).","journal-title":"Sci. Data"},{"key":"19286_CR32","doi-asserted-by":"publisher","first-page":"1024","DOI":"10.1109\/TMI.2017.2780115","volume":"37","author":"R Rasti","year":"2018","unstructured":"Rasti, R., Rabbani, H., Mehridehnavi, A. & Hajizadeh, F. Macular OCT classification using a Multi-scale convolutional neural network ensemble. IEEE Trans. Med. Imag. 37, 1024\u20131034 (2018).","journal-title":"IEEE Trans. Med. Imag."},{"key":"19286_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, P. et al. Patch progression masked autoencoder with fusion CNN network for classifying evolution between two pairs of 2D OCT slices. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.20064 (2025).","DOI":"10.48550\/arXiv.2508.20064"},{"key":"19286_CR34","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.15270469","author":"G Quellec","year":"2025","unstructured":"Quellec, G. & Zeghlache, R. MARIO: Monitoring age-related macular degeneration progression in optical coherence tomography. Zenodo https:\/\/doi.org\/10.5281\/zenodo.15270469 (2025)."},{"key":"19286_CR35","doi-asserted-by":"publisher","unstructured":"Chen, S., Ma, K. & Zheng, Y. Med3D: Transfer learning for 3D medical image analysis. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1904.00625 (2019).","DOI":"10.48550\/arXiv.1904.00625"},{"key":"19286_CR36","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In proc. IEEE conference on computer vision and pattern recognition 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"19286_CR37","doi-asserted-by":"publisher","unstructured":"Beyer, L. et al. FlexiViT: One Model for all patch sizes. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2212.08013 (2023).","DOI":"10.48550\/arXiv.2212.08013"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19286-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19286-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19286-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T02:02:18Z","timestamp":1760407338000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-19286-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["19286"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-19286-y","relation":{"references":[{"id-type":"doi","id":"10.5281\/zenodo.15270469","asserted-by":"subject"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"27 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"The author Philippe Zhang declares no Competing Non-Financial Interests but the following Competing Financial Interests: Employee \u2013 Evolucare Technologies. The authors Sarah Matta, Tanguy Thiery and Mathieu Lamard declare no Competing Financial or Non-Financial Interests. The author Laurent Borderie declares no Competing Non-Financial Interests but the following Competing Financial Interests: Employee \u2013 Evolucare Technologies. The author Alexandre Le Guilcher declares no Competing Non-Financial Interests but the following Competing Financial Interests: Research & Innovation director \u2013 Evolucare Technologies; CEO \u2013 OphtAI. The author Gwenol\u00e9 Quellec declares no Competing Non-Financial Interests but the following Competing Financial Interests: Consultant \u2013 Evolucare Technologies, Adcis. The author B\u00e9atrice Cochener declares no Competing Non-Financial Interests but the following Competing Financial Interests: Consultant and clinical investigator \u2013 Thea, Alcon, Zeiss, B&L, Hoya, Horus, Santen, SIFI, Cutting Edge, J&J. All the remaining authors declare no conflict of interest. All the remaining authors declare no conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"35334"}}