{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T18:45:37Z","timestamp":1781376337877,"version":"3.54.1"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T00:00:00Z","timestamp":1741046400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Biomedical Research Institute"},{"DOI":"10.13039\/501100004600","name":"Kyungpook National University Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004600","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2018R1A5A1060031"],"award-info":[{"award-number":["NRF-2018R1A5A1060031"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","award":["NRF-2021R1A2C2013939"],"award-info":[{"award-number":["NRF-2021R1A2C2013939"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>This study aimed to develop a novel multi-stage self-supervised learning model tailored for the accurate classification of optical coherence tomography (OCT) images in ophthalmology reducing reliance on costly labeled datasets while maintaining high diagnostic accuracy.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>A private dataset of 2719 OCT images from 493 patients was employed, along with 3 public datasets comprising 84\u00a0484 images from 4686 patients, 3231 images from 45 patients, and 572 images. Extensive internal, external, and clinical validation were performed to assess model performance. Grad-CAM was employed for qualitative analysis to interpret the model\u2019s decisions by highlighting relevant areas. Subsampling analyses evaluated the model\u2019s robustness with varying labeled data availability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The proposed model outperformed conventional supervised or self-supervised learning-based models, achieving state-of-the-art results across 3 public datasets. In a clinical validation, the model exhibited up to 17.50% higher accuracy and 17.53% higher macro F-1 score than a supervised learning-based model under limited training data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>The model\u2019s robustness in OCT image classification underscores the potential of the multi-stage self-supervised learning to address challenges associated with limited labeled data. The availability of source codes and pre-trained models promotes the use of this model in a variety of clinical settings, facilitating broader adoption.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>This model offers a promising solution for advancing OCT image classification, achieving high accuracy while reducing the cost of extensive expert annotation and potentially streamlining clinical workflows, thereby supporting more efficient patient management.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf021","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T02:07:45Z","timestamp":1741140465000},"page":"800-810","source":"Crossref","is-referenced-by-count":5,"title":["Development and validation of a multi-stage self-supervised learning model for optical coherence tomography image classification"],"prefix":"10.1093","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2235-6142","authenticated-orcid":false,"given":"Sungho","family":"Shim","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST) , Daegu 42988,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"School of Computing, Korea Advanced Institute of Science and Technology (KAIST) , Daejeon 34141,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Che Gyem","family":"Yae","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kyungpook National University , Daegu 41944,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Koo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kyungpook National University , Daegu 41944,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Rock","family":"Do","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kyungpook National University , Daegu 41944,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong Kyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kyungpook National University , Daegu 41944,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2221-3042","authenticated-orcid":false,"given":"Hyun-Lim","family":"Yang","sequence":"additional","affiliation":[{"name":"Office of Hospital Information, Seoul National University Hospital , Seoul 03080,","place":["Republic of Korea"]},{"name":"Innovative Medical Technology Research Institute, Seoul National University Hospital , Seoul 03080,","place":["Republic of Korea"]},{"name":"Department of Medicine, College of Medicine, Seoul National University , Seoul 03080,","place":["Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"2025042203524039200_ocaf021-B1","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1126\/science.1957169","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"Science."},{"key":"2025042203524039200_ocaf021-B2","doi-asserted-by":"crossref","first-page":"1835","DOI":"10.1016\/S0140-6736(08)61759-6","article-title":"Age-related macular degeneration","volume":"372","author":"Coleman","year":"2008","journal-title":"Lancet."},{"key":"2025042203524039200_ocaf021-B3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40662-015-0026-2","article-title":"Epidemiology of diabetic retinopathy, diabetic macular edema and related vision loss","volume":"2","author":"Lee","year":"2015","journal-title":"Eye Vis."},{"key":"2025042203524039200_ocaf021-B4","first-page":"844","article-title":"Global data on visual impairment in the year 2002","volume":"82","author":"Resnikoff","year":"2004","journal-title":"Bull World Health Organ."},{"key":"2025042203524039200_ocaf021-B5","doi-asserted-by":"crossref","first-page":"020703","DOI":"10.7189\/jogh.07.020703","article-title":"The national and subnational prevalence and burden of age\u2013related macular degeneration in China","volume":"7","author":"Song","year":"2017","journal-title":"J Glob Health"},{"key":"2025042203524039200_ocaf021-B6","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1016\/j.ophtha.2017.05.035","article-title":"Prevalence of age-related macular degeneration in Europe: the past and the future","volume":"124","author":"Colijn","year":"2017","journal-title":"Ophthalmology"},{"key":"2025042203524039200_ocaf021-B7","doi-asserted-by":"crossref","first-page":"2087","DOI":"10.1007\/s00247-021-05114-8","article-title":"How does artificial intelligence in radiology improve efficiency and health outcomes?","volume":"52","author":"Van Leeuwen","year":"2022","journal-title":"Pediatr Radiol."},{"key":"2025042203524039200_ocaf021-B8","doi-asserted-by":"crossref","first-page":"e468","DOI":"10.1016\/S2589-7500(20)30185-0","article-title":"Effect of artificial intelligence-based triaging of breast cancer screening mammograms on cancer detection and radiologist workload: a retrospective simulation study","volume":"2","author":"Dembrower","year":"2020","journal-title":"Lancet Digit Health."},{"key":"2025042203524039200_ocaf021-B9","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1007\/s00330-020-07165-1","article-title":"Identifying normal mammograms in a large screening population using artificial intelligence","volume":"31","author":"L\u00e5ng","year":"2021","journal-title":"Eur Radiol."},{"key":"2025042203524039200_ocaf021-B10","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025042203524039200_ocaf021-B11","first-page":"818","author":"Zeiler","year":"2014"},{"key":"2025042203524039200_ocaf021-B12","author":"Simonyan","year":"2014"},{"key":"2025042203524039200_ocaf021-B13","first-page":"1","author":"Szegedy","year":"2015"},{"key":"2025042203524039200_ocaf021-B14","first-page":"770","author":"He","year":"2016"},{"key":"2025042203524039200_ocaf021-B15","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.oret.2016.12.009","article-title":"Deep learning is effective for classifying normal versus age-related macular degeneration OCT images","volume":"1","author":"Lee","year":"2017","journal-title":"Ophthalmol Retina"},{"key":"2025042203524039200_ocaf021-B16","doi-asserted-by":"crossref","first-page":"6204","DOI":"10.1364\/BOE.10.006204","article-title":"Deep learning-based automated detection of retinal diseases using optical coherence tomography images","volume":"10","author":"Li","year":"2019","journal-title":"Biomed Opt Express."},{"key":"2025042203524039200_ocaf021-B17","first-page":"964","author":"Kamran","year":"2019"},{"key":"2025042203524039200_ocaf021-B18","first-page":"69","author":"Noroozi","year":"2016"},{"key":"2025042203524039200_ocaf021-B19","author":"Gidaris","year":"2018"},{"key":"2025042203524039200_ocaf021-B20","first-page":"9729","author":"He","year":"2020"},{"key":"2025042203524039200_ocaf021-B21","first-page":"1597","author":"Chen","year":"2020"},{"key":"2025042203524039200_ocaf021-B22","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025042203524039200_ocaf021-B23","doi-asserted-by":"crossref","first-page":"100400","DOI":"10.1016\/j.patter.2021.100400","article-title":"Contrastive learning of heart and lung sounds for label-efficient diagnosis","volume":"3","author":"Soni","year":"2022","journal-title":"Patterns"},{"key":"2025042203524039200_ocaf021-B24","first-page":"2","author":"Zhang","year":"2022"},{"key":"2025042203524039200_ocaf021-B25","first-page":"247","article-title":"Pneumonia detection on chest x-ray using radiomic features and contrastive learning","volume":"2021","author":"Han","year":"2021","journal-title":"Proc IEEE Int Symp Biomed Imaging."},{"key":"2025042203524039200_ocaf021-B26","first-page":"3478","author":"Azizi","year":"2021"},{"key":"2025042203524039200_ocaf021-B27","doi-asserted-by":"crossref","first-page":"2851","DOI":"10.1007\/s11517-022-02627-8","article-title":"Self-supervised patient-specific features learning for OCT image classification","volume":"60","author":"Fang","year":"2022","journal-title":"Med Biol Eng Comput."},{"key":"2025042203524039200_ocaf021-B28","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.2196\/jmir.5870","article-title":"Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view","volume":"18","author":"Luo","year":"2016","journal-title":"J Med Internet Res."},{"key":"2025042203524039200_ocaf021-B29","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","year":"2018","journal-title":"Cell"},{"key":"2025042203524039200_ocaf021-B30","doi-asserted-by":"crossref","first-page":"3568","DOI":"10.1364\/BOE.5.003568","article-title":"Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images","volume":"5","author":"Srinivasan","year":"2014","journal-title":"Biomed Opt Express."},{"key":"2025042203524039200_ocaf021-B31","doi-asserted-by":"crossref","first-page":"106532","DOI":"10.1016\/j.compeleceng.2019.106532","article-title":"OCTID: optical coherence tomography image database","volume":"81","author":"Gholami","year":"2020","journal-title":"Comput Electr Eng"},{"key":"2025042203524039200_ocaf021-B32","first-page":"41","author":"Shim","year":"2024"},{"key":"2025042203524039200_ocaf021-B33","doi-asserted-by":"crossref","first-page":"1895","DOI":"10.1162\/089976698300017197","article-title":"Approximate statistical tests for comparing supervised classification learning algorithms","volume":"10","author":"Dietterich","year":"1998","journal-title":"Neural Comput."},{"key":"2025042203524039200_ocaf021-B34","first-page":"618","author":"Selvaraju","year":"2017"},{"key":"2025042203524039200_ocaf021-B35","doi-asserted-by":"crossref","first-page":"18272","DOI":"10.1038\/s41598-020-75506-7","article-title":"Quantitative analysis of choroidal vasculature in polypoidal choroidal vasculopathy using ultra-widefield indocyanine green angiography","volume":"10","author":"Ryu","year":"2020","journal-title":"Sci Rep"},{"key":"2025042203524039200_ocaf021-B36","doi-asserted-by":"crossref","first-page":"951","DOI":"10.1007\/s00592-024-02306-0","article-title":"Association between choroidal thickness and diabetic macular edema: a meta-analysis","volume":"61","author":"Li","year":"2024","journal-title":"Acta Diabetol"},{"key":"2025042203524039200_ocaf021-B37","doi-asserted-by":"crossref","first-page":"e0215076","DOI":"10.1371\/journal.pone.0215076","article-title":"Weakly supervised lesion localization for age-related macular degeneration detection using optical coherence tomography images","volume":"14","author":"Yang","year":"2019","journal-title":"PLoS One."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/5\/800\/62266403\/ocaf021.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/5\/800\/62266403\/ocaf021.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T07:52:59Z","timestamp":1745308379000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/5\/800\/8051867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,4]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,3,4]]},"published-print":{"date-parts":[[2025,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf021","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,5]]},"published":{"date-parts":[[2025,3,4]]}}}