{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:38:56Z","timestamp":1786556336891,"version":"build-2736575974"},"reference-count":27,"publisher":"BMJ","license":[{"start":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:00:00Z","timestamp":1781222400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20242093"],"award-info":[{"award-number":["GZC20242093"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC","doi-asserted-by":"crossref","award":["82371111"],"award-info":[{"award-number":["82371111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC","doi-asserted-by":"crossref","award":["82441003"],"award-info":[{"award-number":["82441003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China (NSFC","doi-asserted-by":"crossref","award":["92368205"],"award-info":[{"award-number":["92368205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515012292"],"award-info":[{"award-number":["2024A1515012292"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Planning Project of Guangzhou City","award":["2025A03J3989"],"award-info":[{"award-number":["2025A03J3989"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Br J Ophthalmol"],"accepted":{"date-parts":[[2026,5,27]]},"abstract":"<jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>To develop and validate DeepAdapter, a novel deep learning algorithm that integrates self-supervised learning (SSL) and unsupervised domain adaptation (UDA) to enhance model generalisability for retinopathy of prematurity (ROP) screening.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>DeepAdapter was developed in two stages. First, SSL was applied to 500\u2009000 unlabelled infantile colour fundus photographs (CFPs) retrospectively collected from four Chinese clinical centres to learn general fundus representations. Second, a much smaller labelled dataset of Normal and ROP CFPs was constructed, and a UDA module was incorporated to mitigate domain shift, defined as distribution differences between training and deployment datasets that may impair model performance. Correlation Alignment (CORAL) distance was employed to quantify these domain shifts. External validation was performed using data from an independent clinical centre and two public multiethnic datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      A total of 500\u2009000 non-overlapping unlabelled CFPs and 39\u2009456 labelled CFPs were included. Compared with the supervised method, DeepAdapter decreased CORAL distance from 0.297 to 3.550\u00d710\n                      <jats:sup>\u22126<\/jats:sup>\n                      . Both algorithms achieved high internal accuracy (0.989) in ROP prediction, but DeepAdapter significantly outperformed the supervised method on external testing (accuracy: 0.828 (95% CI 0.823 to 0.833)\u2009vs 0.739 (95% CI 0.733 to 0.745), p\u2009&lt;0.001) and on the public cross-ethnicity dataset (accuracy: 0.839 (95% CI 0.818 to 0.859)\u2009vs 0.813 (95% CI 0.791 to 0.835), p=0.014). A web-based system integrating quality control and ROP diagnosis was developed for large-scale, multicentre clinical screening.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>DeepAdapter effectively mitigated domain shift and significantly improved model generalisability for ROP screening, providing a valuable reference for developing generalisable models in other medical specialties.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bjo-2025-328559","type":"journal-article","created":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T17:20:14Z","timestamp":1781284814000},"page":"bjo-2025-328559","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["DeepAdapter: a generalisable algorithm integrating self-supervised learning and unsupervised domain adaptation for robust retinopathy of prematurity screening"],"prefix":"10.1136","author":[{"given":"Jiaman","family":"Zhao","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"},{"name":"School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7533-5642","authenticated-orcid":false,"given":"Longhui","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenzhe","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingjie","family":"Luo","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyuan","family":"Yun","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"},{"name":"School of Biomedical Engineering, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Wen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixue","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiao","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Qilu Hospital, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Qilu Hospital, Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suzhen","family":"Xie","sequence":"additional","affiliation":[{"name":"Guangdong Women and Children Hospital, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meirong","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Maternal and Children\u2019s Hospital, Liuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baohai","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Maternal and Children\u2019s Hospital, Linyi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4853-2474","authenticated-orcid":false,"given":"Zhenzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duoru","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4672-9721","authenticated-orcid":false,"given":"Haotian","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Zhongshan Ophthalmic Center, State Key Laboratory of Ophthalmology, Guangzhou, Guangdong, China"},{"name":"Hainan Eye Hospital and Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Haikou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,12]]},"reference":[{"key":"2026081210201207000_bjo-2025-328559v2.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaapos.2012.09.004"},{"key":"2026081210201207000_bjo-2025-328559v2.2","doi-asserted-by":"crossref","first-page":"e489","DOI":"10.1016\/S2214-109X(20)30488-5","article-title":"The Lancet Global Health Commission on Global Eye Health: vision beyond 2020","volume":"9","author":"Burton","year":"2021","journal-title":"Lancet Glob Health"},{"key":"2026081210201207000_bjo-2025-328559v2.3","doi-asserted-by":"crossref","first-page":"102840","DOI":"10.1016\/j.eclinm.2024.102840","article-title":"Global, regional, and national burden of preterm birth, 1990\u20132021: a systematic analysis from the global burden of disease study 2021","volume":"76","author":"Liang","year":"2024","journal-title":"eClinicalMedicine"},{"key":"2026081210201207000_bjo-2025-328559v2.4","doi-asserted-by":"crossref","first-page":"102967","DOI":"10.1016\/j.arcmed.2024.102967","article-title":"Global Prevalence and Severity of Retinopathy of Prematurity over the Last Four Decades (1985-2021): A Systematic Review and Meta-Analysis","volume":"55","author":"Garc\u00eda","year":"2024","journal-title":"Arch Med Res"},{"key":"2026081210201207000_bjo-2025-328559v2.5","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2019-314336"},{"key":"2026081210201207000_bjo-2025-328559v2.6","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.ebiom.2018.08.033","article-title":"Automated retinopathy of prematurity screening using deep neural networks","volume":"35","author":"Wang","year":"2018","journal-title":"EBioMedicine"},{"key":"2026081210201207000_bjo-2025-328559v2.7","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1001\/jamaophthalmol.2018.1934","article-title":"Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep Convolutional Neural Networks","volume":"136","author":"Brown","year":"2018","journal-title":"JAMA Ophthalmol"},{"key":"2026081210201207000_bjo-2025-328559v2.8","doi-asserted-by":"crossref","first-page":"3131","DOI":"10.1007\/s10278-024-01154-2","article-title":"RDLR: A Robust Deep Learning-Based Image Registration Method for Pediatric Retinal Images","volume":"37","author":"Zhou","year":"2024","journal-title":"J Digit Imaging Inform med"},{"key":"2026081210201207000_bjo-2025-328559v2.9","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxz041"},{"key":"2026081210201207000_bjo-2025-328559v2.10","doi-asserted-by":"crossref","first-page":"e340","DOI":"10.1016\/S2589-7500(23)00050-X","article-title":"Development and international validation of custom-engineered and code-free deep-learning models for detection of plus disease in retinopathy of prematurity: a retrospective study","volume":"5","author":"Wagner","year":"2023","journal-title":"Lancet Digit Health"},{"key":"2026081210201207000_bjo-2025-328559v2.11","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1097\/ICU.0000000000000680","article-title":"Artificial intelligence for retinopathy of prematurity","volume":"31","author":"Gensure","year":"2020","journal-title":"Curr Opin Ophthalmol"},{"key":"2026081210201207000_bjo-2025-328559v2.12","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1016\/j.oret.2019.01.015","article-title":"Automated Fundus Image Quality Assessment in Retinopathy of Prematurity Using Deep Convolutional Neural Networks","volume":"3","author":"Coyner","year":"2019","journal-title":"Ophthalmol Retina"},{"key":"2026081210201207000_bjo-2025-328559v2.13","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature New Biol"},{"key":"2026081210201207000_bjo-2025-328559v2.14","doi-asserted-by":"crossref","unstructured":"Ben-David S , Blitzer J , Crammer K , et al . Analysis of representations for domain adaptation. In: Sch\u00f6lkopf B , Platt J , Hofmann T , eds. Advances in Neural Information Processing Systems 19. The MIT Press, 2007: 137\u201344.","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"2026081210201207000_bjo-2025-328559v2.15","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.oret.2021.06.010","article-title":"Self-Supervised Feature Learning and Phenotyping for Assessing Age-Related Macular Degeneration Using Retinal Fundus Images","volume":"6","author":"Yellapragada","year":"2022","journal-title":"Ophthalmol Retina"},{"key":"2026081210201207000_bjo-2025-328559v2.16","doi-asserted-by":"crossref","first-page":"976467","DOI":"10.3389\/fmed.2022.976467","article-title":"Self-supervised learning mechanism for identification of eyelid malignant melanoma in pathologic slides with limited annotation","volume":"9","author":"Wang","year":"2022","journal-title":"Front Med"},{"key":"2026081210201207000_bjo-2025-328559v2.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02702-z"},{"key":"2026081210201207000_bjo-2025-328559v2.18","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-023-00943-3","article-title":"DeepQuality improves infant retinopathy screening","volume":"6","author":"Li","year":"2023","journal-title":"NPJ Digit Med"},{"key":"2026081210201207000_bjo-2025-328559v2.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2021.05.031"},{"key":"2026081210201207000_bjo-2025-328559v2.20","unstructured":"Chen X , Fan H , Girshick RB , et al . Improved Baselines with Momentum Contrastive Learning. ArXiv 2020."},{"key":"2026081210201207000_bjo-2025-328559v2.21","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1109\/TNNLS.2020.2988928","article-title":"Deep Subdomain Adaptation Network for Image Classification","volume":"32","author":"Zhu","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2026081210201207000_bjo-2025-328559v2.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"2026081210201207000_bjo-2025-328559v2.23","doi-asserted-by":"crossref","unstructured":"Sun B , Feng J , Saenko K . Return of frustratingly easy domain adaptation. Phoenix, Arizona: AAAI Press; 2016:2058\u201365. doi:10.1609\/aaai.v30i1.10306","DOI":"10.1609\/aaai.v30i1.10306"},{"key":"2026081210201207000_bjo-2025-328559v2.24","doi-asserted-by":"crossref","DOI":"10.1038\/s41597-024-03409-7","article-title":"Retinal Image Dataset of Infants and Retinopathy of Prematurity","volume":"11","author":"Timkovi\u010d","year":"2024","journal-title":"Sci Data"},{"key":"2026081210201207000_bjo-2025-328559v2.25","doi-asserted-by":"crossref","DOI":"10.1016\/j.dib.2023.109839","article-title":"HVDROPDB datasets for research in retinopathy of prematurity","volume":"52","author":"Agrawal","year":"2024","journal-title":"Data Brief"},{"key":"2026081210201207000_bjo-2025-328559v2.26","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.8.6.23","article-title":"Deep Learning Algorithm for Automated Diagnosis of Retinopathy of Prematurity Plus Disease","volume":"8","author":"Tan","year":"2019","journal-title":"Transl Vis Sci Technol"},{"key":"2026081210201207000_bjo-2025-328559v2.27","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.12.8.13","article-title":"Multicenter Validation of Deep Learning Algorithm ROP.AI for the Automated Diagnosis of Plus Disease in ROP","volume":"12","author":"Bai","year":"2023","journal-title":"Transl Vis Sci Technol"}],"container-title":["British Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bjo-2025-328559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T17:20:25Z","timestamp":1786555225000},"score":1,"resource":{"primary":{"URL":"https:\/\/bjo.bmj.com\/lookup\/doi\/10.1136\/bjo-2025-328559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,12]]},"references-count":27,"alternative-id":["10.1136\/bjo-2025-328559"],"URL":"https:\/\/doi.org\/10.1136\/bjo-2025-328559","relation":{},"ISSN":["0007-1161","1468-2079"],"issn-type":[{"value":"0007-1161","type":"print"},{"value":"1468-2079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,12]]}}}