{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T01:48:26Z","timestamp":1794707306637,"version":"4.9.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,3]],"date-time":"2026-01-03T00:00:00Z","timestamp":1767398400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":31,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Ophthalmol"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Retinal detachment (RD) requires prompt detection to prevent vision loss. Ultra-widefield (UWF) imaging captures the peripheral retina, and deep learning (DL) may enable automated RD detection. We aimed to systematically review and meta-analyze the diagnostic accuracy of DL applied to UWF images for detecting RD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We systematically searched PubMed, Web of Science, and reference lists (last search 22 May 2025) for diagnostic-accuracy studies evaluating DL models for retinal detachment on UWF images with extractable 2\u2009\u00d7\u20092 data. Two reviewers independently selected studies, extracted data, and assessed risk of bias and concerns regarding applicability using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). Sensitivity, specificity, and area under the curve (AUC) were pooled using random-effects models, with subgroup analyses by dataset origin (internal vs. external) and retinal detachment spectrum.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We included 11 studies (2017\u20132024) using UWF imaging and DL, with test set sizes ranging from 89 to 6,222 images. The pooled sensitivity and specificity were 0.95 (95% CI, 0.94\u20130.96) and 0.99 (95% CI, 0.99\u20130.99); the AUC of the summary receiver operating characteristic (SROC)\u2009=\u20090.9962. Heterogeneity was high (I\u00b2 = 92% for sensitivity; 90% for specificity). In subgroup analyses, external evaluations showed higher sensitivity than internal ones (0.97 vs. 0.92), with similarly high specificity (both \u2248\u20090.99). Heterogeneity remained substantial within subgroups. QUADAS-2 indicated a low risk of bias in most domains, with unclear index test risk common due to non-prespecified thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>DL applied to UWF imaging shows high diagnostic accuracy for RD, with pooled sensitivity and specificity of 0.95 and 0.99, respectively, and an AUC of 0.9962. However, the evidence is limited by substantial heterogeneity, inconsistent index-test reporting, and variation in case spectrum and sample size, which may constrain generalizability. Overall, these findings suggest that DL combined with UWF imaging is likely to serve as a valuable adjunctive tool for RD detection and triage, particularly in settings where rapid, wide-field assessment is needed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Registration<\/jats:title>\n                    <jats:p>UMIN-CTR UMIN000057903; PROSPERO CRD420251058209.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12886-025-04605-8","type":"journal-article","created":{"date-parts":[[2026,1,4]],"date-time":"2026-01-04T02:18:17Z","timestamp":1767493097000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic accuracy of deep learning using ultra-widefield fundus imaging for retinal detachment: a systematic review and meta-analysis"],"prefix":"10.1186","volume":"26","author":[{"given":"Chiaki","family":"Kawamoto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3722-0659","authenticated-orcid":false,"given":"Yuki","family":"Mizuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobuyuki","family":"Horita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuichi","family":"Kuramochi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shun","family":"Kanasashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatsukata","family":"Kawagoe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobuhisa","family":"Mizuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,3]]},"reference":[{"key":"4605_CR1","doi-asserted-by":"publisher","unstructured":"Shah V, Hall N, Goldacre M. Retinal detachment in England: database studies of trends over time and geographical variation. Br J Ophthalmol. 2015-05-01 2015;99(5):639\u201343. https:\/\/doi.org\/10.1136\/bjophthalmol-2014-305774.","DOI":"10.1136\/bjophthalmol-2014-305774"},{"issue":"7655","key":"4605_CR2","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1136\/bmj.39581.525532.47","volume":"31","author":"HK Kang","year":"2008","unstructured":"Kang HK, Luff AJ. Management of retinal detachment: a guide for non-ophthalmologists. BMJ May. 2008;31(7655):1235\u201340. https:\/\/doi.org\/10.1136\/bmj.39581.525532.47.","journal-title":"BMJ May"},{"key":"4605_CR3","doi-asserted-by":"publisher","unstructured":"Iida M, Horiguchi H, Katagiri S, et al. Association of meteorological factors with the frequency of primary rhegmatogenous retinal detachment in Japan. Scientific Reports. 2021-05-05 2021;11(1)9559. https:\/\/doi.org\/10.1038\/s41598-021-88979-x.","DOI":"10.1038\/s41598-021-88979-x"},{"key":"4605_CR4","doi-asserted-by":"publisher","DOI":"10.1055\/a-2116-9565","author":"VMM Radeck","year":"2023","unstructured":"Radeck VMM, Helbig H, Barth T, Gamulescu A, Maerker D, Wolf A. Are retinal detachments becoming more frequent? Data from 2 university eye clinics and literature review. Klin Monbl Augenheilkd Sep. 2023;240(9):1046\u201351. https:\/\/doi.org\/10.1055\/a-2116-9565."},{"key":"4605_CR5","doi-asserted-by":"publisher","unstructured":"Lorenzo-Carrero J, Perez-Flores I, Cid-Galano M, et al. B-Scan ultrasonography to screen for retinal tears in acute symptomatic age-related posterior vitreous Detachment. Ophthalmology. 2009-01-01 2009;116(1):94\u20139. https:\/\/doi.org\/10.1016\/j.ophtha.2008.08.040.","DOI":"10.1016\/j.ophtha.2008.08.040"},{"issue":"5","key":"4605_CR6","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1097\/IAE.0000000000004040","volume":"01","author":"J Meng","year":"2024","unstructured":"Meng J, Cheng K, Huang Z, et al. Combined application of b-scan ultrasonography and eye-steering ultrawide field imaging to improve the detection of retinal tears before cataract surgery. Retina May. 2024;01(5):810\u20139. https:\/\/doi.org\/10.1097\/IAE.0000000000004040.","journal-title":"Retina May"},{"issue":"7","key":"4605_CR7","doi-asserted-by":"publisher","first-page":"575","DOI":"10.4103\/0301-4738.167122","volume":"63","author":"SS Shoughy","year":"2015","unstructured":"Shoughy SS, Arevalo JF, Kozak I. Update on wide- and ultra-widefield retinal imaging. Indian J Ophthalmol Jul. 2015;63(7):575\u201381. https:\/\/doi.org\/10.4103\/0301-4738.167122.","journal-title":"Indian J Ophthalmol Jul"},{"key":"4605_CR8","doi-asserted-by":"publisher","unstructured":"Peng J, Zhang Q, Jin H, Lu W, Zhao P. Ultra-wide field imaging system and traditional retinal examinations for screening fundus changes after cataract surgery. Int J Ophthalmol. 2016-09-18 2016;9(9):1299\u2013303. https:\/\/doi.org\/10.18240\/ijo.2016.09.11.","DOI":"10.18240\/ijo.2016.09.11"},{"key":"4605_CR9","doi-asserted-by":"publisher","unstructured":"Pandey P, Ballios B, Christakis P, et al. An ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs. Br J Ophthalmol. 2023-01-31 2024;108(3):417\u201323. https:\/\/doi.org\/10.1136\/bjo-2022-322183.","DOI":"10.1136\/bjo-2022-322183"},{"key":"4605_CR10","doi-asserted-by":"publisher","unstructured":"Bhambra N, Antaki F, El Malt F, Xu A, Duval R. Deep learning for ultra-widefield imaging: a scoping review. Graefes archive for clinical and experimental Ophthalmology. 2022-07-20 2022;260(12):3737\u201378. https:\/\/doi.org\/10.1007\/s00417-022-05741-3.","DOI":"10.1007\/s00417-022-05741-3"},{"key":"4605_CR11","doi-asserted-by":"crossref","unstructured":"Liu X, Faes L, Kale A, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2019-10-01 2019;1(6):E271\u201397.","DOI":"10.1016\/S2589-7500(19)30123-2"},{"issue":"2","key":"4605_CR12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","volume":"103","author":"D Ting","year":"2019","unstructured":"Ting D, Pasquale L, Peng L, et al. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol. 2019;103(2):167\u201375. https:\/\/doi.org\/10.1136\/bjophthalmol-2018-313173. -02-01 2019.","journal-title":"Br J Ophthalmol"},{"issue":"1","key":"4605_CR13","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1136\/bjophthalmol-2021-319030","volume":"107","author":"F Antaki","year":"2023","unstructured":"Antaki F, Coussa RG, Kahwati G, Hammamji K, Sebag M, Duval R. Accuracy of automated machine learning in classifying retinal pathologies from ultra-widefield pseudocolour fundus images. Br J Ophthalmol Jan. 2023;107(1):90\u20135. https:\/\/doi.org\/10.1136\/bjophthalmol-2021-319030.","journal-title":"Br J Ophthalmol Jan"},{"issue":"2","key":"4605_CR14","doi-asserted-by":"publisher","first-page":"1081","DOI":"10.1007\/s40123-023-00651-x","volume":"12","author":"T Wang","year":"2023","unstructured":"Wang T, Liao G, Chen L, et al. Intelligent diagnosis of multiple peripheral retinal lesions in Ultra-widefield fundus images based on deep learning. Ophthalmol Ther Apr. 2023;12(2):1081\u201395. https:\/\/doi.org\/10.1007\/s40123-023-00651-x.","journal-title":"Ophthalmol Ther Apr"},{"issue":"4","key":"4605_CR15","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1001\/jama.2017.19163","volume":"319","author":"MDF McInnes","year":"2018","unstructured":"McInnes MDF, Moher D, Thombs BD, et al. Preferred reporting items for a systematic review and Meta-analysis of diagnostic test accuracy studies (PRISMA-DTA): the PRISMA-DTA statement. JAMA. 2018;319(4):388\u201396.","journal-title":"JAMA"},{"key":"4605_CR16","doi-asserted-by":"crossref","unstructured":"Deeks JJ, Bossuyt PM, Leeflang MM, Takwoingi Y, editors. Cochrane handbook for systematic reviews of diagnostic test accuracy. Version 2.0 (updated July 2023). Cochrane; 2023. Available from: https:\/\/training.cochrane.org\/handbook-diagnostic-test-accuracy\/current","DOI":"10.1002\/14651858.ED000163"},{"issue":"8","key":"4605_CR17","doi-asserted-by":"publisher","first-page":"529","DOI":"10.7326\/0003-4819-155-8-201110180-00009","volume":"155","author":"PF Whiting","year":"2011","unstructured":"Whiting PF, Rutjes AW, Westwood ME, et al. QUADAS-2 Group. QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med. 2011;155(8):529\u201336. https:\/\/doi.org\/10.7326\/0003-4819-155-8-201110180-00009.","journal-title":"Ann Intern Med"},{"issue":"1","key":"4605_CR18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1002\/jrsm.1411","volume":"12","author":"LA McGuinness","year":"2021","unstructured":"McGuinness LA, Higgins JPT. Risk-of-bias visualization (robvis): an R package and Shiny web app for visualizing risk-of-bias assessments. Res Synth Methods. 2021;12(1):55\u201361. https:\/\/doi.org\/10.1002\/jrsm.1411.","journal-title":"Res Synth Methods"},{"issue":"1","key":"4605_CR19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s42003-019-0730-x","volume":"08","author":"Z Li","year":"2020","unstructured":"Li Z, Guo C, Nie D, et al. Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images. Commun Biol Jan. 2020;08(1):15. https:\/\/doi.org\/10.1038\/s42003-019-0730-x.","journal-title":"Commun Biol Jan"},{"issue":"8","key":"4605_CR20","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.1007\/s00417-021-05105-3","volume":"259","author":"C Zhang","year":"2021","unstructured":"Zhang C, He F, Li B, et al. Development of a deep-learning system for detection of lattice degeneration, retinal breaks, and retinal detachment in tessellated eyes using ultra-wide-field fundus images: a pilot study. Graefes Arch Clin Exp Ophthalmol Aug. 2021;259(8):2225\u201334. https:\/\/doi.org\/10.1007\/s00417-021-05105-3.","journal-title":"Graefes Arch Clin Exp Ophthalmol Aug"},{"issue":"9","key":"4605_CR21","doi-asserted-by":"publisher","first-page":"2200067","DOI":"10.1002\/aisy.202200067","volume":"4","author":"WD Zhou","year":"2022","unstructured":"Zhou WD, Dong L, Zhang K, et al. Deep learning for automatic detection of recurrent retinal detachment after surgery using ultra-Widefield fundus images: A single\u2010center study. Adv Intell Syst. 2022;4(9):2200067. https:\/\/doi.org\/10.1002\/aisy.202200067.","journal-title":"Adv Intell Syst"},{"key":"4605_CR22","doi-asserted-by":"publisher","first-page":"101633","DOI":"10.1016\/j.eclinm.2022.101633","volume":"53","author":"J Cao","year":"2022","unstructured":"Cao J, You K, Zhou J, et al. A cascade eye diseases screening system with interpretability and expandability in ultra-wide field fundus images: A multicentre diagnostic accuracy study. EClinicalMedicine. 2022;53:101633. https:\/\/doi.org\/10.1016\/j.eclinm.2022.101633.","journal-title":"EClinicalMedicine"},{"issue":"2","key":"4605_CR23","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s40123-022-00627-3","volume":"12","author":"G Sun","year":"2023","unstructured":"Sun G, Wang X, Xu L, et al. Deep learning for the detection of multiple fundus diseases using Ultra-widefield images. Ophthalmol Ther Apr. 2023;12(2):895\u2013907. https:\/\/doi.org\/10.1007\/s40123-022-00627-3.","journal-title":"Ophthalmol Ther Apr"},{"key":"4605_CR24","doi-asserted-by":"publisher","unstructured":"Tang YW, Ji J, Lin JW Asia Pac J, et al. Automatic detection of peripheral retinal lesions from ultrawide-field fundus images using deep learning. Ophthalmol (Phila). 2023 May-Jun 01 2023;12(3):284\u2013292. https:\/\/doi.org\/10.1097\/APO.0000000000000599.","DOI":"10.1097\/APO.0000000000000599"},{"issue":"11","key":"4605_CR25","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1001\/jamaophthalmol.2023.4650","volume":"01","author":"T Cui","year":"2023","unstructured":"Cui T, Lin D, Yu S, et al. Deep learning performance of Ultra-Widefield fundus imaging for screening retinal lesions in rural locales. JAMA Ophthalmol Nov. 2023;01(11):1045\u201351. https:\/\/doi.org\/10.1001\/jamaophthalmol.2023.4650.","journal-title":"JAMA Ophthalmol Nov"},{"issue":"1","key":"4605_CR26","doi-asserted-by":"publisher","first-page":"9425","DOI":"10.1038\/s41598-017-09891-x","volume":"25","author":"H Ohsugi","year":"2017","unstructured":"Ohsugi H, Tabuchi H, Enno H, Ishitobi N. Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment. Sci Rep Aug. 2017;25(1):9425. https:\/\/doi.org\/10.1038\/s41598-017-09891-x.","journal-title":"Sci Rep Aug"},{"issue":"4","key":"4605_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1167\/tvst.13.4.1","volume":"02","author":"M Christ","year":"2024","unstructured":"Christ M, Habra O, Monnin K, et al. Deep Learning-Based automated detection of retinal breaks and detachments on fundus photography. Transl Vis Sci Technol Apr. 2024;02(4):1. https:\/\/doi.org\/10.1167\/tvst.13.4.1.","journal-title":"Transl Vis Sci Technol Apr"},{"issue":"1","key":"4605_CR28","doi-asserted-by":"publisher","first-page":"188","DOI":"10.18240\/ijo.2024.01.24","volume":"17","author":"QQ Tang","year":"2024","unstructured":"Tang QQ, Yang XG, Wang HQ, Wu DW, Zhang MX. Applications of deep learning for detecting ophthalmic diseases with ultrawide-field fundus images. Int J Ophthalmol. 2024;17(1):188\u2013200. https:\/\/doi.org\/10.18240\/ijo.2024.01.24.","journal-title":"Int J Ophthalmol"},{"issue":"3","key":"4605_CR29","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1177\/09691413221144382","volume":"30","author":"Z Zhelev","year":"2023","unstructured":"Zhelev Z, Peters J, Rogers M, Allen M, Kijauskaite G, Seedat F, Wilkinson E, Hyde C. Test accuracy of artificial intelligence-based grading of fundus images in diabetic retinopathy screening: a systematic review. J Med Screen. 2023;30(3):97\u2013112. https:\/\/doi.org\/10.1177\/09691413221144382.","journal-title":"J Med Screen"},{"issue":"4","key":"4605_CR30","doi-asserted-by":"publisher","first-page":"e0284060","DOI":"10.1371\/journal.pone.0284060","volume":"18","author":"X Leng","year":"2023","unstructured":"Leng X, Shi R, Wu Y, Zhu S, Cai X, Lu X, Liu R. Deep learning for detection of age-related macular degeneration: a systematic review and meta-analysis of diagnostic test accuracy studies. PLoS ONE. 2023;18(4):e0284060. https:\/\/doi.org\/10.1371\/journal.pone.0284060.","journal-title":"PLoS ONE"}],"container-title":["BMC Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12886-025-04605-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12886-025-04605-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12886-025-04605-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:05:17Z","timestamp":1781625917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12886-025-04605-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,3]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["4605"],"URL":"https:\/\/doi.org\/10.1186\/s12886-025-04605-8","relation":{"references":[{"id-type":"doi","id":"10.1055\/a-2116-9565","asserted-by":"subject"}]},"ISSN":["1471-2415"],"issn-type":[{"value":"1471-2415","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,3]]},"assertion":[{"value":"15 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This study was a meta-analysis based solely on previously published data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"60"}}