{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T17:34:29Z","timestamp":1789752869504,"version":"4.0.1"},"reference-count":45,"publisher":"JMIR Publications Inc.","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"\n Background<\/jats:title>\n The supervised deep learning approach provides state-of-the-art performance in a variety of fundus image classification tasks, but it is not applicable for screening tasks with numerous or unknown disease types. The unsupervised anomaly detection (AD) approach, which needs only normal samples to develop a model, may be a workable and cost-saving method of screening for ocular diseases.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to develop and evaluate an AD model for detecting ocular diseases on the basis of color fundus images.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A generative adversarial network\u2013based AD method for detecting possible ocular diseases was developed and evaluated using 90,499 retinal fundus images derived from 4 large-scale real-world data sets. Four other independent external test sets were used for external testing and further analysis of the model\u2019s performance in detecting 6 common ocular diseases (diabetic retinopathy [DR], glaucoma, cataract, age-related macular degeneration, hypertensive retinopathy [HR], and myopia), DR of different severity levels, and 36 categories of abnormal fundus images. The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the model\u2019s performance were calculated and presented.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Our model achieved an AUC of 0.896 with 82.69% sensitivity and 82.63% specificity in detecting abnormal fundus images in the internal test set, and it achieved an AUC of 0.900 with 83.25% sensitivity and 85.19% specificity in 1 external proprietary data set. In the detection of 6 common ocular diseases, the AUCs for DR, glaucoma, cataract, AMD, HR, and myopia were 0.891, 0.916, 0.912, 0.867, 0.895, and 0.961, respectively. Moreover, the AD model had an AUC of 0.868 for detecting any DR, 0.908 for detecting referable DR, and 0.926 for detecting vision-threatening DR.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n The AD approach achieved high sensitivity and specificity in detecting ocular diseases on the basis of fundus images, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. Future studies are required to evaluate the practical applicability of the AD approach in ocular disease screening.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/27822","type":"journal-article","created":{"date-parts":[[2021,5,24]],"date-time":"2021-05-24T18:53:12Z","timestamp":1621882392000},"page":"e27822","source":"Crossref","is-referenced-by-count":37,"title":["Application of an Anomaly Detection Model to Screen for Ocular Diseases Using Color Retinal Fundus Images: Design and Evaluation Study"],"prefix":"10.2196","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8868-0327","authenticated-orcid":false,"given":"Yong","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7443-7067","authenticated-orcid":false,"given":"Weiming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6357-2194","authenticated-orcid":false,"given":"Mengmeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5694-2441","authenticated-orcid":false,"given":"Zhiyuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7442-1383","authenticated-orcid":false,"given":"Feng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8219-5064","authenticated-orcid":false,"given":"Xiangtong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2135-046X","authenticated-orcid":false,"given":"Lixin","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1890-5548","authenticated-orcid":false,"given":"Xia","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6657-6940","authenticated-orcid":false,"given":"Xiuhua","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2021,7,13]]},"reference":[{"key":"ref1","unstructured":"Blindness and vision impairmentWorld Health Organization20212021-06-24https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/blindness-and-visual-impairment"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(17)30293-0"},{"key":"ref3","unstructured":"Diabetic Retinal Screening, Grading, Monitoring and Referral GuidanceNew Zealand Government: Ministry of Health20162021-06-24https:\/\/www.health.govt.nz\/publication\/diabetic-retinal-screening-grading-monitoring-and-referral-guidance"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2015.0068"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2019.16285"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2337\/diacare.25.4.804"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2005.11.001"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-33013-w"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2004.09.083"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/5893601"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2019.07.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.2196\/16607"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2196\/12100"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.02.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2017.3782"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2019.02.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2837012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1260\/2040-2295.1.1.1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2019.8851808"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/S1353-4858(03)00313-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1023\/B:AIRE.0000045502.10941.a9"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.04.007"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2015.11.016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2015.01.001"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging4020036"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2877080"},{"key":"ref31","unstructured":"SchleglTSeeb\u00f6ckPWaldsteinSMSchmidt-ErfurthULangsGUnsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery201725th International Conference on Information Processing in Medical ImagingJune 25-30, 2017Boone, NC"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.010"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/isbi45749.2020.9098374"},{"key":"ref34","first-page":"225","author":"Ouardini, K","year":"2019","journal-title":"Domain Adaptation and Representation Transfer and Medical Image Learning with Less Labels and Imperfect Data"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2013.1743"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5566\/ias.1155"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(03)00475-5"},{"key":"ref38","first-page":"1","volume":"abs\/2001.10883","author":"Davletshina, D","year":"2020","journal-title":"ArXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.07.012"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14569\/IJARAI.2013.020206"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1586\/eop.12.52"},{"key":"ref44","unstructured":"Diabetic eye screening: commission and provideNational Health Service (NHS) Diabetic Eye Screening Programme and Population Screening Programmes20152021-06-24https:\/\/www.gov.uk\/government\/collections\/diabetic-eye-screening-commission-and-provide"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17563"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2021\/7\/e27822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:40:18Z","timestamp":1782841218000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2021\/7\/e27822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,13]]},"references-count":45,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.2196\/27822","relation":{"has-preprint":[{"id-type":"doi","id":"10.2196\/preprints.27822","asserted-by":"object"}]},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,13]]}}}