{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T19:32:03Z","timestamp":1785526323871,"version":"3.56.0"},"reference-count":34,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T00:00:00Z","timestamp":1725926400000},"content-version":"unspecified","delay-in-days":9,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Ophth"],"accepted":{"date-parts":[[2024,8,25]]},"published-print":{"date-parts":[[2024,9]]},"abstract":"<jats:sec>\n                  <jats:title>Objectives<\/jats:title>\n                  <jats:p>Train an automatic retinal image analysis (ARIA) method to screen glaucomatous optic neuropathy (GON) on non-mydriatic retinal images labelled with the additional results of optical coherence tomography (OCT) and assess different models for the GON classification.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>All the images were obtained from the hospital for training and 10-fold cross-validation. Two methods were used to improve the classification performance: (1) using images labelled with the additional results of OCT as the reference standard and (2) generating models using retinal features from the entire images, the region of interest (ROI) of the optic disc, and the ROI of the macula, and the combination of all the features.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Overall, we collected 1338 images with paired OCT scans. In 10-fold validation, ARIA achieved sensitivities of 92.2 %, 92.7% and 85.7%, specificities of 88.8%, 86.7% and 80.2% and accuracies of 90.6%, 89.9% and 83.1% using the retinal features from the entire images, the ROI of the optic disc and the ROI of the macula, respectively. We found the model combining all the features has the best classification performance and obtained a sensitivity of 92.5%, a specificity of 92.1% and an accuracy of 92.4%, which is significantly different from other models (p&lt;0.001).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>We used two methods to improve the classification performance and found the best model to detect glaucoma on colour fundus retinal images. It can become a cost-effective and relatively more accurate glaucoma screening tool than conventional methods.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1136\/bmjophth-2023-001594","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T22:50:17Z","timestamp":1726008617000},"page":"e001594","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic retinal image analysis methods using colour fundus images for screening glaucomatous optic neuropathy"],"prefix":"10.1136","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8010-8585","authenticated-orcid":false,"given":"Chuying","family":"Shi","sequence":"first","affiliation":[{"name":"Center for Clinical Research and Biostatistics, Jockey Club School of Public Health and Primary Care, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China"},{"name":"Department of Ophthalmology, Zhongshan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Lee","sequence":"additional","affiliation":[{"name":"Center for Clinical Research and Biostatistics, Jockey Club School of Public Health and Primary Care, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Pathology, Fudan University Shanghai Cancer Center, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gechun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Zhongshan Hospital, Fudan University, Shanghai, China"},{"name":"Department of Ophthalmology, Affiliated Xiaoshan Hospital, Hangzhou Normal University, Hangzhou, Zhejiang, People's Republic of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Zhongshan Hospital, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7238-845X","authenticated-orcid":false,"given":"Benny Chung-Ying","family":"Zee","sequence":"additional","affiliation":[{"name":"Center for Clinical Research and Biostatistics, Jockey Club School of Public Health and Primary Care, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2024,9,10]]},"reference":[{"key":"2025090109134383000_9.1.e001594.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2014.05.013"},{"key":"2025090109134383000_9.1.e001594.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2011.02.050"},{"key":"2025090109134383000_9.1.e001594.3","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1001\/jamaophthalmol.2015.1478","article-title":"Prevalence, Risk Factors, and Visual Features of Undiagnosed Glaucoma: The Singapore Epidemiology of Eye Diseases Study","volume":"133","author":"Chua","year":"2015","journal-title":"JAMA Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.4","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1097\/ICU.0000000000000649","article-title":"Glaucoma screening: where are we and where do we need to go?","volume":"31","author":"Tan","year":"2020","journal-title":"Curr Opin Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.5","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1016\/bs.pbr.2020.07.002","article-title":"Artificial intelligence and deep learning in glaucoma: Current state and future prospects","volume":"257","author":"Girard","year":"2020","journal-title":"Prog Brain Res"},{"key":"2025090109134383000_9.1.e001594.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.01.023"},{"key":"2025090109134383000_9.1.e001594.7","doi-asserted-by":"crossref","first-page":"1353","DOI":"10.1001\/jamaophthalmol.2019.3501","article-title":"Development and Validation of a Deep Learning System to Detect Glaucomatous Optic Neuropathy Using Fundus Photographs","volume":"137","author":"Liu","year":"2019","journal-title":"JAMA Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"2025090109134383000_9.1.e001594.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2019.07.024"},{"key":"2025090109134383000_9.1.e001594.10","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.ophtha.2015.10.055","article-title":"Primary Open-Angle Glaucoma Suspect Preferred Practice Pattern(\u00ae) Guidelines","volume":"123","author":"Prum","year":"2016","journal-title":"Ophthalmology"},{"key":"2025090109134383000_9.1.e001594.11","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1097\/OPX.0000000000000394","article-title":"Visual Fields and OCT Role in Diagnosis of Glaucoma","volume":"91","author":"Bae","year":"2014","journal-title":"Optom Vis Sci"},{"key":"2025090109134383000_9.1.e001594.12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2008.07.023"},{"key":"2025090109134383000_9.1.e001594.13","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(94)31118-3"},{"key":"2025090109134383000_9.1.e001594.14","doi-asserted-by":"crossref","first-page":"1281","DOI":"10.2147\/OPTH.S140225","article-title":"Agreement on the evaluation of glaucomatous optic nerve head findings by ophthalmology residents and a glaucoma specialist","volume":"11","author":"Rossetto","year":"2017","journal-title":"Clin Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.15","doi-asserted-by":"crossref","first-page":"ii15","DOI":"10.1136\/bjophthalmol-2013-304326","article-title":"OCT for glaucoma diagnosis, screening and detection of glaucoma progression","volume":"98 Suppl 2","author":"Bussel","year":"2014","journal-title":"Br J Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2008.01.011"},{"key":"2025090109134383000_9.1.e001594.17","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1111\/j.1442-9071.2007.01457.x","article-title":"Glaucoma screening: analysis of conventional and telemedicine\u2010friendly devices","volume":"35","author":"Kumar","year":"2007","journal-title":"Clinical Exper Ophthalmology"},{"key":"2025090109134383000_9.1.e001594.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.05.008"},{"key":"2025090109134383000_9.1.e001594.19","doi-asserted-by":"crossref","first-page":"357","DOI":"10.4103\/IJO.IJO_939_23","article-title":"Evaluation of ganglion cell-inner plexiform layer thickness in the diagnosis of pre-perimetric glaucoma and comparison to retinal nerve fiber layers","volume":"72","author":"Yadav","year":"2024","journal-title":"Indian J Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.20","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1001\/jamaophthalmol.2022.1608","article-title":"Identifying Glaucoma in Primary Care Offices","volume":"140","author":"Quigley","year":"2022","journal-title":"JAMA Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.21","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics12051100","article-title":"Combining Optical Coherence Tomography and Fundus Photography to Improve Glaucoma Screening","volume":"12","author":"Watanabe","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"2025090109134383000_9.1.e001594.22","unstructured":"Zee CY , Lee JW , Li Q . Method and device for retinal image analysis. US8787638 B2. 2014. Available: https:\/\/patents.google.com\/patent\/US20120257164A1\/en"},{"key":"2025090109134383000_9.1.e001594.23","doi-asserted-by":"crossref","unstructured":"Kaiming H , Xiangyu Z , Shaoqing R , et al . Deep Residual Learning for Image Recognition. 2016:770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025090109134383000_9.1.e001594.24","unstructured":"Hastie T . The elements of statistical learning: data mining, inference, and prediction. Second edition ed. In: Tibshirani R and Friedman JH ed. New York: Springer, 2009."},{"key":"2025090109134383000_9.1.e001594.25","doi-asserted-by":"publisher","DOI":"10.2307\/2531595"},{"key":"2025090109134383000_9.1.e001594.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2012.09.055"},{"key":"2025090109134383000_9.1.e001594.27","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1016\/j.ophtha.2016.03.025","article-title":"African Descent and Glaucoma Evaluation Study (ADAGES): Racial Differences in Optic Disc Hemorrhage and Beta-Zone Parapapillary Atrophy","volume":"123","author":"Skaat","year":"2016","journal-title":"Ophthalmology"},{"key":"2025090109134383000_9.1.e001594.28","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.ajo.2019.02.015","article-title":"Predictive Factors for the Rate of Visual Field Progression in the Advanced Imaging for Glaucoma Study","volume":"202","author":"Zhang","year":"2019","journal-title":"Am J Ophthalmol"},{"key":"2025090109134383000_9.1.e001594.29","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/j.ophtha.2016.02.017","article-title":"Risk of Visual Field Progression in Glaucoma Patients with Progressive Retinal Nerve Fiber Layer Thinning: A 5-Year Prospective Study","volume":"123","author":"Yu","year":"2016","journal-title":"Ophthalmology"},{"key":"2025090109134383000_9.1.e001594.30","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1146\/annurev-vision-100419-111350","article-title":"Optical Coherence Tomography and Glaucoma","volume":"7","author":"Geevarghese","year":"2021","journal-title":"Annu Rev Vis Sci"},{"key":"2025090109134383000_9.1.e001594.31","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2014-305907"},{"key":"2025090109134383000_9.1.e001594.32","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.ogla.2018.04.002","article-title":"A Deep Learning-Based Algorithm Identifies Glaucomatous Discs Using Monoscopic Fundus Photographs","volume":"1","author":"Liu","year":"2018","journal-title":"Ophthalmol Glaucoma"},{"key":"2025090109134383000_9.1.e001594.33","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1097\/IJG.0000000000001187","article-title":"Screening Glaucoma With Red-free Fundus Photography Using Deep Learning Classifier and Polar Transformation","volume":"28","author":"Lee","year":"2019","journal-title":"J Glaucoma"},{"key":"2025090109134383000_9.1.e001594.34","doi-asserted-by":"crossref","first-page":"e94","DOI":"10.1111\/aos.14193","article-title":"Accurate prediction of glaucoma from colour fundus images with a convolutional neural network that relies on active and transfer learning","volume":"98","author":"Hemelings","year":"2020","journal-title":"Acta Ophthalmol"}],"container-title":["BMJ Open Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjophth-2023-001594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T16:13:54Z","timestamp":1756743234000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjophth.bmj.com\/lookup\/doi\/10.1136\/bmjophth-2023-001594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,9,10]]},"published-print":{"date-parts":[[2024,9]]}},"alternative-id":["10.1136\/bmjophth-2023-001594"],"URL":"https:\/\/doi.org\/10.1136\/bmjophth-2023-001594","relation":{},"ISSN":["2397-3269"],"issn-type":[{"value":"2397-3269","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}