{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:12:44Z","timestamp":1782835964350,"version":"3.54.5"},"reference-count":32,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Shantou Municipal Science and Technology Project","award":["190917155269927"],"award-info":[{"award-number":["190917155269927"]}]},{"name":"Central Guiding Local Science and Technology Development Project","award":["STKJ2024064"],"award-info":[{"award-number":["STKJ2024064"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Ophth"],"accepted":{"date-parts":[[2025,9,25]]},"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>To develop a multidimensional imaging model to detect primary open-angle glaucoma (POAG) by combining fundus photographs with the retinal nerve fibre layer (RNFL) and ganglion cell-inner plexiform layer (GCIPL) thickness maps and deviation maps.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>1054 eyes of 546 patients were included. Images were randomly divided into training, validation and test datasets at 64%, 16% and 20%. Four basic convolutional neural network algorithms were used to develop the multidimensional imaging model by combining fundus photographs, RNFL and GCIPL deviation maps, with RNFL and GCIPL thickness maps. POAG structure damage was defined as RNFL and GCIPL thinning with neuroretinal rim thinning.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Multidimensional imaging model obtained an area under the receiver operating characteristic curve (AUC) of 0.970 (95% CI 0.958 to 0.979), which was superior to the fundus photographs model (AUC, 0.945 (95% CI 0.929 to 0.958); p\uff1c0.05), RNFL and GCIPL deviation maps model (AUC, 0.931 (95% CI 0.915 to 0.946); p\uff1c0.001), RNFL and GCIPL thickness maps model (AUC, 0.958 (95% CI 0.944 to 0.969)) in the test dataset. There was a significant difference between the multidimensional imaging model (AUC, 0.969 (95% CI 0.934 to 0.988)) and three glaucoma ophthalmologists (attending ophthalmologist 1: AUC, 0.847; attending ophthalmologist 2: AUC, 0.842; resident ophthalmologist: AUC, 0.755; p\uff1c0.001 for both) in one fold of the test dataset. Furthermore, the overall AUCs were lower in the myopic group than in the non-myopic group. The overall AUC for lesion detection by each model (p=0.159) was: low myopia group (AUC, 0.968 (95% CI 0.940 to 0.985)) &gt; moderate myopia group (AUC, 0.966 (95% CI 0.936 to 0.984)) &gt;high myopia group (AUC, 0.958 (95% CI 0.927 to 0.978)). The multidimensional imaging model outperformed unimodal models in diagnosing myopia combined with POAG.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The multidimensional imaging model, combining fundus photographs, RNFL and GCIPL deviation maps, with RNFL and GCIPL thickness maps, could perform better than unimodal models. Its potential to improve the diagnostic accuracy of myopia combined with POAG for various myopia levels is promising. This means it could be a valuable tool for assisting with POAG diagnosis in the clinic, offering hope for improved patient care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjophth-2025-002274","type":"journal-article","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T06:50:20Z","timestamp":1761202220000},"page":"e002274","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Multidimensional imaging model for diagnosing primary open-angle glaucoma using fundus photographs and optical coherence tomography images"],"prefix":"10.1136","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1061-4313","authenticated-orcid":false,"given":"Jiali","family":"Qiu","sequence":"first","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5712-1581","authenticated-orcid":false,"given":"Jianwei","family":"Lin","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7017-8537","authenticated-orcid":false,"given":"Lipin","family":"Shi","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3219-1329","authenticated-orcid":false,"given":"Chukai","family":"Huang","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4414-9758","authenticated-orcid":false,"given":"Kunliang","family":"Qiu","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8476-1955","authenticated-orcid":false,"given":"Geng","family":"Wang","sequence":"additional","affiliation":[{"name":"Joint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"2026010721211340000_10.1.e002274.1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2014.05.013"},{"key":"2026010721211340000_10.1.e002274.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2018.10.007"},{"key":"2026010721211340000_10.1.e002274.3","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2014.3192"},{"key":"2026010721211340000_10.1.e002274.4","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(04)16257-0"},{"key":"2026010721211340000_10.1.e002274.5","doi-asserted-by":"crossref","first-page":"e172","DOI":"10.1016\/S2589-7500(19)30085-8","article-title":"Detection of glaucomatous optic neuropathy with spectral-domain optical coherence tomography: a retrospective training and validation deep-learning analysis","volume":"1","author":"Ran","year":"2019","journal-title":"Lancet Digit Health"},{"key":"2026010721211340000_10.1.e002274.6","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9394(89)90488-1"},{"key":"2026010721211340000_10.1.e002274.7","doi-asserted-by":"crossref","first-page":"S17","DOI":"10.1016\/j.survophthal.2008.08.003","article-title":"Diagnostic tools for glaucoma detection and management","volume":"53 Suppl1","author":"Sharma","year":"2008","journal-title":"Surv Ophthalmol"},{"key":"2026010721211340000_10.1.e002274.8","doi-asserted-by":"publisher","DOI":"10.1111\/ceo.12158"},{"key":"2026010721211340000_10.1.e002274.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2016.01.006"},{"key":"2026010721211340000_10.1.e002274.10","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":"2026010721211340000_10.1.e002274.11","doi-asserted-by":"publisher","DOI":"10.1097\/IJG.0000000000001458"},{"key":"2026010721211340000_10.1.e002274.12","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0219126","article-title":"A feature agnostic approach for glaucoma detection in OCT volumes","volume":"14","author":"Maetschke","year":"2019","journal-title":"PLoS One"},{"key":"2026010721211340000_10.1.e002274.13","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1016\/j.ophtha.2019.10.025","article-title":"The Impact of OCT on Diagnostic Accuracy of the Technology-Based Eye Care Services Protocol: Part II of the Technology-Based Eye Care Services Compare Trial","volume":"127","author":"Maa","year":"2020","journal-title":"Ophthalmology"},{"key":"2026010721211340000_10.1.e002274.14","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0207784","article-title":"Automated algorithms combining structure and function outperform general ophthalmologists in diagnosing glaucoma","volume":"13","author":"Shigueoka","year":"2018","journal-title":"PLoS One"},{"key":"2026010721211340000_10.1.e002274.15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"2026010721211340000_10.1.e002274.16","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1038\/s41433-020-01191-5","article-title":"Deep learning in glaucoma with optical coherence tomography: a review","volume":"35","author":"Ran","year":"2021","journal-title":"Eye (Lond)"},{"key":"2026010721211340000_10.1.e002274.17","doi-asserted-by":"crossref","first-page":"100759","DOI":"10.1016\/j.preteyeres.2019.04.003","article-title":"Deep learning in ophthalmology: The technical and clinical considerations","volume":"72","author":"Ting","year":"2019","journal-title":"Prog Retin Eye Res"},{"key":"2026010721211340000_10.1.e002274.18","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2018-313173"},{"key":"2026010721211340000_10.1.e002274.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2020.10.022"},{"key":"2026010721211340000_10.1.e002274.20","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ophtha.2015.10.053","article-title":"Primary Open-Angle Glaucoma Preferred Practice Pattern(\u00ae) Guidelines","volume":"123","author":"Prum","year":"2016","journal-title":"Ophthalmology"},{"key":"2026010721211340000_10.1.e002274.21","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.ophtha.2021.07.032","article-title":"Multimodal Machine Learning Using Visual Fields and Peripapillary Circular OCT Scans in Detection of Glaucomatous Optic Neuropathy","volume":"129","author":"Xiong","year":"2022","journal-title":"Ophthalmology"},{"key":"2026010721211340000_10.1.e002274.22","doi-asserted-by":"crossref","DOI":"10.1186\/s12880-018-0273-5","article-title":"Automatic differentiation of Glaucoma visual field from non-glaucoma visual filed using deep convolutional neural network","volume":"18","author":"Li","year":"2018","journal-title":"BMC Med Imaging"},{"key":"2026010721211340000_10.1.e002274.23","doi-asserted-by":"publisher","DOI":"10.1007\/s00417-020-04609-8"},{"key":"2026010721211340000_10.1.e002274.24","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":"2026010721211340000_10.1.e002274.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2011.03.012"},{"key":"2026010721211340000_10.1.e002274.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2024.101246"},{"key":"2026010721211340000_10.1.e002274.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2011.01.058"},{"key":"2026010721211340000_10.1.e002274.28","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18152"},{"key":"2026010721211340000_10.1.e002274.29","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-018-35044-9","article-title":"Performance of Deep Learning Architectures and Transfer Learning for Detecting Glaucomatous Optic Neuropathy in Fundus Photographs","volume":"8","author":"Christopher","year":"2018","journal-title":"Sci Rep"},{"key":"2026010721211340000_10.1.e002274.30","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1007\/s10384-014-0366-9","article-title":"Diagnostic performance and reproducibility of circumpapillary retinal nerve fiber layer thickness measurement in 10-degree sectors in early stage glaucoma","volume":"59","author":"Hirasawa","year":"2015","journal-title":"Jpn J Ophthalmol"},{"key":"2026010721211340000_10.1.e002274.31","doi-asserted-by":"publisher","DOI":"10.1097\/IJG.0000000000000765"},{"key":"2026010721211340000_10.1.e002274.32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.01.023"}],"container-title":["BMJ Open Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjophth-2025-002274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:22:11Z","timestamp":1767849731000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjophth.bmj.com\/lookup\/doi\/10.1136\/bmjophth-2025-002274"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,10,22]]},"published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1136\/bmjophth-2025-002274"],"URL":"https:\/\/doi.org\/10.1136\/bmjophth-2025-002274","relation":{},"ISSN":["2397-3269"],"issn-type":[{"value":"2397-3269","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}