{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:49:09Z","timestamp":1791395349065,"version":"4.3.3"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T00:00:00Z","timestamp":1754265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000053","name":"National Eye Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Ophthalmol."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To evaluate the diagnostic accuracy of a deep learning autoencoder-based model utilizing regions of interest (ROI) from optical coherence tomography (OCT) texture enface images for detecting glaucoma in myopic eyes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This cross-sectional study included a total of 453 eyes from 315 participants from the multi-center \"Swept-Source OCT (SS-OCT) Myopia and Glaucoma Study\", composed of 268 eyes from 168 healthy individuals and 185 eyes from 147 glaucomatous individuals. All participants underwent swept-source optical coherence tomography (SS-OCT) imaging, from which texture enface images were constructed and analyzed. The study compared four methods: (1) global RNFL thickness, (2) texture enface image, (3) a single autoencoder model trained only on healthy eyes, and (4) a dual autoencoder model trained on both healthy and glaucomatous eyes. Diagnostic accuracy was assessed using the area under the receiver operating curves (AUROC) and precision recall curves (AUPRC).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The dual autoencoder model achieved the highest AUROC (95% CI) (0.92 [0.88, 0.95]), significantly outperforming the single autoencoder model trained only on healthy eyes (0.86 [0.83, 0.88], p = 0.01), the global RNFL thickness model (0.84 [0.80, 0.86], p = 0.003), and the texture enface model (0.83 [0.79, 0.85], p = 0.005). Using AUPRC (95% CI), the dual autoencoder model (0.86 [0.83, 0.89]) also outperformed the single autoencoder model trained only on healthy eyes (0.80 [0.78, 0.82], p = 0.02), the global RNFL thickness model (0.74 [0.70, 0.76], p = 0.001), and the texture enface model (0.71 [0.68, 0.73], p&amp;lt;0.001). No significant difference was observed between the global RNFL thickness measurement and the texture enface measurement (p = 0.47).<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The dual autoencoder model, which integrates reconstruction errors from both healthy and glaucomatous training data, demonstrated superior diagnostic accuracy compared to the single autoencoder model, global RNFL thickness and texture enface-based approaches. These findings suggest that deep learning models leveraging ROI-based reconstruction error from texture enface images may enhance glaucoma classification in myopic eyes, providing a robust alternative to conventional structural thickness metrics.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fopht.2025.1624015","type":"journal-article","created":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T04:10:34Z","timestamp":1754280634000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Glaucoma detection in myopic eyes using deep learning autoencoder-based regions of interest"],"prefix":"10.3389","volume":"5","author":[{"given":"Christopher","family":"Bowd","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akram","family":"Belghith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Christopher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makoto","family":"Araie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aiko","family":"Iwase","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goji","family":"Tomita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyoko","family":"Ohno-Matsui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hitomi","family":"Saito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroshi","family":"Murata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsutomu","family":"Kikawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhisa","family":"Sugiyama","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomomi","family":"Higashide","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Atsuya","family":"Miki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toru","family":"Nakazawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Makoto","family":"Aihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae-Woo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher Kai Shun","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert N.","family":"Weinreb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linda M.","family":"Zangwill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2021-320644","article-title":"High myopia as risk factor for the 10-year incidence of open-angle glaucoma in the Beijing Eye Study","volume":"107","author":"Wang","year":"2023","journal-title":"Br J Ophthalmol"},{"key":"B2","doi-asserted-by":"crossref","DOI":"10.1001\/archopht.1994.01090180121046","article-title":"Prevalence of open angle glaucoma","volume":"112","author":"Leske","year":"1994","journal-title":"Arch Ophthalmol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.06.050","article-title":"High myopia and glaucoma susceptibility the Beijing Eye Study","volume":"114","author":"Xu","year":"2007","journal-title":"Ophthalmology."},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1016\/S0161-6420(99)90416-5","article-title":"The relationship between glaucoma and myopia: the Blue Mountain Eye Study","volume":"106","author":"Mitchell","year":"1999","journal-title":"Ophthalmology."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2016.01.006","article-title":"Global prevalence of myopia and high myopia and temporal trends from 2000 through 2050","volume":"123","author":"Holden","year":"2016","journal-title":"Ophthalmology. May"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1097\/Ijg.0000000000000574","article-title":"Optic nerve head histopathology in high axial myopia","volume":"26","author":"Jonas","year":"2017","journal-title":"J Glaucoma."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s00417-016-3542-4","article-title":"Optic disc and peripapillary retinal nerve fiber layer characteristics associated with glaucomatous optic disc in young myopia","volume":"255","author":"Lee","year":"2017","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1136\/bjophthalmol-2018-313530","article-title":"Glaucoma in myopia: diagnostic dilemmas","volume":"103","author":"Tan","year":"2019","journal-title":"Brit J Ophthalmol Oct"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2024.12.003","article-title":"Evaluating glaucoma in myopic eyes: Challenges and opportunities","volume":"70","author":"Jiravarnsirikul","year":"2024","journal-title":"Surv Ophthalmol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.ajo.2022.04.019","article-title":"Diagnostic accuracy of macular thickness map and texture en face images for detecting glaucoma in eyes with axial high myopia","volume":"242","author":"Bowd","year":"2022","journal-title":"Am J Ophthalmol May 2"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.10.8.19","article-title":"Individualized glaucoma change detection using deep learning auto encoder-based regions of interest","volume":"10","author":"Bowd","year":"2021","journal-title":"Transl Vis Sci Technol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.ajo.2023.09.002","article-title":"Association of bergmeister papilla and deep optic nerve head structures with prelaminar schisis of normal and glaucomatous eyes","volume":"257","author":"Saito","year":"2024","journal-title":"Am J Ophthalmol Jan"},{"key":"B13","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.ajo.2024.02.017","article-title":"Effects of deep optic nerve head structures on bruch's membrane opening- minimum rim width and peripapillary retinal nerve fiber layer","volume":"263","author":"Kambayashi","year":"2024","journal-title":"Am J Ophthalmol Jul"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2023.01.003","article-title":"Deep optic nerve head structures associated with increasing axial length in healthy myopic eyes of moderate axial length","volume":"249","author":"Saito","year":"2023","journal-title":"Am J Ophthalmol May"},{"key":"B15","article-title":"Clinical decisions in glaucoma","author":"Hodapp","year":"1993","journal-title":"Mosby"},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10584-0_25","article-title":"OTC: A novel local descriptor for scene classification","volume":"8695","author":"Margolin","year":"2014","journal-title":"Lect Notes Comput Sc."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.1.3.034504","article-title":"Glaucoma progression detection using nonlocal Markov random field prior","volume":"1","author":"Belghith","year":"2014","journal-title":"J Med Imaging."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2006.03.005","article-title":"Markov random field image segmentation model for color textured images","volume":"24","author":"Kato","year":"2006","journal-title":"Image Vis Comput"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2019.09.036","article-title":"Deep learning approaches predict glaucomatous visual field damage from OCT optic nerve head en face images and retinal nerve fiber layer thickness maps","volume":"127","author":"Christopher","year":"2020","journal-title":"Ophthalmology."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/3.3.421","article-title":"Distribution-free ROC analysis using binary regression techniques","volume":"3","author":"Alonzo","year":"2002","journal-title":"Biostatistics."},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2022.04.012","article-title":"Retinal nerve fiber layer optical texture analysis (ROTA): involvement of the papillomacular bundle and papillofoveal bundle in early glaucoma","volume":"129","author":"Leung","year":"2022","journal-title":"Ophthalmology."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2024.05.013","article-title":"Retinal nerve fiber layer optical texture analysis and 10\u20132 visual field assessment in glaucoma","volume":"266","author":"Kamalipour","year":"2024","journal-title":"Am J Ophthalmol Oct"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1260\/2040-2295.1.1.1","article-title":"Detection of pathological myopia by PAMELA with texture-based features through an SVM approach","volume":"1","author":"Liu","year":"2010","journal-title":"J Healthc Eng."},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1109\/ICIEA.2010.5515493","volume-title":"Fusion of pixel and texture features to detect pathological myopia","author":"Benghai","year":"2010"},{"key":"B25","doi-asserted-by":"publisher","first-page":"8040","DOI":"10.1038\/s41598-023-34794-5","article-title":"Development of a deep learning system to detect glaucoma using macular vertical optical coherence tomography scans of myopic eyes","volume":"13","author":"Kim","year":"2023","journal-title":"Sci Rep"},{"key":"B26","first-page":"791","article-title":"Diagnostic ability of ganglion cell complex thickness to detect glaucoma in high myopia eyes by Fourier domain optical coherence tomography","volume":"11","author":"Wang","year":"2018","journal-title":"Int J ophthalmology."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1097\/ijg.0000000000002268","article-title":"The prevalence of optical coherence tomography artifacts in high myopia and its influence on glaucoma diagnosis","volume":"32","author":"Poon","year":"2023","journal-title":"J Glaucoma."},{"key":"B28","doi-asserted-by":"publisher","first-page":"9762","DOI":"10.1038\/s41598-025-91880-6","article-title":"Optical coherence tomography angiography compared with optical coherence tomography for detection of glaucoma progression with high myopia","volume":"15","author":"Chang","year":"2025","journal-title":"Sci Rep"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0317354","article-title":"In vivo imaging of mitochondrial function in normal, glaucoma suspect, and glaucoma eyes","volume":"20","author":"Caro","year":"2025","journal-title":"PloS One"}],"container-title":["Frontiers in Ophthalmology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2025.1624015\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,4]],"date-time":"2025-08-04T04:10:36Z","timestamp":1754280636000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fopht.2025.1624015\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,4]]},"references-count":29,"alternative-id":["10.3389\/fopht.2025.1624015"],"URL":"https:\/\/doi.org\/10.3389\/fopht.2025.1624015","relation":{},"ISSN":["2674-0826"],"issn-type":[{"value":"2674-0826","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,4]]},"article-number":"1624015"}}