{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:48:51Z","timestamp":1791395331782,"version":"4.3.3"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T00:00:00Z","timestamp":1669161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>We aimed to investigate the performance of a deep learning model to discriminate early normal-tension glaucoma (NTG) from glaucoma suspect (GS) eyes using Bruch\u2019s membrane opening (BMO)-based optic disc photography.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>501 subjects in total were included in this cross-sectional study, including 255 GS eyes and 246 eyes of early NTG patients. BMO-based optic disc photography (BMO overview) was obtained from spectral-domain optical coherence tomography (OCT). The convolutional neural networks (CNN) model built from scratch was used to classify between early NTG and GS. For diagnostic performances of the model, the accuracy and the area under the curve (AUC) of the receiver operating characteristic curve (ROC) were evaluated in the test set.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The baseline demographics were age, 48.01 \u00b1 13.03 years in GS, 54.48 \u00b1 11.28 years in NTG (<jats:italic>p<\/jats:italic> = 0.000); mean deviation, \u22120.73 \u00b1 2.10 dB in GS, \u22122.80 \u00b1 2.40 dB in NTG (<jats:italic>p<\/jats:italic> = 0.000); and intraocular pressure, 14.92 \u00b1 2.62 mmHg in GS, 14.79 \u00b1 2.61 mmHg in NTG (<jats:italic>p<\/jats:italic> = 0.624). Our CNN model showed the mean AUC of 0.94 (0.83\u20131.00) and the mean accuracy of 0.91 (0.82\u20130.98) with 10-fold cross validation for discriminating between early NTG and GS.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The performance of the CNN model using BMO-based optic disc photography was considerably good in classifying early NTG from GS. This new disc photography of BMO overview can aid in the diagnosis of early glaucoma.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2022.1037647","type":"journal-article","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T05:05:25Z","timestamp":1669179925000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Deep learning classification of early normal-tension glaucoma and glaucoma suspect eyes using Bruch\u2019s membrane opening-based disc photography"],"prefix":"10.3389","volume":"9","author":[{"given":"Sat Byul","family":"Seo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun-kyung","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,11,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1016\/S0140-6736(04)16257-0","article-title":"Primary open-angle glaucoma.","volume":"363","author":"Weinreb","year":"2004","journal-title":"Lancet."},{"key":"B2","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/S0002-9394(00)00538-9","article-title":"The advanced glaucoma intervention study (AGIS): 7. The relationship between control of intraocular pressure and visual field deterioration.","volume":"130","year":"2000","journal-title":"Am J Ophthalmol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1001\/archopht.120.6.701","article-title":"The ocular hypertension treatment study: a randomized trial determines that topical ocular hypotensive medication delays or prevents the onset of primary open-angle glaucoma.","volume":"120","author":"Kass","year":"2002","journal-title":"Arch Ophthalmol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1111\/j.1442-9071.2012.02770.x","article-title":"\u201cStructure-function relationship\u201d in glaucoma: past thinking and current concepts.","volume":"40","author":"Malik","year":"2012","journal-title":"Clin Exp Ophthalmol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1603","DOI":"10.1016\/j.ophtha.2006.05.061","article-title":"The association between glaucomatous visual fields and optic nerve head features in the ocular hypertension treatment study.","volume":"113","author":"Keltner","year":"2006","journal-title":"Ophthalmology."},{"key":"B6","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.preteyeres.2007.08.001","article-title":"A framework for comparing structural and functional measures of glaucomatous damage.","volume":"26","author":"Hood","year":"2007","journal-title":"Prog Retin Eye Res."},{"key":"B7","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.ajo.2013.04.016","article-title":"From clinical examination of the optic disc to clinical assessment of the optic nerve head: a paradigm change.","volume":"156","author":"Chauhan","year":"2013","journal-title":"Am J Ophthalmol."},{"key":"B8","first-page":"254","article-title":"Spectral domain optical coherence tomography in glaucoma: qualitative and quantitative analysis of the optic nerve head and retinal nerve fiber layer (an AOS thesis).","volume":"107","author":"Chen","year":"2009","journal-title":"Trans Am Ophthalmol Soc."},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1117\/1.2773736","article-title":"Minimum distance mapping using three-dimensional optical coherence tomography for glaucoma diagnosis.","volume":"12","author":"Povazay","year":"2007","journal-title":"J Biomed Opt."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1786","DOI":"10.1016\/j.ophtha.2015.06.001","article-title":"Bruch\u2019s membrane opening minimum rim width and retinal nerve fiber layer thickness in a normal white population: a multicenter study.","volume":"122","author":"Chauhan","year":"2015","journal-title":"Ophthalmology."},{"key":"B11","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.ophtha.2012.09.055","article-title":"Enhanced detection of open-angle glaucoma with an anatomically accurate optical coherence tomography-derived neuroretinal rim parameter.","volume":"120","author":"Chauhan","year":"2013","journal-title":"Ophthalmology."},{"key":"B12","doi-asserted-by":"publisher","first-page":"1203","DOI":"10.2147\/OPTH.S62521","article-title":"Correlation between optic nerve head structural parameters and glaucomatous visual field indices.","volume":"8","author":"Mizumoto","year":"2014","journal-title":"Clin Ophthalmol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2953","DOI":"10.1167\/iovs.13-13482","article-title":"Structure-function relationships with spectral-domain optical coherence tomography retinal nerve fiber layer and optic nerve head measurements.","volume":"55","author":"Pollet-Villard","year":"2014","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3390\/jcm8091362","article-title":"Characteristics of patients showing discrepancy between bruch\u2019s membrane opening-minimum rim width and peripapillary retinal nerve fiber layer thickness.","volume":"8","author":"Cho","year":"2019","journal-title":"J Clin Med."},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-76154-7","article-title":"Deep learning classification of early normal-tension glaucoma and glaucoma suspects using Bruch\u2019s membrane opening-minimum rim width and RNFL.","volume":"10","author":"Seo","year":"2020","journal-title":"Sci Rep."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1007\/s00417-010-1585-5","article-title":"Diagnostic ability of retinal ganglion cell complex, retinal nerve fiber layer, and optic nerve head measurements by fourier-domain optical coherence tomography.","volume":"249","author":"Schulze","year":"2011","journal-title":"Graefes Arch Clin Exp Ophthalmol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1016\/j.ophtha.2010.01.031","article-title":"Comparison of different spectral domain optical coherence tomography scanning areas for glaucoma diagnosis.","volume":"117","author":"Rao","year":"2010","journal-title":"Ophthalmology."},{"key":"B18","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1016\/j.jcjo.2011.09.006","article-title":"Spectral-domain optical coherence tomography for early glaucoma assessment: analysis of macular ganglion cell complex versus peripapillary retinal nerve fiber layer.","volume":"46","author":"Moreno","year":"2011","journal-title":"Can J Ophthalmol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1109\/EMBC.2015.7318462","article-title":"Glaucoma detection based on deep convolutional neural network.","volume":"2015","author":"Chen","year":"2015","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc."},{"key":"B20","article-title":"A deep learning based joint segmentation and classification framework for glaucoma assessment in retinal color fundus images.","author":"Chakravarty","year":"2018","journal-title":"arXiv"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","article-title":"Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs.","volume":"125","author":"Li","year":"2018","journal-title":"Ophthalmology."},{"key":"B22","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.knosys.2018.07.043","article-title":"Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models.","volume":"161","author":"Chai","year":"2018","journal-title":"Knowl Based Syst."},{"key":"B23","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/978-3-319-24574-4_80","article-title":"Automatic feature learning for glaucoma detection based on deep learning. Proc. Medical image computing and computer-assisted intervention \u2013 MICCAI.","volume":"9351","author":"Chen","year":"2015","journal-title":"Lecture Notes Comput Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-00949-6_38","article-title":"Glaucoma diagnosis from eye fundus images based on deep morphometric feature estimation.","volume":"2018","author":"Perdomo","year":"2018","journal-title":"Comput Pathol Ophthalmic Med Image Analy."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2775","DOI":"10.1109\/ICIP.2018.8451029","article-title":"A convolutional autoencoding classifier framework for the detection of glaucoma from retinal fundus images.","author":"Pal","year":"2018","journal-title":"Proceeding of the 25th IEEE international conference on image processing (ICIP)."},{"key":"B26","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.survophthal.2013.09.003","article-title":"Population-based glaucoma prevalence studies in Asians.","volume":"59","author":"Cho","year":"2014","journal-title":"Surv Ophthalmol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1038\/eye.2013.285","article-title":"Initial central scotomas vs peripheral scotomas in normal-tension glaucoma: clinical characteristics and progression rates.","volume":"28","author":"Cho","year":"2014","journal-title":"Eye."},{"key":"B28","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.ajo.2019.08.013","article-title":"Clinical evaluation of Swedish interactive thresholding algorithm-faster compared with Swedish interactive thresholding algorithm-standard in normal subjects, glaucoma suspects, and patients with glaucoma.","volume":"208","author":"Phu","year":"2019","journal-title":"Am J Ophthalmol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: an overview.","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Networks."},{"key":"B30","author":"Goodfellow","year":"2016","journal-title":"Deep learning."},{"key":"B31","article-title":"Tensor flow: large-scale machine learning on heterogeneous systems.","author":"Abadi","year":"2016","journal-title":"arXiv"},{"key":"B32","article-title":"An overview of gradient descent optimization algorithms.","author":"Ruder","year":"2016","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"615","DOI":"10.3390\/make3030032","article-title":"Classification of explainable artificial intelligence methods through their output formats.","volume":"3","author":"Vilone","year":"2013","journal-title":"Mach Learn Knowl Extract."},{"key":"B34","doi-asserted-by":"publisher","first-page":"42200","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries.","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access."},{"key":"B35","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1145\/2939672.2939778","article-title":"Why should I trust you? Explaining the predictions of any classifier.","author":"Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2019.101758","article-title":"Ophthalmic diagnosis using deep learning with fundus images \u2013 a critical review.","volume":"102","author":"Sengupta","year":"2020","journal-title":"Artif Intell Med."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1974","DOI":"10.1016\/j.ophtha.2016.05.029","article-title":"Detecting preperimetric glaucoma with standard automated perimetry using a deep learning classifier.","volume":"123","author":"Asaoka","year":"2016","journal-title":"Ophthalmology."},{"key":"B38","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1097\/IJG.0000000000000532","article-title":"Bruch\u2019s membrane opening minimum rim width assessment with spectral-domain optical coherence tomography performs better than confocal scanning laser ophthalmoscopy in discriminating early glaucoma patients from control subjects.","volume":"26","author":"Toshev","year":"2017","journal-title":"J Glaucoma."},{"key":"B39","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.survophthal.2006.10.002","article-title":"Optic disk size and glaucoma.","volume":"52","author":"Hoffmann","year":"2007","journal-title":"Surv Ophthalmol."},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0118920","article-title":"Morphological features and important parameters of large optic discs for diagnosing glaucoma.","volume":"10","author":"Okimoto","year":"2015","journal-title":"PLoS One."},{"key":"B41","first-page":"2012","article-title":"Human optic nerve fiber count and optic disc size.","volume":"33","author":"Jonas","year":"1992","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1136\/bjophthalmol-2015-307730","article-title":"Neuroretinal rim in non-glaucomatous large optic nerve heads: a comparison of confocal scanning laser tomography and spectral domain optical coherence tomography.","volume":"101","author":"Enders","year":"2017","journal-title":"Br J Ophthalmol."},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-61485-2","article-title":"Parapapillary atrophy and changes in the optic nerve head and posterior pole in high myopia.","volume":"10","author":"Sung","year":"2020","journal-title":"Sci Rep."},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.729523","article-title":"Diagnostic classification of bruch\u2019s membrane opening-minimum rim width and retinal nerve fiber layer thickness in myopic eyes by optical coherence tomography.","volume":"8","author":"Wang","year":"2021","journal-title":"Front Med."},{"key":"B45","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1097\/IJG.0000000000001934","article-title":"Clinical utility of bruch membrane opening-minimum rim width for detecting early glaucoma in myopic eyes.","volume":"30","author":"Park","year":"2021","journal-title":"J Glaucoma."},{"key":"B46","doi-asserted-by":"publisher","first-page":"162","DOI":"10.29271\/jcpsp.2021.02.162","article-title":"Comparison of retinal nerve fibre layer versus bruch membrane opening-minimum rim width as an optical coherence tomography-based marker for glaucoma in myopia.","volume":"31","author":"Uzair","year":"2021","journal-title":"J Coll Physicians Surg Pak."},{"key":"B47","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1001\/archopht.1990.01070050091039","article-title":"Quantitative regional structure of the normal human lamina cribrosa. A racial comparison.","volume":"108","author":"Dandona","year":"1990","journal-title":"Arch Ophthalmol."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.1037647\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T05:05:29Z","timestamp":1669179929000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2022.1037647\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,23]]},"references-count":47,"alternative-id":["10.3389\/fmed.2022.1037647"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2022.1037647","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,23]]},"article-number":"1037647"}}