{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:48:56Z","timestamp":1791395336665,"version":"4.3.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T00:00:00Z","timestamp":1670803200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T00:00:00Z","timestamp":1670803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Ophthalmol"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>To verify efficacy of automatic screening and classification of glaucoma with deep learning system.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>A cross-sectional, retrospective study in a tertiary referral hospital. Patients with healthy optic disc, high-tension, or normal-tension glaucoma were enrolled. Complicated non-glaucomatous optic neuropathy was excluded. Colour and red-free fundus images were collected for development of DLS and comparison of their efficacy. The convolutional neural network with the pre-trained EfficientNet-b0 model was selected for machine learning. Glaucoma screening (Binary) and ternary classification with or without additional demographics (age, gender, high myopia) were evaluated, followed by creating confusion matrix and heatmaps. Area under receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score were viewed as main outcome measures.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Two hundred and twenty-two cases (421 eyes) were enrolled, with 1851 images in total (1207 normal and 644 glaucomatous disc). Train set and test set were comprised of 1539 and 312 images, respectively. If demographics were not provided, AUC, accuracy, precision, sensitivity, F1 score, and specificity of our deep learning system in eye-based glaucoma screening were 0.98, 0.91, 0.86, 0.86, 0.86, and 0.94 in test set. Same outcome measures in eye-based ternary classification without demographic data were 0.94, 0.87, 0.87, 0.87, 0.87, and 0.94 in our test set, respectively. Adding demographics has no significant impact on efficacy, but establishing a linkage between eyes and images is helpful for a better performance. Confusion matrix and heatmaps suggested that retinal lesions and quality of photographs could affect classification. Colour fundus images play a major role in glaucoma classification, compared to red-free fundus images.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Promising results with high AUC and specificity were shown in distinguishing normal optic nerve from glaucomatous fundus images and doing further classification.\n<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12886-022-02730-2","type":"journal-article","created":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T11:02:59Z","timestamp":1670842979000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["Application of a deep learning system in glaucoma screening and further classification with colour fundus photographs: a case control study"],"prefix":"10.1186","volume":"22","author":[{"given":"Kuo-Hsuan","family":"Hung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Ching","family":"Kao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hsuan","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Ting","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuen-Heng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oscar Kuang-Sheng","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,12]]},"reference":[{"key":"2730_CR1","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1136\/bjo.2005.081224","volume":"90","author":"HA Quigley","year":"2006","unstructured":"Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006;90:262\u20137.","journal-title":"Br J Ophthalmol"},{"key":"2730_CR2","doi-asserted-by":"publisher","first-page":"705","DOI":"10.3109\/02713683.2013.867353","volume":"39","author":"K Shon","year":"2014","unstructured":"Shon K, Wollstein G, Schuman JS, Sung KR. Prediction of glaucomatous visual field progression: pointwise analysis. Curr Eye Res. 2014;39:705\u201310.","journal-title":"Curr Eye Res"},{"key":"2730_CR3","first-page":"CD008803","volume":"11","author":"M Michelessi","year":"2015","unstructured":"Michelessi M, Lucenteforte E, Oddone F, Brazzelli M, Parravano M, Franchi S, et al. Optic nerve head and fiber layer imaging for diagnosing glaucoma. version 2. Cochrane Database Syst Rev. 2015;11:CD008803.","journal-title":"Cochrane Database Syst Rev"},{"issue":"4","key":"2730_CR4","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1016\/j.ophtha.2018.11.016","volume":"126","author":"R Sayres","year":"2019","unstructured":"Sayres R, Taly A, Rahimy E, Blumer K, Coz D, Hammel N, et al. Using a deep learning algorithm and integrated gradients explanation to assist grading for diabetic retinopathy. Ophthalmology. 2019;126(4):552\u201364.","journal-title":"Ophthalmology"},{"key":"2730_CR5","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1001\/jamaophthalmol.2017.3782","volume":"135","author":"PM Burlina","year":"2017","unstructured":"Burlina PM, Joshi N, Pekala M, Pacheco KD, Freund DE, Bressler NM. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 2017;135:1170\u20136.","journal-title":"JAMA Ophthalmol"},{"key":"2730_CR6","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1056\/NEJMoa1917130","volume":"382","author":"D Milea","year":"2020","unstructured":"Milea D, Najjar RP, Zhubo J, Ting D, Vasseneix C, Xu X, et al. Artificial intelligence to detect papilledema from ocular fundus photographs. N Engl J Med. 2020;382:1687\u201395.","journal-title":"N Engl J Med"},{"issue":"8","key":"2730_CR7","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","volume":"125","author":"Z Li","year":"2018","unstructured":"Li Z, He Y, Keel S, Meng W, Chang RT, He M. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology. 2018;125(8):1199\u2013206.","journal-title":"Ophthalmology"},{"key":"2730_CR8","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.ajo.2018.10.007","volume":"198","author":"R Asaoka","year":"2019","unstructured":"Asaoka R, Murata H, Hirasawa K, Fujino Y, Matsuura M, Miki A, et al. Using deep learning and transfer learning to accurately diagnose early-onset glaucoma from macular optical coherence tomography images. Am J Ophthalmol. 2019;198:136\u201345.","journal-title":"Am J Ophthalmol"},{"issue":"7","key":"2730_CR9","doi-asserted-by":"publisher","first-page":"2748","DOI":"10.1167\/iovs.17-23387","volume":"59","author":"M Christopher","year":"2018","unstructured":"Christopher M, Belghith A, Weinreb RN, Bowd C, Goldbaum MH, Saunders LJ, et al. Retinal nerve fiber layer features identified by unsupervised machine learning on optical coherence tomography scans predict glaucoma progression. Invest Ophthalmol Vis Sci. 2018;59(7):2748\u201356.","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2730_CR10","doi-asserted-by":"publisher","unstructured":"An G, Omodaka K, Hashimoto K, Tsuda S, Shiga Y, Takada N, et al. Glaucoma Diagnosis with Machine Learning Based on Optical Coherence Tomography and Color Fundus Images. J Healthc Eng. 2019;2019:4061313. https:\/\/doi.org\/10.1155\/2019\/4061313.","DOI":"10.1155\/2019\/4061313"},{"key":"2730_CR11","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2017.18152","volume":"318","author":"DSW Ting","year":"2017","unstructured":"Ting DSW, Cheung CY, Lim G, Tan GSW, Quang ND, Gan A, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211\u201323.","journal-title":"JAMA"},{"issue":"1","key":"2730_CR12","doi-asserted-by":"publisher","first-page":"20313","DOI":"10.1038\/s41598-021-99605-1","volume":"11","author":"R Hemelings","year":"2021","unstructured":"Hemelings R, Elen B, Barbosa-Breda J, Blaschko MB, De Boever P, Stalmans I. Deep learning on fundus images detects glaucoma beyond the optic disc. Sci Rep. 2021;11(1):20313.","journal-title":"Sci Rep"},{"key":"2730_CR13","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1136\/bjophthalmol-2020-318107","volume":"106","author":"K Nakahara","year":"2022","unstructured":"Nakahara K, Asaoka R, Tanito M, Shibata N, Mitsuhashi K, Fujino Y, et al. Deep learning-assisted (automatic) diagnosis of glaucoma using a smartphone. Br J Ophthalmol. 2022;106:587\u201392.","journal-title":"Br J Ophthalmol"},{"issue":"1","key":"2730_CR14","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1007\/s10384-019-00706-2","volume":"64","author":"J Lee","year":"2020","unstructured":"Lee J, Kim YK, Jeoung JW, Ha A, Kim YW, Park KH. Machine learning classifiers-based prediction of normal-tension glaucoma progression in young myopic patients. Jpn J Ophthalmol. 2020;64(1):68\u201376.","journal-title":"Jpn J Ophthalmol"},{"key":"2730_CR15","doi-asserted-by":"publisher","first-page":"19042","DOI":"10.1038\/s41598-020-76154-7","volume":"10","author":"SB Seo","year":"2020","unstructured":"Seo SB, Cho HK. Deep learning classification of early normal-tension glaucoma and glaucoma suspects using Bruch\u2019s membrane opening-minimum rim width and RNFL. Sci Rep. 2020;10:19042.","journal-title":"Sci Rep"},{"key":"2730_CR16","unstructured":"Tan M, Le QV. Efficientnet: Rethinking model scaling for convolutional neural networks. 2019 URL: https:\/\/arxiv.org\/abs\/1905.11946."},{"key":"2730_CR17","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li LJ, Li\u00a0K, Fei-Fei L. \"ImageNet: A large-scale hierarchical image database,\" 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009. pp. 248-255. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2730_CR18","unstructured":"Perez L, Wang, J.The Effectiveness of Data Augmentation in Image Classification using Deep Learning. 2017 URL: https:\/\/arxiv.org\/abs\/1712.04621."},{"key":"2730_CR19","unstructured":"Kingma DP, Ba J. Adam : A Method for Stochastic Optimization. International Conference on Learning Representations, 2014. arXiv:1412.6980."},{"key":"2730_CR20","unstructured":"Smith LN, A disciplined approach to neural network hyper-parameters : Part 1\u2014learning rate, batch size, momentum, and weight decay.arXiv e-prints, 2018: p.arXiv:1803.09820."},{"key":"2730_CR21","unstructured":"Huang G, Li Y, Pleiss G, Liu Z, Hopcroft JE, Weinberger KQ. Snapshot Ensembles: Train 1, get M for free. 2017. ArXiv, abs\/1704.00109."},{"issue":"19","key":"2730_CR22","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1001\/jama.2013.5099","volume":"309","author":"H Hollands","year":"2013","unstructured":"Hollands H, Johnson D, Hollands S, Simel DL, Jinapriya D, Sharma S. Do findings on routine examination identify patients at risk for primary open-angle glaucoma? the rational clinical examination systematic review. JAMA. 2013;309(19):2035\u201342.","journal-title":"JAMA"},{"issue":"10","key":"2730_CR23","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1016\/j.ophtha.2011.03.012","volume":"118","author":"MW Marcus","year":"2011","unstructured":"Marcus MW, de Vries MM, Junoy Montolio FG, Jansonius NM. Myopia as a risk factor for open-angle glaucoma: a systematic review and meta-analysis. Ophthalmology. 2011;118(10):1989-1994.e2.","journal-title":"Ophthalmology"},{"key":"2730_CR24","first-page":"62417","volume":"7","author":"N Zhang","year":"2021","unstructured":"Zhang N, Wang J, Chen B, Li Y, Jiang B. Prevalence of primary angle closure glaucoma in the last 20 years: a meta-analysis and systematic review. Front Med (Lausanne). 2021;7:62417.","journal-title":"Front Med (Lausanne)"},{"key":"2730_CR25","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.cmpb.2015.10.010","volume":"124","author":"A Singh","year":"2016","unstructured":"Singh A, Dutta MK, Partha Sarathi M, Uher V, Burget R. Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image. Comput Methods Programs Biomed. 2016;124:108\u201320.","journal-title":"Comput Methods Programs Biomed"},{"key":"2730_CR26","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1097\/IJG.0000000000000354","volume":"25","author":"L Chakrabarty","year":"2016","unstructured":"Chakrabarty L, Joshi GD, Chakravarty A, Raman GV, Krishnadas SR, Sivaswamy J. Automated detection of glaucoma from topographic features of the optic nerve head in color fundus photographs. J Glaucoma. 2016;25:590\u20137.","journal-title":"J Glaucoma"},{"key":"2730_CR27","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.cmpb.2015.08.002","volume":"122","author":"A Issac","year":"2015","unstructured":"Issac A, Partha Sarathi M, Dutta MK. An adaptive threshold based image processing technique for improved glaucoma detection and classification. Comput Methods Programs Biomed. 2015;122:229\u201344.","journal-title":"Comput Methods Programs Biomed"},{"issue":"1","key":"2730_CR28","doi-asserted-by":"publisher","first-page":"16685","DOI":"10.1038\/s41598-018-35044-9","volume":"8","author":"M Christopher","year":"2018","unstructured":"Christopher M, Belghlith A, Bowd C, Proudfoot JA, Goldbaum MH, Weinreb RN, et al. Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci Rep. 2018;8(1):16685.","journal-title":"Sci Rep"},{"issue":"1","key":"2730_CR29","doi-asserted-by":"publisher","first-page":"3687","DOI":"10.1038\/s41598-020-80839-4","volume":"11","author":"K Ishii","year":"2021","unstructured":"Ishii K, Asaoka R, Omoto T, Mitaki S, Fujino Y, Murata H, et al. Predicting intraocular pressure using systemic variables or fundus photography with deep learning in a health examination cohort. Sci Rep. 2021;11(1):3687. https:\/\/doi.org\/10.1038\/s41598-020-80839-4.","journal-title":"Sci Rep"}],"container-title":["BMC Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12886-022-02730-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12886-022-02730-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12886-022-02730-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T11:04:48Z","timestamp":1670843088000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcophthalmol.biomedcentral.com\/articles\/10.1186\/s12886-022-02730-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,12]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["2730"],"URL":"https:\/\/doi.org\/10.1186\/s12886-022-02730-2","relation":{},"ISSN":["1471-2415"],"issn-type":[{"value":"1471-2415","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,12]]},"assertion":[{"value":"17 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No animal is involved in this study. The study was approved by the Institutional Review Board of Chang Gung Memorial Hospital, Linkou (No.201801801B0C601) and adhered to the tenets of the Declaration of Helsinki. Inform consent was waived by by the Institutional Review Board of Chang Gung Memorial Hospital, Linkou, due to its retrospective entity.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"483"}}