{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T00:34:30Z","timestamp":1793406870025,"version":"4.5.0"},"reference-count":30,"publisher":"BMJ","issue":"9","content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2019,8,30]]},"published-print":{"date-parts":[[2019,9]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>A diagnostic accuracy study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>A single-centre study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Participants<\/jats:title>\n                    <jats:p>A total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main outcome measures<\/jats:title>\n                    <jats:p>The diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Deep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Deep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical trial registration number<\/jats:title>\n                    <jats:p>000034587.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2019-031313","type":"journal-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T14:05:39Z","timestamp":1569593139000},"page":"e031313","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":126,"title":["Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study"],"prefix":"10.1136","volume":"9","author":[{"given":"Kazutaka","family":"Kamiya","sequence":"first","affiliation":[{"name":"Visual Phisiology, School of Allied Health Sciences, Kitasato University, Sagamihara, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuji","family":"Ayatsuka","sequence":"additional","affiliation":[{"name":"Cresco Ltd, Technology Laboratory, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yudai","family":"Kato","sequence":"additional","affiliation":[{"name":"Cresco Ltd, Technology Laboratory, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fusako","family":"Fujimura","sequence":"additional","affiliation":[{"name":"Visual Phisiology, School of Allied Health Sciences, Kitasato University, Sagamihara, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masahide","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kitasato University, Sagamihara, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nobuyuki","family":"Shoji","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, School of Medicine, Kitasato University, Sagamihara, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yosai","family":"Mori","sequence":"additional","affiliation":[{"name":"Miyata Eye Hospital, Department of Ophthalmology, Miyakonojo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazunori","family":"Miyata","sequence":"additional","affiliation":[{"name":"Miyata Eye Hospital, Department of Ophthalmology, Miyakonojo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2019,9,27]]},"reference":[{"key":"2025121403093925000_9.9.e031313.1","doi-asserted-by":"publisher","DOI":"10.1016\/ S0893-6080(03)00115-1"},{"key":"2025121403093925000_9.9.e031313.2","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1109\/TNN.2005.845144","article-title":"Efficient training algorithms for a class of shunting inhibitory convolutional neural networks","volume":"16","author":"Tivive","year":"2005","journal-title":"IEEE Trans Neural Netw"},{"key":"2025121403093925000_9.9.e031313.3","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.1109\/TNN.2006.879766","article-title":"A convolutional neural network approach for objective video quality assessment","volume":"17","author":"Le Callet","year":"2006","journal-title":"IEEE Trans Neural Netw"},{"key":"2025121403093925000_9.9.e031313.4","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"2025121403093925000_9.9.e031313.5","doi-asserted-by":"crossref","first-page":"2366","DOI":"10.1001\/jama.2016.17563","article-title":"Artificial intelligence with deep learning technology looks into diabetic retinopathy screening","volume":"316","author":"Wong","year":"2016","journal-title":"JAMA"},{"key":"2025121403093925000_9.9.e031313.6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2017.02.008"},{"key":"2025121403093925000_9.9.e031313.7","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.03-0343"},{"key":"2025121403093925000_9.9.e031313.8","first-page":"715","article-title":"Glaucoma detection based on deep convolutional neural network","volume":"2015","author":"Xiangyu","year":"2015","journal-title":"Conf Proc IEEE Eng Med Biol Soc"},{"key":"2025121403093925000_9.9.e031313.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2016.05.029"},{"key":"2025121403093925000_9.9.e031313.10","first-page":"2749","article-title":"Automated keratoconus screening with corneal topography analysis","volume":"35","author":"Maeda","year":"1994","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2025121403093925000_9.9.e031313.11","first-page":"1327","article-title":"Neural network classification of corneal topography. Preliminary demonstration","volume":"36","author":"Maeda","year":"1995","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2025121403093925000_9.9.e031313.12","first-page":"2290","article-title":"Current keratoconus detection methods compared with a neural network approach","volume":"38","author":"Smolek","year":"1997","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"2025121403093925000_9.9.e031313.13","doi-asserted-by":"publisher","DOI":"10.1016\/S1532-0464(02)00513-0"},{"key":"2025121403093925000_9.9.e031313.14","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1590\/S1807-59322010001200002","article-title":"Evaluation of machine learning classifiers in keratoconus detection from Orbscan II examinations","volume":"65","author":"Souza","year":"2010","journal-title":"Clinics"},{"key":"2025121403093925000_9.9.e031313.15","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1016\/j.ophtha.2012.06.005","article-title":"Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data","volume":"119","author":"Arbelaez","year":"2012","journal-title":"Ophthalmology"},{"key":"2025121403093925000_9.9.e031313.16","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.ajo.2013.03.034","article-title":"Detection of subclinical keratoconus using an automated decision tree classification","volume":"156","author":"Smadja","year":"2013","journal-title":"Am J Ophthalmol"},{"key":"2025121403093925000_9.9.e031313.17","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.jcrs.2015.09.020","article-title":"Accuracy of machine learning classifiers using bilateral data from a scheimpflug camera for identifying eyes with preclinical signs of keratoconus","volume":"42","author":"Kov\u00e1cs","year":"2016","journal-title":"J Cataract Refract Surg"},{"key":"2025121403093925000_9.9.e031313.18","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1097\/ICO.0000000000000834","article-title":"Evaluation of a Machine-Learning classifier for keratoconus detection based on scheimpflug tomography","volume":"35","author":"Ruiz Hidalgo","year":"2016","journal-title":"Cornea"},{"key":"2025121403093925000_9.9.e031313.19","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1097\/ICO.0000000000001194","article-title":"Validation of an objective keratoconus detection system implemented in a scheimpflug Tomographer and comparison with other methods","volume":"36","author":"Ruiz Hidalgo","year":"2017","journal-title":"Cornea"},{"key":"2025121403093925000_9.9.e031313.20","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0205998","article-title":"Keratoconus severity identification using unsupervised machine learning","volume":"13","author":"Yousefi","year":"2018","journal-title":"PLoS One"},{"key":"2025121403093925000_9.9.e031313.21","doi-asserted-by":"crossref","first-page":"622","DOI":"10.1364\/BOE.10.000622","article-title":"CorneaNet: fast segmentation of cornea OCT scans of healthy and keratoconic eyes using deep learning","volume":"10","author":"Dos Santos","year":"2019","journal-title":"Biomed Opt Express"},{"key":"2025121403093925000_9.9.e031313.22","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.compbiomed.2019.04.024","article-title":"Computer aided diagnosis for suspect keratoconus detection","volume":"109","author":"Issarti","year":"2019","journal-title":"Comput Biol Med"},{"key":"2025121403093925000_9.9.e031313.23","doi-asserted-by":"publisher","DOI":"10.1016\/S0039-6257(97)00119-7"},{"key":"2025121403093925000_9.9.e031313.24","doi-asserted-by":"publisher","DOI":"10.3928\/1081597X-20090401-07"},{"key":"2025121403093925000_9.9.e031313.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrs.2006.02.060"},{"key":"2025121403093925000_9.9.e031313.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2006.03.046"},{"key":"2025121403093925000_9.9.e031313.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2008.02.020"},{"key":"2025121403093925000_9.9.e031313.28","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1097\/ICO.0B013E31823D1EE0","article-title":"Correlation of corneal elevation with severity of keratoconus by means of anterior and posterior topographic analysis","volume":"31","author":"Ishii","year":"2012","journal-title":"Cornea"},{"key":"2025121403093925000_9.9.e031313.29","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2013-304132"},{"key":"2025121403093925000_9.9.e031313.30","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1097\/ICO.0b013e31823f098c","article-title":"Repeatability of pachymetric mapping using Fourier domain optical coherence tomography in corneas with opacities","volume":"31","author":"Samy El Gendy","year":"2012","journal-title":"Cornea"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2019-031313","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T11:09:48Z","timestamp":1765710588000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2019-031313"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9]]},"references-count":30,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2019,9,27]]},"published-print":{"date-parts":[[2019,9]]}},"alternative-id":["10.1136\/bmjopen-2019-031313"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2019-031313","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9]]}}}