{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:34:56Z","timestamp":1780450496533,"version":"3.54.1"},"reference-count":24,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T00:00:00Z","timestamp":1678665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Kowa Research Institute"},{"DOI":"10.13039\/100015993","name":"Kowa Company","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015993","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Kowa Research Institute"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Purpose<\/jats:title>\n<jats:p>Dry eye disease affects hundreds of millions of people worldwide and is one of the most common causes for visits to eye care practitioners. The fluorescein tear breakup time test is currently widely used to diagnose dry eye disease, but it is an invasive and subjective method, thus resulting in variability in diagnostic results. This study aimed to develop an objective method to detect tear breakup using the convolutional neural networks on the tear film images taken by the non-invasive device KOWA DR-1\u03b1.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>The image classification models for detecting characteristics of tear film images were constructed using transfer learning of the pre-trained ResNet50 model. The models were trained using a total of 9,089 image patches extracted from video data of 350 eyes of 178 subjects taken by the KOWA DR-1\u03b1. The trained models were evaluated based on the classification results for each class and overall accuracy of the test data in the six-fold cross validation. The performance of the tear breakup detection method using the models was evaluated by calculating the area under curve (AUC) of receiver operating characteristic, sensitivity, and specificity using the detection results of 13,471 frame images with breakup presence\/absence labels.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>The performance of the trained models was 92.3%, 83.4%, and 95.2% for accuracy, sensitivity, and specificity, respectively in classifying the test data into the tear breakup or non-breakup group. Our method using the trained models achieved an AUC of 0.898, a sensitivity of 84.3%, and a specificity of 83.3% in detecting tear breakup for a frame image.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>We were able to develop a method to detect tear breakup on images taken by the KOWA DR-1\u03b1. This method could be applied to the clinical use of non-invasive and objective tear breakup time test.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0282973","type":"journal-article","created":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T17:26:00Z","timestamp":1678728360000},"page":"e0282973","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Non-invasive and objective tear film breakup detection on interference color images using convolutional neural networks"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1964-5496","authenticated-orcid":true,"given":"Yasushi","family":"Kikukawa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin","family":"Tanaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takuya","family":"Kosugi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen C.","family":"Pflugfelder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,3,13]]},"reference":[{"issue":"3","key":"pone.0282973.ref001","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.jtos.2017.05.008","article-title":"TFOS DEWS II Definition and Classification Report","volume":"15","author":"JP Craig","year":"2017","journal-title":"Ocul Surf"},{"key":"pone.0282973.ref002","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.ajo.2017.06.033","article-title":"Prevalence of Diagnosed Dry Eye Disease in the United States Among Adults Aged 18 Years and Older","volume":"182","author":"KF Farrand","year":"2017","journal-title":"Am J Ophthalmol"},{"key":"pone.0282973.ref003","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.ajo.2019.01.026","article-title":"Estimated Prevalence and Incidence of Dry Eye Disease Based on Coding Analysis of a Large, All-age United States Health Care System","volume":"202","author":"R Dana","year":"2019","journal-title":"Am J Ophthalmol"},{"issue":"9","key":"pone.0282973.ref004","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1097\/OPX.0b013e3182231b1a","article-title":"Knowledge and use of tear film evaluation tests by spanish practitioners","volume":"88","author":"G Cardona","year":"2011","journal-title":"Optom Vis Sci"},{"issue":"12","key":"pone.0282973.ref005","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1097\/OPX.0000000000000087","article-title":"An evidence-based analysis of Australian optometrists\u2019 dry eye practices","volume":"90","author":"LE Downie","year":"2013","journal-title":"Optom Vis Sci"},{"issue":"6","key":"pone.0282973.ref006","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1097\/01.ico.0000611384.81547.8d","article-title":"Current patterns in the use of diagnostic tests in dry eye evaluation","volume":"27","author":"J Smith","year":"2008","journal-title":"Cornea"},{"issue":"3","key":"pone.0282973.ref007","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/j.jtos.2017.05.001","article-title":"TFOS DEWS II Diagnostic Methodology report","volume":"15","author":"JS Wolffsohn","year":"2017","journal-title":"Ocul Surf"},{"issue":"1","key":"pone.0282973.ref008","doi-asserted-by":"crossref","first-page":"9","DOI":"10.3109\/02713688508999961","article-title":"Effect of fluorescein instillation on the pre-corneal tear film stability","volume":"4","author":"LS Mengher","year":"1985","journal-title":"Curr Eye Res"},{"issue":"3","key":"pone.0282973.ref009","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.clae.2017.01.004","article-title":"Minimising instilled volume reduces the impact of fluorescein on clinical measurements of tear film stability","volume":"40","author":"JK Mooi","year":"2017","journal-title":"Cont Lens Anterior Eye"},{"key":"pone.0282973.ref010","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1038\/s41746-018-0040-6","article-title":"Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices","volume":"1","author":"MD Abr\u00e0moff","year":"2018","journal-title":"NPJ Digit Med"},{"key":"pone.0282973.ref011","doi-asserted-by":"crossref","first-page":"4281","DOI":"10.2147\/OPTH.S321764","article-title":"Comparison of Autonomous AS-OCT Deep Learning Algorithm and Clinical Dry Eye Tests in Diagnosis of Dry Eye Disease","volume":"15","author":"C Chase","year":"2021","journal-title":"Clin Ophthalmol"},{"key":"pone.0282973.ref012","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1038\/s41746-020-00329-9","article-title":"Development and clinical deployment of a smartphone-based visual field deep learning system for glaucoma detection","volume":"3","author":"F Li","year":"2020","journal-title":"NPJ Digit Med"},{"issue":"11","key":"pone.0282973.ref013","doi-asserted-by":"crossref","first-page":"714","DOI":"10.21037\/atm-20-976","article-title":"Application of artificial intelligence in anterior segment ophthalmic diseases: diversity and standardization","volume":"8","author":"X Wu","year":"2020","journal-title":"Ann Transl Med"},{"key":"pone.0282973.ref014","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.jtos.2021.11.004","article-title":"Artificial intelligence in dry eye disease","volume":"23","author":"AM Stor\u00e5s","year":"2022","journal-title":"Ocul Surf"},{"key":"pone.0282973.ref015","first-page":"1","article-title":"Tear Film Break-Up Time Measurement Using Deep Convolutional Neural Networks for Screening Dry Eye Disease","author":"TY Su","year":"2018","journal-title":"IEEE Sensors Journal"},{"issue":"2","key":"pone.0282973.ref016","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/S1542-0124(12)70083-6","article-title":"Methodologies to diagnose and monitor dry eye disease: report of the Diagnostic Methodology Subcommittee of the International Dry Eye WorkShop (2007)","volume":"5","year":"2007","journal-title":"Ocul Surf"},{"issue":"21","key":"pone.0282973.ref017","doi-asserted-by":"crossref","first-page":"10384","DOI":"10.3390\/app112110384","article-title":"Advances in the Noninvasive Diagnosis of Dry Eye Disease","volume":"11","author":"LD Cello","year":"2021","journal-title":"Appl. Sci"},{"issue":"9","key":"pone.0282973.ref018","first-page":"4860","article-title":"Automated classification of dry eye type analyzing interfering fringe color images of tear film using machine learning technologies","volume":"59","author":"K Yabusaki","year":"2018","journal-title":"Investigative Ophthalmology & Visual Science"},{"issue":"2","key":"pone.0282973.ref019","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s10384-018-00645-4","article-title":"Tear-film-oriented diagnosis for dry eye","volume":"63","author":"N Yokoi","year":"2019","journal-title":"Jpn J Ophthalmol"},{"key":"pone.0282973.ref020","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016:770\u20138.","DOI":"10.1109\/CVPR.2016.90"},{"key":"pone.0282973.ref021","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"O Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"pone.0282973.ref022","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J, editors. Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks. 2014 IEEE Conference on Computer Vision and Pattern Recognition; 2014 23\u201328 June 2014.","DOI":"10.1109\/CVPR.2014.222"},{"issue":"14","key":"pone.0282973.ref023","doi-asserted-by":"crossref","first-page":"DES13","DOI":"10.1167\/iovs.17-23700","article-title":"Tear Film-Oriented Diagnosis and Tear Film-Oriented Therapy for Dry Eye Based on Tear Film Dynamics","volume":"59","author":"N Yokoi","year":"2018","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0282973.ref024","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","volume":"25","author":"A Krizhevsky","year":"2012","journal-title":"Neural Information Processing Systems"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0282973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,13]],"date-time":"2023-03-13T17:26:32Z","timestamp":1678728392000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0282973"}},"subtitle":[],"editor":[{"given":"Surbhi","family":"Bhatia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,3,13]]},"references-count":24,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0282973","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,13]]}}}