{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T07:44:08Z","timestamp":1782373448622,"version":"3.54.5"},"reference-count":32,"publisher":"Cambridge University Press (CUP)","issue":"4","license":[{"start":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T00:00:00Z","timestamp":1585785600000},"content-version":"unspecified","delay-in-days":1,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Laryngol. Otol."],"published-print":{"date-parts":[[2020,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec id=\"S0022215120000717_sec_a1\"><jats:title>Objective<\/jats:title><jats:p>To explore the feasibility of constructing a proof-of-concept artificial intelligence algorithm to detect tympanic membrane perforations, for future application in under-resourced rural settings.<\/jats:p><\/jats:sec><jats:sec id=\"S0022215120000717_sec_a2\" sec-type=\"methods\"><jats:title>Methods<\/jats:title><jats:p>A retrospective review was conducted of otoscopic images analysed using transfer learning with Google's Inception-V3 convolutional neural network architecture. The \u2018gold standard\u2019 \u2018ground truth\u2019 was defined by otolaryngologists. Perforation size was categorised as less than one-third (small), one-third to two-thirds (medium), or more than two-thirds (large) of the total tympanic membrane diameter.<\/jats:p><\/jats:sec><jats:sec id=\"S0022215120000717_sec_a3\" sec-type=\"results\"><jats:title>Results<\/jats:title><jats:p>A total of 233 tympanic membrane images were used (183 for training, 50 for testing). The algorithm correctly identified intact and perforated tympanic membranes (overall accuracy = 76.0 per cent, 95 per cent confidence interval = 62.1\u201386.0 per cent); the area under the curve was 0.867 (95 per cent confidence interval = 0.771\u20130.963).<\/jats:p><\/jats:sec><jats:sec id=\"S0022215120000717_sec_a4\" sec-type=\"conclusions\"><jats:title>Conclusion<\/jats:title><jats:p>A proof-of-concept image-classification artificial intelligence algorithm can be used to detect tympanic membrane perforations and, with further development, may prove to be a valuable tool for ear disease screening. Future endeavours are warranted to develop a point-of-care tool for healthcare workers in areas distant from otolaryngology.<\/jats:p><\/jats:sec>","DOI":"10.1017\/s0022215120000717","type":"journal-article","created":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T03:58:10Z","timestamp":1585799890000},"page":"311-315","source":"Crossref","is-referenced-by-count":29,"title":["Artificial intelligence to detect tympanic membrane perforations"],"prefix":"10.1017","volume":"134","author":[{"given":"A-R","family":"Habib","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R","family":"Sacks","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2020,4,2]]},"reference":[{"key":"S0022215120000717_ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2016.02.017"},{"key":"S0022215120000717_ref21","doi-asserted-by":"publisher","DOI":"10.1089\/tmj.2010.0045"},{"key":"S0022215120000717_ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"S0022215120000717_ref32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0138369"},{"key":"S0022215120000717_ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2008.01.030"},{"key":"S0022215120000717_ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2018.09.002"},{"key":"S0022215120000717_ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0194599815624407"},{"key":"S0022215120000717_ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.vaccine.2006.09.006"},{"key":"S0022215120000717_ref9","doi-asserted-by":"publisher","DOI":"10.1002\/alr.22196"},{"key":"S0022215120000717_ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0188532"},{"key":"S0022215120000717_ref14","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2431-5-27"},{"key":"S0022215120000717_ref16","doi-asserted-by":"publisher","DOI":"10.5694\/mja18.00249"},{"key":"S0022215120000717_ref29","volume-title":"Otitis Media Analysis: An Automated Feature Extraction and Image Classification System","author":"Kasher","year":"2018"},{"key":"S0022215120000717_ref10","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.22.6.060503"},{"key":"S0022215120000717_ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S1473-3099(17)30131-7"},{"key":"S0022215120000717_ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsurg.2015.07.011"},{"key":"S0022215120000717_ref11","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.8.004579"},{"key":"S0022215120000717_ref15","doi-asserted-by":"publisher","DOI":"10.1046\/j.1440-1754.2003.00210.x"},{"key":"S0022215120000717_ref1","doi-asserted-by":"publisher","DOI":"10.1136\/svn-2017-000101"},{"key":"S0022215120000717_ref30","doi-asserted-by":"publisher","DOI":"10.1136\/bmjgh-2018-000798"},{"key":"S0022215120000717_ref6","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017162326"},{"key":"S0022215120000717_ref24","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"S0022215120000717_ref3","first-page":"1","article-title":"Self-supervised learning for dense depth estimation in monocular endoscopy","author":"Liu","year":"2018","journal-title":"ArXiv"},{"key":"S0022215120000717_ref23","unstructured":"23 GIMP: GNU Image Manipulation Program. In: https:\/\/www.gimp.org\/ [9 March 2020]"},{"key":"S0022215120000717_ref28","doi-asserted-by":"publisher","DOI":"10.1101\/515007"},{"key":"S0022215120000717_ref7","first-page":"1","article-title":"Deep learning for identifying metastatic breast cancer","author":"Wang","year":"2016","journal-title":"ArXiv"},{"key":"S0022215120000717_ref18","doi-asserted-by":"publisher","DOI":"10.1111\/j.1440-1754.2009.01532.x"},{"key":"S0022215120000717_ref22","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2013.281053"},{"key":"S0022215120000717_ref25","doi-asserted-by":"publisher","DOI":"10.1111\/j.1651-2227.2005.tb01912.x"},{"key":"S0022215120000717_ref17","volume-title":"2017 AMA Report Card on Indigenous Health: A National Strategic Approach to Ending Chronic Otitis Media and its Life Long Impacts in Indigenous Communities","year":"2017"},{"key":"S0022215120000717_ref13","doi-asserted-by":"publisher","DOI":"10.2471\/BLT.08.020408"},{"key":"S0022215120000717_ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2018.02.018"}],"container-title":["The Journal of Laryngology &amp; Otology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0022215120000717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,9]],"date-time":"2021-03-09T09:26:54Z","timestamp":1615282014000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0022215120000717\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["S0022215120000717"],"URL":"https:\/\/doi.org\/10.1017\/s0022215120000717","relation":{},"ISSN":["0022-2151","1748-5460"],"issn-type":[{"value":"0022-2151","type":"print"},{"value":"1748-5460","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4]]}}}