{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T14:13:25Z","timestamp":1793888005838,"version":"4.8.0"},"reference-count":16,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Otolaryngology - Head &amp; Neck Surgery"],"published-print":{"date-parts":[[2019,1]]},"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p> Otologic diseases are often difficult to diagnose accurately for primary care providers. Deep learning methods have been applied with great success in many areas of medicine, often outperforming well trained human observers. The aim of this work was to develop and evaluate an automatic software prototype to identify otologic abnormalities using a deep convolutional neural network. <\/jats:p><\/jats:sec><jats:sec><jats:title>Material and methods<\/jats:title><jats:p> A database of 734 unique otoscopic images of various ear pathologies, including 63 cerumen impactions, 120 tympanostomy tubes, and 346 normal tympanic membranes were acquired. 80% of the images were used for the training of a convolutional neural network and the remaining 20% were used for algorithm validation. Image augmentation was employed on the training dataset to increase the number of training images. The general network architecture consisted of three convolutional layers plus batch normalization and dropout layers to avoid over fitting. <\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p> The validation based on 45 datasets not used for model training revealed that the proposed deep convolutional neural network is capable of identifying and differentiating between normal tympanic membranes, tympanostomy tubes, and cerumen impactions with an overall accuracy of 84.4%. <\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p> Our study shows that deep convolutional neural networks hold immense potential as a diagnostic adjunct for otologic disease management. <\/jats:p><\/jats:sec>","DOI":"10.1186\/s40463-019-0389-9","type":"journal-article","created":{"date-parts":[[2019,11,26]],"date-time":"2019-11-26T17:03:29Z","timestamp":1574787809000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":39,"title":["Building an Otoscopic screening prototype tool using deep learning"],"prefix":"10.1177","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4734-0980","authenticated-orcid":false,"given":"Devon","family":"Livingstone","sequence":"first","affiliation":[{"name":"Division of Otolaryngology \u2013 Head and Neck Surgery, Department of Surgery, University of Calgary, 7th floor, 4448 Front Street SE, T3M 1M4, Calgary, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aron S.","family":"Talai","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justin","family":"Chau","sequence":"additional","affiliation":[{"name":"Division of Otolaryngology \u2013 Head and Neck Surgery, Department of Surgery, University of Calgary, 7th floor, 4448 Front Street SE, T3M 1M4, Calgary, Alberta, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nils D.","family":"Forkert","sequence":"additional","affiliation":[{"name":"Department of Radiology, Hotchkiss Brain Institute, University of Calgary, Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2019,1,1]]},"reference":[{"key":"bibr1-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2008.01.030"},{"key":"bibr2-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1111\/j.1651-2227.2005.tb01912.x"},{"key":"bibr3-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2007.09.010"},{"key":"bibr4-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2004.10.013"},{"key":"bibr5-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1001\/archpedi.155.10.1137"},{"key":"bibr6-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.03.025"},{"key":"bibr7-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2016.02.017"},{"key":"bibr8-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"bibr9-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1007\/s11605-017-3518-7"},{"key":"bibr10-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2017.12.023"},{"key":"bibr11-s40463-019-0389-9","volume-title":"Autoscope: automated otoscopy image analysis to diagnose ear pathology and use of clinically motivated eardrum features: SPIE","author":"Senaras C","year":"2017"},{"key":"bibr12-s40463-019-0389-9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2018.03.521"},{"key":"bibr13-s40463-019-0389-9","volume-title":"Automated dermatological diagnosis: hype or reality? J invest Dermatol","author":"Navarrete-Dechent C","year":"2018"},{"key":"bibr14-s40463-019-0389-9","unstructured":"Cellscope. 2018 [Available from: https:\/\/www.cellscope.com. Accessed Jan 2019."},{"key":"bibr15-s40463-019-0389-9","unstructured":"Smith LN. A disciplined approach to neural network hyper-parameters: part 1 \u2013 learning rate, batch size, momentum, and weight decay. US Naval Research Laboratory Tehnical Report. 2018;5510026."},{"key":"bibr16-s40463-019-0389-9","unstructured":"ENTiD. Online Open Access Portal; 2019. Accessible at www.entid.ca. Accessed Jan 2019."}],"container-title":["Journal of Otolaryngology - Head &amp; Neck Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1186\/s40463-019-0389-9","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40463-019-0389-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1186\/s40463-019-0389-9","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40463-019-0389-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1186\/s40463-019-0389-9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T08:27:20Z","timestamp":1741681640000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1186\/s40463-019-0389-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1]]},"references-count":16,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,1]]}},"alternative-id":["10.1186\/s40463-019-0389-9"],"URL":"https:\/\/doi.org\/10.1186\/s40463-019-0389-9","relation":{},"ISSN":["1916-0216","1916-0216"],"issn-type":[{"value":"1916-0216","type":"print"},{"value":"1916-0216","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1]]},"article-number":"66"}}