{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T14:51:10Z","timestamp":1785768670365,"version":"3.56.0"},"reference-count":14,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T00:00:00Z","timestamp":1664755200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000646","name":"Japan Society for the Promotion of Science London","doi-asserted-by":"publisher","award":["JP22K16936"],"award-info":[{"award-number":["JP22K16936"]}],"id":[{"id":"10.13039\/501100000646","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Cholesteatoma is a progressive middle ear disease that can only be treated surgically but with a high recurrence rate. Depending on the extent of the disease, a surgical approach, such as microsurgery with a retroarticular incision or transcanal endoscopic surgery, is performed. However, the current examination cannot sufficiently predict the progression before surgery, and changes in approach may be made during the surgery. Large amounts of data are typically required to train deep neural network models; however, the prevalence of cholesteatomas is low (1-in-25, 000). Developing analysis methods that improve the accuracy with such a small number of samples is an important issue for medical artificial intelligence (AI) research. This paper presents an AI-based system to automatically detect mastoid extensions using CT. This retrospective study included 164 patients (80 with mastoid extension and 84 without mastoid extension) who underwent surgery. This study adopted a relatively lightweight neural network model called MobileNetV2 to learn and predict the CT images of 164 patients. The training was performed with eight divided groups for cross-validation and was performed 24 times with each of the eight groups to verify accuracy fluctuations caused by randomly augmented learning. An evaluation was performed by each of the 24 single-trained models, and 24 sets of ensemble predictions with 23 models for 100% original size images and 400% zoomed images. Fifteen otolaryngologists diagnosed the images and compared the results. The average accuracy of predicting 400% zoomed images using ensemble prediction model was 81.14% (sensitivity = 84.95%, specificity = 77.33%). The average accuracy of the otolaryngologists was 73.41% (sensitivity, 83.17%; specificity, 64.13%), which was not affected by their clinical experiences. Noteworthily, despite the small number of cases, we were able to create a highly accurate AI. These findings represent an important first step in the automatic diagnosis of the cholesteatoma extension.<\/jats:p>","DOI":"10.1371\/journal.pone.0273915","type":"journal-article","created":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T17:27:58Z","timestamp":1664818078000},"page":"e0273915","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":27,"title":["Preoperative prediction by artificial intelligence for mastoid extension in pars flaccida cholesteatoma using temporal bone high-resolution computed tomography: A retrospective study"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7286-2326","authenticated-orcid":true,"given":"Masahiro","family":"Takahashi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katsuhiko","family":"Noda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaname","family":"Yoshida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keisuke","family":"Tsuchida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryosuke","family":"Yui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takara","family":"Nakazawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sho","family":"Kurihara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akira","family":"Baba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0947-6526","authenticated-orcid":true,"given":"Masaomi","family":"Motegi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuhisa","family":"Yamamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yutaka","family":"Yamamoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroya","family":"Ojiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiromi","family":"Kojima","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,10,3]]},"reference":[{"key":"pone.0273915.ref001","first-page":"289","article-title":"The 10-year disease-free rate of attic cholesteatoma based on a new staging system.","volume":"7","author":"M Hashimoto-Ikehara","year":"2011","journal-title":"J Int Adv Otol"},{"issue":"1","key":"pone.0273915.ref002","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1097\/MAO.0b013e3182a446bc","article-title":"Extension of indications for transcanal endoscopic ear surgery using an ultrasonic bone curette for cholesteatomas","volume":"35","author":"S Kakehata","year":"2014","journal-title":"Otol Neurotol"},{"issue":"4","key":"pone.0273915.ref003","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s00405-020-06594-4","article-title":"Transcanal endoscopic approach for pars flaccida cholesteatoma using a 70-degree angled endoscope.","volume":"278","author":"M Takahashi","year":"2021","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"pone.0273915.ref004","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1016\/B978-0-323-05355-6.00018-5","volume-title":"Head and Neck Imaging","author":"JD HM Swartz","year":"2011","edition":"5"},{"issue":"4","key":"pone.0273915.ref005","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1097\/MAO.0000000000001353","article-title":"A Meta-Analysis on the Diagnostic Performance of Non-Echoplanar Diffusion-Weighted Imaging in Detecting Middle Ear Cholesteatoma: 10 Years On.","volume":"38","author":"RK Lingam","year":"2017","journal-title":"Otol Neurotol"},{"issue":"3","key":"pone.0273915.ref006","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1111\/coa.12762","article-title":"Diffusion-weighted magnetic resonance imaging for residual and recurrent cholesteatoma: a systematic review and meta-analysis.","volume":"42","author":"J Muzaffar","year":"2017","journal-title":"Clin Otolaryngol"},{"issue":"5","key":"pone.0273915.ref007","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1016\/j.anl.2021.01.010","article-title":"Non-echoplanar diffusion weighed imaging and T1-weighted imaging for cholesteatoma mastoid extension.","volume":"48","author":"A Baba","year":"2021","journal-title":"Auris Nasus Larynx.Oct"},{"key":"pone.0273915.ref008","author":"OECD Indicators","year":"2021","journal-title":"Health at a Glance"},{"issue":"3","key":"pone.0273915.ref009","doi-asserted-by":"crossref","first-page":"e0248526","DOI":"10.1371\/journal.pone.0248526","article-title":"Automated system for diagnosing endometrial cancer by adopting deep-learning technology in hysteroscopy","volume":"16","author":"Y Takahashi","year":"2021","journal-title":"PLoS One"},{"issue":"6","key":"pone.0273915.ref010","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.amjoto.2017.06.007","article-title":"Temporal bone computed tomography findings associated with feasibility of endoscopic ear surgery","volume":"38","author":"D Abdul-Aziz","year":"2017","journal-title":"Am J Otolaryngol"},{"issue":"1","key":"pone.0273915.ref011","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1017\/S0022215115002753","article-title":"Interpreting pre-operative mastoid computed tomography images: comparison between operating surgeon, radiologist and operative findings.","volume":"130","author":"K Badran","year":"2016","journal-title":"J Laryngol Otol"},{"key":"pone.0273915.ref012","doi-asserted-by":"crossref","first-page":"328","DOI":"10.12659\/PJR.894155","article-title":"Computed Tomography Staging of Middle Ear Cholesteatoma.","volume":"80","author":"AA Razek","year":"2015","journal-title":"Pol J Radiol."},{"issue":"4","key":"pone.0273915.ref013","doi-asserted-by":"crossref","first-page":"609","DOI":"10.1016\/j.anl.2020.11.014","article-title":"Preoperative predictive criteria for mastoid extension in pars accida cholesteatoma in assessments using temporal bone high-resolution computed tomography.","volume":"48","author":"A Baba","year":"2021","journal-title":"Auris Nasus Larynx"},{"issue":"5","key":"pone.0273915.ref014","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1038\/s41563-019-0345-0","article-title":"How to develop machine learning models for healthcare.","volume":"18","author":"PC Chen","year":"2019","journal-title":"Nat Mater."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0273915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T17:28:16Z","timestamp":1664818096000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0273915"}},"subtitle":[],"editor":[{"given":"Rafael da Costa","family":"Monsanto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,10,3]]},"references-count":14,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,10,3]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0273915","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,3]]}}}