{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:01:36Z","timestamp":1787022096250,"version":"build-2736575974"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T00:00:00Z","timestamp":1645747200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Future Medicine 20*30 Project of the Samsung Medical Center","award":["SMX1210791"],"award-info":[{"award-number":["SMX1210791"]}]},{"name":"Bio & Medical Technology Development Program of the NRF funded by the Korean government","award":["NRF-2017M3A9E1064784"],"award-info":[{"award-number":["NRF-2017M3A9E1064784"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study aims to develop artificial intelligence (AI) system to automatically classify patients with maxillary sinus fungal ball (MFB), chronic rhinosinusitis (CRS), and healthy controls (HCs).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected 512 coronal image sets from ostiomeatal unit computed tomography (OMU CT) performed on subjects who visited a single tertiary hospital. These data included 254 MFB, 128 CRS, and 130 HC subjects and were used for training the proposed AI system. The AI system takes these 1024 sets of half CT images as input and classifies these as MFB, CRS, or HC. To optimize the classification performance, we adopted a 3-D convolutional neural network of ResNet 18. We also collected 64 coronal OMU CT image sets for external validation, including 26 MFB, 18 CRS, and 20 HCs from subjects from another referral hospital. Finally, the performance of the developed AI system was compared with that of the otolaryngology resident physicians.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Classification performance was evaluated using internal 5-fold cross-validation (818 training and 206 internal validation data) and external validation (128 data). The area under the receiver operating characteristic over the internal 5-fold cross-validation and the external validation was 0.96 \u00b10.006 and 0.97 \u00b10.006, respectively. The accuracy of the internal 5-fold cross-validation and the external validation was 87.5 \u00b12.3% and 88.4 \u00b13.1%, respectively. As a result of performing a classification test on external validation data from six otolaryngology resident physicians, the accuracy was obtained as 84.6 \u00b111.3%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This AI system is the first study to classify MFB, CRS, and HC using deep neural networks to the best of our knowledge. The proposed system is fully automatic but performs similarly to or better than otolaryngology resident physicians. Therefore, we believe that in regions where otolaryngology specialists are scarce, the proposed AI will perform sufficiently effective diagnosis on behalf of doctors.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0263125","type":"journal-article","created":{"date-parts":[[2022,2,25]],"date-time":"2022-02-25T14:02:56Z","timestamp":1645797776000},"page":"e0263125","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":29,"title":["Detection of maxillary sinus fungal ball via 3-D CNN-based artificial intelligence: Fully automated system and clinical validation"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6622-6545","authenticated-orcid":true,"given":"Kyung-Su","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byung Kil","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myung Jin","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Bin","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7722-5660","authenticated-orcid":true,"given":"Beak Hwan","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7456-849X","authenticated-orcid":true,"given":"Yong Gi","family":"Jung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,2,25]]},"reference":[{"key":"pone.0263125.ref001","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.amjoto.2015.08.002","article-title":"Cone beam CT paranasal sinuses versus standard multidetector and low dose multidetector CT studies","volume":"37","author":"J Al Abduwani","year":"2016","journal-title":"Am J Otolaryngol"},{"key":"pone.0263125.ref002","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.cmpb.2016.10.007","article-title":"Classification of CT brain images based on deep learning networks","volume":"138","author":"XW Gao","year":"2017","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0263125.ref003","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1017\/S0022215119002536","article-title":"An artificial intelligence algorithm that differentiates anterior ethmoidal artery location on sinus computed tomography scans","volume":"134","author":"J Huang","year":"2020","journal-title":"J Laryngol Otol"},{"key":"pone.0263125.ref004","doi-asserted-by":"crossref","first-page":"328","DOI":"10.1017\/S0022215120000444","article-title":"An artificial intelligence algorithm that identifies middle turbinate pneumatisation (concha bullosa) on sinus computed tomography scans","volume":"134","author":"P Parmar","year":"2020","journal-title":"J Laryngol Otol"},{"key":"pone.0263125.ref005","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1002\/alr.22196","article-title":"Automated classification of osteomeatal complex inflammation on computed tomography using convolutional neural networks","volume":"9","author":"NI Chowdhury","year":"2019","journal-title":"Int Forum Allergy Rhinol"},{"key":"pone.0263125.ref006","doi-asserted-by":"crossref","first-page":"e0219369","DOI":"10.1371\/journal.pone.0219369","article-title":"A CAD system for pulmonary nodule prediction based on deep three-dimensional convolutional neural networks and ensemble learning","volume":"14","author":"W Huang","year":"2019","journal-title":"PLoS One"},{"key":"pone.0263125.ref007","doi-asserted-by":"crossref","first-page":"157","DOI":"10.21053\/ceo.2019.00836","article-title":"Clinical Characteristics Other Than Intralesional Hyperdensity May Increase the Preoperative Diagnostic Accuracy of Maxillary Sinus Fungal Ball","volume":"13","author":"H Cha","year":"2020","journal-title":"Clin Exp Otorhinolaryngol"},{"key":"pone.0263125.ref008","unstructured":"Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. 2019. https:\/\/arxiv.org\/abs\/1905.11946."},{"key":"pone.0263125.ref009","first-page":"022022","article-title":"An overview of overfitting and its solutions","volume":"1168","author":"X. Ying","year":"2019","journal-title":"J Phys: Conf Ser"},{"key":"pone.0263125.ref010","volume-title":"Medical Imaging 2020: Computer-Aided Diagnosis","author":"T Uemura","year":"2020"},{"key":"pone.0263125.ref011","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Hillier C, Vijayanarasimhan S, et al. The kinetics human action video dataset. 2017. https:\/\/arxiv.org\/abs\/1705.06950."},{"key":"pone.0263125.ref012","doi-asserted-by":"crossref","first-page":"106885","DOI":"10.1016\/j.asoc.2020.106885","article-title":"The ensemble deep learning model for novel COVID-19 on CT images","volume":"98","author":"T Zhou","year":"2021","journal-title":"Appl Soft Comput"},{"key":"pone.0263125.ref013","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE international conference on computer vision. 2017:618\u201326.","DOI":"10.1109\/ICCV.2017.74"},{"key":"pone.0263125.ref014","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1016\/S0091-6749(97)70073-3","article-title":"Criteria for the diagnosis of sinus mycetoma","volume":"99","author":"RD deShazo","year":"1997","journal-title":"J Allergy Clin Immunol"},{"key":"pone.0263125.ref015","first-page":"227","article-title":"[CT imaging of fungal and nonfungal caseous sinusitis. A report of 50 cases]","volume":"81","author":"JJ Braun","year":"2000","journal-title":"J Radiol"},{"key":"pone.0263125.ref016","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1177\/000348948409300313","article-title":"Aspergillosis of the paranasal sinuses x-ray diagnosis, histopathology, and clinical aspects","volume":"93","author":"H Stammberger","year":"1984","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"pone.0263125.ref017","doi-asserted-by":"crossref","first-page":"18565","DOI":"10.1074\/jbc.R900014200","article-title":"Homeostatic and adaptive responses to zinc deficiency in Saccharomyces cerevisiae","volume":"284","author":"DJ Eide","year":"2009","journal-title":"J Biol Chem"},{"key":"pone.0263125.ref018","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1080\/13693780500235728","article-title":"Paranasal sinus fungus ball: epidemiology, clinical features and diagnosis. A retrospective analysis of 173 cases from a single medical center in France, 1989\u20132002","volume":"44","author":"X Dufour","year":"2006","journal-title":"Med Mycol"},{"key":"pone.0263125.ref019","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1258\/ar.2011.110021","article-title":"Radiologic characteristics of sinonasal fungus ball: an analysis of 119 cases","volume":"52","author":"YJ Seo","year":"2011","journal-title":"Acta Radiol"},{"key":"pone.0263125.ref020","doi-asserted-by":"crossref","first-page":"227","DOI":"10.2500\/105065800779954446","article-title":"Diagnostic accuracy in sinus fungus balls: CT scan and operative findings","volume":"14","author":"HJ Dhong","year":"2000","journal-title":"Am J Rhinol"},{"key":"pone.0263125.ref021","doi-asserted-by":"crossref","first-page":"731640","DOI":"10.1155\/2013\/731640","article-title":"Sinus fungus ball in the Japanese population: clinical and imaging characteristics of 104 cases","volume":"2013","author":"K Nomura","year":"2013","journal-title":"Int J Otolaryngol"},{"key":"pone.0263125.ref022","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1097\/00005537-199701000-00021","article-title":"Functional endoscopic sinus surgery and 109 mycetomas of paranasal sinuses","volume":"107","author":"JM Klossek","year":"1997","journal-title":"Laryngoscope"},{"key":"pone.0263125.ref023","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"key":"pone.0263125.ref024","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1097\/RLI.0000000000000503","article-title":"Deep Learning in Diagnosis of Maxillary Sinusitis Using Conventional Radiography","volume":"54","author":"Y Kim","year":"2019","journal-title":"Invest Radiol"},{"key":"pone.0263125.ref025","doi-asserted-by":"crossref","first-page":"942","DOI":"10.21037\/qims.2019.05.15","article-title":"Improvement diagnostic accuracy of sinusitis recognition in paranasal sinus X-ray using multiple deep learning models","volume":"9","author":"HG Kim","year":"2019","journal-title":"Quant Imaging Med Surg"},{"key":"pone.0263125.ref026","article-title":"Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs","volume":"11","author":"Y Jeon","year":"2021","journal-title":"Diagnostics (Basel)"},{"key":"pone.0263125.ref027","doi-asserted-by":"crossref","first-page":"800","DOI":"10.3390\/cancers11060800","article-title":"Machine-Learning-Based Prediction of Treatment Outcomes Using MR Imaging-Derived Quantitative Tumor Information in Patients with Sinonasal Squamous Cell Carcinomas: A Preliminary Study","volume":"11","author":"N Fujima","year":"2019","journal-title":"Cancers (Basel)"},{"key":"pone.0263125.ref028","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.3174\/ajnr.A5106","article-title":"MRI-Based Texture Analysis to Differentiate Sinonasal Squamous Cell Carcinoma from Inverted Papilloma","volume":"38","author":"S Ramkumar","year":"2017","journal-title":"AJNR Am J Neuroradiol"},{"key":"pone.0263125.ref029","doi-asserted-by":"crossref","first-page":"e0244406","DOI":"10.1371\/journal.pone.0244406","article-title":"3D multi-scale deep convolutional neural networks for pulmonary nodule detection","volume":"16","author":"H Peng","year":"2021","journal-title":"PLoS One"},{"key":"pone.0263125.ref030","first-page":"409","article-title":"Lung cancer detection and classification with 3D convolutional neural network (3D-CNN)","volume":"8","author":"W Alakwaa","year":"2017","journal-title":"Int J Adv Comput Sci Appl"},{"key":"pone.0263125.ref031","doi-asserted-by":"crossref","unstructured":"Huang X, Shan J, Vaidya V. Lung nodule detection in CT using 3D convolutional neural networks. 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017). 2017:379\u201383.","DOI":"10.1109\/ISBI.2017.7950542"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0263125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T18:05:30Z","timestamp":1674842730000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0263125"}},"subtitle":[],"editor":[{"given":"Yan Chai","family":"Hum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,2,25]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,2,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0263125","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,25]]}}}