{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T12:06:12Z","timestamp":1788264372157,"version":"build-2803163510"},"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Korean Rhinologic Society"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Nasal endoscopy is routinely performed to distinguish the pathological types of masses. There is a lack of studies on deep learning algorithms for discriminating a wide range of endoscopic nasal cavity mass lesions. Therefore, we aimed to develop an endoscopic-examination-based deep learning model to detect and classify nasal cavity mass lesions, including nasal polyps (NPs), benign tumors, and malignant tumors. The clinical feasibility of the model was evaluated by comparing the results to those of manual assessment. Biopsy-confirmed nasal endoscopic images were obtained from 17 hospitals in South Korea. Here, 400 images were used for the test set. The training and validation datasets consisted of 149,043 normal nasal cavity, 311,043 NP, 9,271 benign tumor, and 5,323 malignant tumor lesion images. The proposed Xception architecture achieved an overall accuracy of 0.792 with the following class accuracies on the test set: normal = 0.978 \u00b1 0.016, NP = 0.790 \u00b1 0.016, benign = 0.708 \u00b1 0.100, and malignant = 0.698 \u00b1 0.116. With an average area under the receiver operating characteristic curve (AUC) of 0.947, the AUC values and F1 score were highest in the order of normal, NP, malignant tumor, and benign tumor classes. The classification performances of the proposed model were comparable with those of manual assessment in the normal and NP classes. The proposed model outperformed manual assessment in the benign and malignant tumor classes (sensitivities of 0.708 \u00b1 0.100 vs. 0.549 \u00b1 0.172, 0.698 \u00b1 0.116 vs. 0.518 \u00b1 0.153, respectively). In urgent (malignant) versus nonurgent binary predictions, the deep learning model achieved superior diagnostic accuracy. The developed model based on endoscopic images achieved satisfactory performance in classifying four classes of nasal cavity mass lesions, namely normal, NP, benign tumor, and malignant tumor. The developed model can therefore be used to screen nasal cavity lesions accurately and rapidly.<\/jats:p>","DOI":"10.1371\/journal.pone.0297536","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:40:14Z","timestamp":1710351614000},"page":"e0297536","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":16,"title":["Deep learning algorithm for the automated detection and classification of nasal cavity mass in nasal endoscopic images"],"prefix":"10.1371","volume":"19","author":[{"given":"Kyung Won","family":"Kwon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong Hyeon","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Hoon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong-Young","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Il-Ho","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun-Jin","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong Seung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joo Yeon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Duk","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shin Ae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5083-8720","authenticated-orcid":true,"given":"Shin Hyuk","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soo Kyoung","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Jae","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Hee","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tae-Bin","family":"Won","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Woo Ri","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Min","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Wan","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1230-9307","authenticated-orcid":true,"given":"Jong-Yeup","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Hwan","family":"Kwon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4529-0254","authenticated-orcid":true,"given":"Myeong Sang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"issue":"1","key":"pone.0297536.ref001","doi-asserted-by":"crossref","first-page":"45","DOI":"10.4103\/sjhs.sjhs_168_19","article-title":"Clinical, histopathological, and radiological features of unilateral nasal mass in Saudi Arabia: A retrospective study","volume":"9","author":"K Hakami","year":"2020","journal-title":"Saudi J Health Sci"},{"issue":"3","key":"pone.0297536.ref002","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1007\/BF03050834","article-title":"Masses of nasal cavity, paranasal sinuses and nasopharynx: A clinicopathological study.","volume":"58","author":"N Khan","year":"2006","journal-title":"Indian J Otolaryngol Head Neck Surg"},{"issue":"6","key":"pone.0297536.ref003","first-page":"372","article-title":"Clinico-pathological profile of sinonasal masses: a study from a tertiary care hospital of India.","volume":"31","author":"A Lathi","year":"2011","journal-title":"Acta Otorhinolaryngol Ital"},{"issue":"2","key":"pone.0297536.ref004","doi-asserted-by":"crossref","first-page":"507","DOI":"10.2147\/TCRM.S2379","article-title":"A review of nasal polyposis.","volume":"4","author":"JR Newton","year":"2008","journal-title":"Ther Clin Risk Manag"},{"issue":"4","key":"pone.0297536.ref005","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1093\/ije\/28.4.717","article-title":"Prevalence of asthma, aspirin intolerance, nasal polyposis and chronic obstructive pulmonary disease in a population-based study.","volume":"28","author":"J Hedman","year":"1999","journal-title":"Int J Epidemiol"},{"issue":"2","key":"pone.0297536.ref006","doi-asserted-by":"crossref","first-page":"157","DOI":"10.2500\/ajra.2012.26.3732","article-title":"Inverted papillomas and benign nonneoplastic lesions of the nasal cavity","volume":"26","author":"JW Wood","year":"2012","journal-title":"Am J Rhinol Allergy"},{"key":"pone.0297536.ref007","volume-title":"Allergy Asthma Proc.","author":"GA Settipane","year":"1996"},{"key":"pone.0297536.ref008","volume-title":"Int Forum Allergy Rhinol","author":"M Paz Silva","year":"2015"},{"issue":"6","key":"pone.0297536.ref009","first-page":"1040","article-title":"Polypoidal lesions in the nasal cavity.","volume":"7","author":"KK MK","year":"2013","journal-title":"J Clin Diagn Res"},{"issue":"3","key":"pone.0297536.ref010","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":"Int J Comput Vis"},{"key":"pone.0297536.ref011","article-title":"editors. Imagenet: A large-scale hierarchical image database. 2009","author":"IEEE","year":"2009","journal-title":"IEEE Conf Comput Vis Pattern Recognit Image"},{"issue":"22","key":"pone.0297536.ref012","doi-asserted-by":"crossref","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"V Gulshan","year":"2016","journal-title":"JAMA"},{"issue":"1","key":"pone.0297536.ref013","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/JBHI.2016.2637004","article-title":"Integrating online and offline three-dimensional deep learning for automated polyp detection in colonoscopy videos","volume":"21","author":"L Yu","year":"2016","journal-title":"IEEE J Biomed Health Inform"},{"issue":"4","key":"pone.0297536.ref014","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s10120-018-0793-2","article-title":"Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images","volume":"21","author":"T Hirasawa","year":"2018","journal-title":"Gastric Cancer"},{"issue":"7639","key":"pone.0297536.ref015","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"issue":"11","key":"pone.0297536.ref016","first-page":"E686","article-title":"Automatic recognition of laryngoscopic images using a deep\u2010learning technique","volume":"130","author":"J Ren","year":"2020","journal-title":"The Laryngoscope"},{"key":"pone.0297536.ref017","volume-title":"Int Forum Allergy Rhinol","author":"B Girdler","year":"2021"},{"issue":"5","key":"pone.0297536.ref018","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.anorl.2016.03.006","article-title":"Sinonasal inverted papilloma: From diagnosis to treatment.","volume":"133","author":"Q Lisan","year":"2016","journal-title":"Eur Ann Otorhinolaryngol Head Neck Dis"},{"issue":"7","key":"pone.0297536.ref019","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1017\/S0022215110000599","article-title":"Sinonasal inverted papilloma: narrative review.","volume":"124","author":"S Anari","year":"2010","journal-title":"J Laryngol Otol"},{"issue":"4","key":"pone.0297536.ref020","doi-asserted-by":"crossref","first-page":"2420","DOI":"10.3390\/curroncol28040222","article-title":"Malignant sinonasal tumors: update on histological and clinical management.","volume":"28","author":"A Bracigliano","year":"2021","journal-title":"Curr Oncol"},{"issue":"6","key":"pone.0297536.ref021","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.jaci.2015.10.010","article-title":"Current and future treatment options for adult chronic rhinosinusitis: focus on nasal polyposis","volume":"136","author":"C Bachert","year":"2015","journal-title":"J Allergy Clin Immunol"},{"issue":"2","key":"pone.0297536.ref022","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/j.otc.2009.01.006","article-title":"Surgical management of benign sinonasal masses.","volume":"42","author":"RJ Harvey","year":"2009","journal-title":"Otolaryngol Clin North Am"},{"issue":"3","key":"pone.0297536.ref023","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1177\/0145561319875711","article-title":"The diagnostic value of traditional nasal examination tools in an endoscopic era.","volume":"100","author":"S Chainansamit","year":"2021","journal-title":"Ear Nose Throat J"},{"issue":"12","key":"pone.0297536.ref024","doi-asserted-by":"crossref","first-page":"116","DOI":"10.3390\/jcm6120116","article-title":"Imaging characteristics of malignant sinonasal tumors.","volume":"6","author":"M Kawaguchi","year":"2017","journal-title":"J Clin Med"},{"issue":"1","key":"pone.0297536.ref025","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"F Zhuang","year":"2020","journal-title":"Proc IEEE"},{"key":"pone.0297536.ref026","unstructured":"Raghu M, Zhang C, Kleinberg J, Bengio S. Transfusion: Understanding transfer learning with applications to medical imaging. arXiv 2019. arXiv preprint arXiv:190207208. 2019."},{"key":"pone.0297536.ref027","unstructured":"Canziani A, Paszke A, Culurciello E. An analysis of deep neural network models for practical applications. arXiv preprint arXiv:160507678. 2016."},{"key":"pone.0297536.ref028","article-title":"editor Xception: Deep learning with depthwise separable convolutions","author":"F Chollet","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"issue":"12","key":"pone.0297536.ref029","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.3390\/diagnostics11122183","article-title":"Impact of image resolution on deep learning performance in endoscopy image classification: an experimental study using a large dataset of endoscopic images.","volume":"11","author":"V Thambawita","year":"2021","journal-title":"Diagn"},{"issue":"5","key":"pone.0297536.ref030","first-page":"661","article-title":"Analysis study on the detection and classification of COVID-19 in chest X-ray images using artificial intelligence","volume":"16","author":"M-S Yoon","year":"2022","journal-title":"Korean Soc Radiol"},{"issue":"10","key":"pone.0297536.ref031","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"SJ Pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"pone.0297536.ref032","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep learning in medical image analysis.","volume":"19","author":"D Shen","year":"2017","journal-title":"Annu Rev Biomed Eng"},{"key":"pone.0297536.ref033","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Med Image Anal"},{"issue":"5","key":"pone.0297536.ref034","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1109\/JBHI.2017.2775662","article-title":"Classification of medical images in the biomedical literature by jointly using deep and handcrafted visual features","volume":"22","author":"J Zhang","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"issue":"4","key":"pone.0297536.ref035","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 Oto."},{"key":"pone.0297536.ref036","volume-title":"Int Forum Allergy Rhinol","author":"NI Chowdhury","year":"2019"},{"issue":"1","key":"pone.0297536.ref037","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 Oto"},{"key":"pone.0297536.ref038","volume-title":"Int Forum Allergy Rhinol","author":"SM Humphries","year":"2020"},{"issue":"2","key":"pone.0297536.ref039","doi-asserted-by":"crossref","first-page":"698","DOI":"10.1016\/j.jaci.2019.12.002","article-title":"Expert-level diagnosis of nasal polyps using deep learning on whole-slide imaging","volume":"145","author":"Q Wu","year":"2020","journal-title":"J Allergy Clin Immunol"},{"issue":"1","key":"pone.0297536.ref040","first-page":"1","article-title":"Deep learning model for tongue cancer diagnosis using endoscopic images","volume":"12","author":"J Heo","year":"2022","journal-title":"Sci Rep"},{"issue":"24","key":"pone.0297536.ref041","article-title":"A deep convolutional neural network-based method for laryngeal squamous cell carcinoma diagnosis","volume":"9","author":"Y He","year":"2021","journal-title":"Ann Transl Med"},{"key":"pone.0297536.ref042","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.ebiom.2019.08.075","article-title":"Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images","volume":"48","author":"H Xiong","year":"2019","journal-title":"EBioMedicine"},{"issue":"1","key":"pone.0297536.ref043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40880-018-0325-9","article-title":"Development and validation of an endoscopic images\u2010based deep learning model for detection with nasopharyngeal malignancies","volume":"38","author":"C Li","year":"2018","journal-title":"Cancer Commun"},{"key":"pone.0297536.ref044","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.ins.2021.04.053","article-title":"RTFN: A robust temporal feature network for time series classification.","volume":"571","author":"Z Xiao","year":"2021","journal-title":"Inf Sci."},{"issue":"12","key":"pone.0297536.ref045","doi-asserted-by":"crossref","first-page":"1645","DOI":"10.1016\/S1470-2045(19)30637-0","article-title":"Real-time artificial intelligence for detection of upper gastrointestinal cancer by endoscopy: a multicentre, case-control, diagnostic study.","volume":"20","author":"H Luo","year":"2019","journal-title":"The Lancet Oncology."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T17:40:53Z","timestamp":1710351653000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0297536"}},"subtitle":[],"editor":[{"given":"Claudio","family":"Andaloro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":45,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0297536","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]}}}