{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T13:34:27Z","timestamp":1787664867949,"version":"build-2736575974"},"reference-count":14,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"7","license":[{"start":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T00:00:00Z","timestamp":1613692800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2017M3A9E8033207"],"award-info":[{"award-number":["2017M3A9E8033207"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["2018R1D1A3B07040862"],"award-info":[{"award-number":["2018R1D1A3B07040862"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"abstract":"<jats:sec>\n            <jats:title>Abstract<\/jats:title>\n            <jats:p>This study was conducted to develop a convolutional neural network (CNN)-based model to predict the sex and age of patients by identifying unique unknown features from paranasal sinus (PNS) X-ray images.<\/jats:p>\n            <jats:p>We employed a retrospective study design and used anonymized patient imaging data. Two CNN models, adopting ResNet-152 and DenseNet-169 architectures, were trained to predict sex and age groups (20\u201339, 40\u201359, 60+ years). The area under the curve (AUC), algorithm accuracy, sensitivity, and specificity were assessed. Class-activation map (CAM) was used to detect deterministic areas. A total of 4160 PNS X-ray images were collected from 4160 patients. The PNS X-ray images of patients aged \u226520\u200ayears were retrieved from the picture archiving and communication database system of our institution. The classification performances in predicting the sex (male vs female) and 3 age groups (20\u201339, 40\u201359, 60+ years) for each established CNN model were evaluated.<\/jats:p>\n            <jats:p>For sex prediction, ResNet-152 performed slightly better (accuracy = 98.0%, sensitivity = 96.9%, specificity = 98.7%, and AUC = 0.939) than DenseNet-169. CAM indicated that maxillary sinuses (males) and ethmoid sinuses (females) were major factors in identifying sex. Meanwhile, for age prediction, the DenseNet-169 model was slightly more accurate in predicting age groups (77.6\u200a\u00b1\u200a1.5% vs 76.3\u200a\u00b1\u200a1.1%). CAM suggested that the maxillary sinus and the periodontal area were primary factors in identifying age groups.<\/jats:p>\n            <jats:p>Our deep learning model could predict sex and age based on PNS X-ray images. Therefore, it can assist in reducing the risk of patient misidentification in clinics.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1097\/md.0000000000024756","type":"journal-article","created":{"date-parts":[[2021,2,26]],"date-time":"2021-02-26T21:23:50Z","timestamp":1614374630000},"page":"e24756","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":12,"title":["Prediction of age and sex from paranasal sinus images using a deep learning network"],"prefix":"10.1097","volume":"100","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4917-0177","authenticated-orcid":false,"given":"Dong-Kyu","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Otorhinolaryngology-Head and Neck Surgery"},{"name":"Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital"},{"name":"Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0244-388X","authenticated-orcid":false,"given":"Bum-Joo","family":"Cho","sequence":"additional","affiliation":[{"name":"Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon"},{"name":"Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang"},{"name":"Division of Biomedical Informatics, Seoul National University Biomedical Informatics (SNUBI), Seoul National University College of Medicine, Seoul, Republic of Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-0619","authenticated-orcid":false,"given":"Myung-Je","family":"Lee","sequence":"additional","affiliation":[{"name":"Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1522-9038","authenticated-orcid":false,"given":"Ju Han","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Biomedical Informatics, Seoul National University Biomedical Informatics (SNUBI), Seoul National University College of Medicine, Seoul, Republic of Korea."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2021,2,19]]},"reference":[{"key":"R1-20250504","first-page":"215","article-title":"Deep learning opens new horizons in personalized medicine","volume":"10","author":"Papadakis","year":"2019","journal-title":"Biomed Rep"},{"key":"R2-20250504","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.neunet.2016.12.002","article-title":"Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection","volume":"87","author":"Kim","year":"2017","journal-title":"Neural Netw"},{"key":"R3-20250504","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1055\/a-0981-6133","article-title":"Automated classification of gastric neoplasms in endoscopic images using a convolutional neural network","volume":"51","author":"Cho","year":"2019","journal-title":"Endoscopy"},{"key":"R4-20250504","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"R5-20250504","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":"Kim","year":"2019","journal-title":"Quant Imaging Med Surg"},{"key":"R6-20250504","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4193\/Rhino12.000","article-title":"EPOS 2012: European position paper on rhinosinusitis and nasal polyps 2012. A summary for otorhinolaryngologists","volume":"50","author":"Fokkens","year":"2012","journal-title":"Rhinology"},{"key":"R7-20250504","first-page":"464","article-title":"Cyclical learning rates for training neural networks","author":"Smith","year":"2017","journal-title":"In: IEEE Winter Conference on Applications of Computer Vision (WACV)"},{"key":"R8-20250504","article-title":"Snapshot Ensembles: Train 1, get M for free","author":"Huang","year":"2017","journal-title":"Arxiv e-Prints"},{"key":"R9-20250504","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"R10-20250504","doi-asserted-by":"crossref","first-page":"011001","DOI":"10.1088\/1741-2552\/14\/1\/011001","article-title":"Support vector machines to detect physiological patterns for EEG and EMG-based human-computer interaction: a review","volume":"14","author":"Quitadamo","year":"2017","journal-title":"J Neural Eng"},{"key":"R11-20250504","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1109\/TCBB.2014.2306200","article-title":"A simple but powerful heuristic method for accelerating k-means clustering of large-scale data in life science","volume":"11","author":"Ichikawa","year":"2014","journal-title":"IEEE ACM Trans Comput Biol Bioinform"},{"key":"R12-20250504","doi-asserted-by":"crossref","first-page":"63","DOI":"10.12688\/gatesopenres.12891.2","article-title":"Automated verbal autopsy classification: Using one-against-all ensemble method and Naive Bayes classifier","volume":"2","author":"Murtaza","year":"2019","journal-title":"Gates Open Res"},{"key":"R13-20250504","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1148\/radiol.2018180547","article-title":"Convolutional neural networks for radiologic images: a radiologist's guide","volume":"290","author":"Soffer","year":"2019","journal-title":"Radiology"},{"key":"R14-20250504","first-page":"1277","article-title":"Weakly supervised food image segmentation using class activation maps","volume":"2017","author":"Wang","year":"2017","journal-title":"Proc Int Conf Image Proc"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000024756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T06:15:54Z","timestamp":1746339354000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000024756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,19]]},"references-count":14,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000024756","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,19]]},"assertion":[{"value":"2020-08-22","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-25","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}