{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T06:59:37Z","timestamp":1768978777149,"version":"3.49.0"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T00:00:00Z","timestamp":1768867200000},"content-version":"vor","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":["2022R1F1A1062925"],"award-info":[{"award-number":["2022R1F1A1062925"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["HR20C0021"],"award-info":[{"award-number":["HR20C0021"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002560","name":"Soonchunhyang University","doi-asserted-by":"publisher","award":["2025-0044"],"award-info":[{"award-number":["2025-0044"]}],"id":[{"id":"10.13039\/501100002560","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>This study aimed to develop and evaluate a deep learning algorithm for detecting and classifying intrasinus calcifications on paranasal sinus (PNS) computed tomography (CT) for the diagnosis of fungal sinusitis and differentiation of fungal and non-fungal sinusitis. A dataset of 277 PNS CT cases from Korea University Guro Hospital, supplemented by temporal and geographic external test sets, was utilized. A 3D U-Net model was employed to segment maxillary sinus regions. YOLO v5 identified calcifications, followed by classification into three patterns: normal sinus or chronic sinusitis without calcifications, dense peripheral dystrophic calcification, and central punctate fungal calcification. A separate convolutional neural network (CNN) refined the classification to ensure accurate categorization of calcification patterns. The 3D U-Net model achieved a Dice Similarity Coefficient of 0.9674, indicating accurate segmentation. YOLO v5 demonstrated precision of 79.50% and recall of 92.14% in detecting calcifications. The CNN classification model attained F1 scores of 94.73%, 90.60%, and 94.01%, and overall accuracies of 97.48%, 86.87%, and 94.01% for internal, temporal, and geographic test sets, respectively. This study demonstrated the capability of deep learning algorithms to accurately detect and classify fungal sinusitis-related calcifications on PNS CT scans. The developed framework achieved high accuracy in segmentation of sinus area and detection\/classification of intrasinus calcifications. The framework also demonstrated its potential for broader application to radiographic imaging.<\/jats:p>","DOI":"10.1371\/journal.pone.0340832","type":"journal-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T18:29:36Z","timestamp":1768933776000},"page":"e0340832","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning detection and classification of fungal and non-fungal calcifications on paranasal sinus CT imaging"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8089-7396","authenticated-orcid":true,"given":"Zepa","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Insung","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5806-6884","authenticated-orcid":true,"given":"Hoo","family":"Yun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye Na","family":"Jung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangil","family":"Suh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8591-2225","authenticated-orcid":true,"given":"Bo Kyu","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byungjun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Hye","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6866-7926","authenticated-orcid":true,"given":"Inseon","family":"Ryoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,1,20]]},"reference":[{"issue":"6","key":"pone.0340832.ref001","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups","volume":"29","author":"G Hinton","year":"2012","journal-title":"IEEE Signal Process Mag"},{"issue":"12","key":"pone.0340832.ref002","article-title":"Deep learning of the tissue-regulated splicing code","volume":"30","author":"MKK Leung","year":"2014","journal-title":"Bioinformatics"},{"issue":"6","key":"pone.0340832.ref003","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"S Ren","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0340832.ref004","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.mri.2019.05.038","article-title":"Applications of a deep learning method for anti-aliasing and super-resolution in MRI","volume":"64","author":"C Zhao","year":"2019","journal-title":"Magn Reson Imaging"},{"issue":"2","key":"pone.0340832.ref005","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1007\/s00330-019-06417-z","article-title":"Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network","volume":"30","author":"N Aldoj","year":"2020","journal-title":"Eur Radiol"},{"issue":"7","key":"pone.0340832.ref006","doi-asserted-by":"crossref","first-page":"5206","DOI":"10.1007\/s00330-020-07568-0","article-title":"Utility of deep learning for the diagnosis of otosclerosis on temporal bone CT","volume":"31","author":"N Fujima","year":"2021","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0340832.ref007","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1007\/s10278-020-00320-6","article-title":"Lung nodule detection from feature engineering to deep learning in thoracic CT images: a comprehensive review","volume":"33","author":"A Halder","year":"2020","journal-title":"J Digit Imaging"},{"issue":"2","key":"pone.0340832.ref008","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1007\/s00330-020-07213-w","article-title":"Deep learning algorithm for detection of aortic dissection on non-contrast-enhanced CT","volume":"31","author":"A Hata","year":"2021","journal-title":"Eur Radiol"},{"issue":"5","key":"pone.0340832.ref009","doi-asserted-by":"crossref","first-page":"1646","DOI":"10.1109\/JBHI.2020.3028243","article-title":"Deep learning for hemorrhagic lesion detection and segmentation on brain CT images","volume":"25","author":"L Li","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0340832.ref010","article-title":"Performance of deep learning to detect mastoiditis using multiple conventional radiographs of mastoid","volume":"15","author":"KJ Lee","year":"2020","journal-title":"PLOS ONE"},{"issue":"9","key":"pone.0340832.ref011","doi-asserted-by":"crossref","first-page":"13855","DOI":"10.1007\/s11042-022-13843-7","article-title":"CDC_Net: multi-classification convolutional neural network model for detection of COVID-19, pneumothorax, pneumonia, lung Cancer, and tuberculosis using chest X-rays","volume":"82","author":"H Malik","year":"2023","journal-title":"Multimed Tools Appl"},{"issue":"2","key":"pone.0340832.ref012","doi-asserted-by":"crossref","first-page":"743","DOI":"10.3390\/s23020743","article-title":"DMFL_Net: a federated learning-based framework for the classification of COVID-19 from multiple chest diseases using X-rays","volume":"23","author":"H Malik","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0340832.ref013","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.jacr.2016.09.039","article-title":"Utilization trends in noncardiac thoracic imaging, 2002-2014","volume":"14","author":"SI Kamel","year":"2017","journal-title":"J Am Coll Radiol"},{"issue":"2","key":"pone.0340832.ref014","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1097\/RTI.0000000000000387","article-title":"Deep learning applications in chest radiography and computed tomography: current state of the art","volume":"34","author":"SM Lee","year":"2019","journal-title":"J Thorac Imaging"},{"issue":"1","key":"pone.0340832.ref015","doi-asserted-by":"crossref","first-page":"5337","DOI":"10.1038\/s41598-023-32147-w","article-title":"Application of symmetry evaluation to deep learning algorithm in detection of mastoiditis on mastoid radiographs","volume":"13","author":"D Choi","year":"2023","journal-title":"Sci Rep"},{"key":"pone.0340832.ref016","volume-title":"Cummings otolaryngology: head and neck surgery, vol. 3","author":"PW Flint","year":"2015"},{"issue":"6","key":"pone.0340832.ref017","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1007\/BF00598965","article-title":"Aspergillosis of the paranasal sinuses","volume":"34","author":"T Chang","year":"1992","journal-title":"Neuroradiology"},{"issue":"4","key":"pone.0340832.ref018","first-page":"571","article-title":"Calcification in chronic maxillary sinusitis: comparison of CT findings with histopathologic results","volume":"20","author":"JH Yoon","year":"1999","journal-title":"AJNR Am J Neuroradiol"},{"issue":"2","key":"pone.0340832.ref019","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1148\/radiology.169.2.3174990","article-title":"Fungal sinusitis: diagnosis with CT and MR imaging","volume":"169","author":"SJ Zinreich","year":"1988","journal-title":"Radiology"},{"issue":"5","key":"pone.0340832.ref020","first-page":"917","article-title":"The significance of sinonasal radiodensities: ossification, calcification, or residual bone?","volume":"15","author":"PM Som","year":"1994","journal-title":"AJNR Am J Neuroradiol"},{"issue":"1","key":"pone.0340832.ref021","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1186\/s12880-024-01203-w","article-title":"Deep learning in computed tomography to predict endotype in chronic rhinosinusitis with nasal polyps","volume":"24","author":"W Du","year":"2024","journal-title":"BMC Med Imaging"},{"issue":"8","key":"pone.0340832.ref022","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1093\/dmfr\/twae042","article-title":"Automated detection of maxillary sinus opacifications compatible with sinusitis from CT images","volume":"53","author":"KW Kwon","year":"2024","journal-title":"Dentomaxillofac Radiol"},{"issue":"9","key":"pone.0340832.ref023","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.3174\/ajnr.A7616","article-title":"Clinical validation and extension of an automated, deep learning-based algorithm for quantitative sinus CT analysis","volume":"43","author":"CJ Massey","year":"2022","journal-title":"AJNR Am J Neuroradiol"},{"issue":"1","key":"pone.0340832.ref024","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1186\/s12880-024-01316-2","article-title":"Preliminary study on AI-assisted diagnosis of bone remodeling in chronic maxillary sinusitis","volume":"24","author":"C Zou","year":"2024","journal-title":"BMC Med Imaging"},{"issue":"2","key":"pone.0340832.ref025","article-title":"Detection of maxillary sinus fungal ball via 3-D CNN-based artificial intelligence: fully automated system and clinical validation","volume":"17","author":"K-S Kim","year":"2022","journal-title":"PLoS One"},{"issue":"3","key":"pone.0340832.ref026","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1148\/radiology.156.3.4023231","article-title":"Aspergillosis of the paranasal sinuses","volume":"156","author":"W Kopp","year":"1985","journal-title":"Radiology"},{"key":"pone.0340832.ref027","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"},{"issue":"5","key":"pone.0340832.ref028","first-page":"161","article-title":"Aspergillus mycoses of the paranasal sinuses. Detection and analysis of roentgen opaque structures in fungal concretions","volume":"31","author":"H Stammberger","year":"1983","journal-title":"HNO"},{"issue":"1","key":"pone.0340832.ref029","first-page":"31","article-title":"Ossification of the endometrium: an unusual finding in secondary sterility","volume":"33","author":"P Fehr","year":"1993","journal-title":"Gynakol Geburtshilfliche Rundsch"},{"issue":"4","key":"pone.0340832.ref030","first-page":"1137","article-title":"Apoptosis and calcification","volume":"9","author":"KM Kim","year":"1995","journal-title":"Scanning Microsc"},{"issue":"1","key":"pone.0340832.ref031","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1007\/s12194-023-00756-9","article-title":"Hierarchical approach for pulmonary-nodule identification from CT images using YOLO model and a 3D neural network classifier","volume":"17","author":"Y Ahmadyar","year":"2024","journal-title":"Radiol Phys Technol"},{"issue":"8","key":"pone.0340832.ref032","doi-asserted-by":"crossref","first-page":"3376","DOI":"10.1002\/mp.14161","article-title":"Pulmonary nodule detection using hybrid two-stage 3D CNNs","volume":"47","author":"M Tan","year":"2020","journal-title":"Med Phys"},{"issue":"3","key":"pone.0340832.ref033","doi-asserted-by":"crossref","first-page":"131","DOI":"10.3390\/diagnostics10030131","article-title":"A two-stage framework for automated malignant pulmonary nodule detection in CT scans","volume":"10","author":"S El-Bana","year":"2020","journal-title":"Diagnostics (Basel)"},{"issue":"22","key":"pone.0340832.ref034","doi-asserted-by":"crossref","first-page":"8949","DOI":"10.3390\/s22228949","article-title":"Multi-perspective hierarchical deep-fusion learning framework for lung nodule classification","volume":"22","author":"K Sekeroglu","year":"2022","journal-title":"Sensors (Basel)"},{"issue":"6","key":"pone.0340832.ref035","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1097\/RCT.0000000000000618","article-title":"Computed tomography features of benign and malignant calcified thyroid nodules: a single-center study","volume":"41","author":"D Kim","year":"2017","journal-title":"J Comput Assist Tomogr"},{"key":"pone.0340832.ref036","article-title":"Different lower extremity arterial calcification patterns in patients with chronic limb-threatening ischemia compared with asymptomatic controls","volume":"11","author":"LCD Konijn","year":"2021","journal-title":"J Med"},{"issue":"3","key":"pone.0340832.ref037","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1016\/j.rcl.2014.02.008","article-title":"BI-RADS update","volume":"52","author":"CL Mercado","year":"2014","journal-title":"Radiol Clin North Am"},{"issue":"3","key":"pone.0340832.ref038","first-page":"383","article-title":"Infrapopliteal calcification patterns in critical limb ischemia: diagnostic, pathologic and therapeutic implications in the search for the endovascular holy grail","volume":"58","author":"JA Mustapha","year":"2017","journal-title":"J Cardiovasc Surg (Torino)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340832","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T18:29:44Z","timestamp":1768933784000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0340832"}},"subtitle":[],"editor":[{"given":"Mohmed Isaqali","family":"Karobari","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,1,20]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0340832","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,20]]}}}