{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:07:18Z","timestamp":1773259638951,"version":"3.50.1"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T00:00:00Z","timestamp":1741651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>To explore the application of a deep learning model based on lateral nasopharyngeal X-rays in diagnosing tonsillar and adenoid hypertrophy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A retrospective study was conducted using DICOM images of lateral nasopharyngeal X-rays from pediatric outpatients aged 2-12 at our hospital from July 2014 to July 2024. The study included patients exhibiting varying degrees of respiratory obstruction symptoms (disease group). Initially, 1006 images were collected, but after excluding low-quality images and standardizing the imaging phase, 819 images remained. These images were divided into training and validation sets in an 8:2 ratio. The independent test set is consisted of 484 images. We delineated the target areas for tonsils and adenoids and used a YOLOv8n-based model for object detection and use various convolutional neural network models to classify the cropped images, assessing the severity of tonsillar and adenoid hypertrophy. We compared the performance of these models on the training and validation sets using metrics such as ROC-AUC, accuracy, precision, recall, and F1 score.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The combined model, incorporating YOLOv8 for object detection and secondary classification, demonstrated excellent performance in diagnosing tonsillar and adenoid hypertrophy, significantly improving diagnostic accuracy and consistency. The ResNet18 model, due to its lightweight nature and minimal computational resource requirements, performed exceptionally well in the YOLOv8-ResNet fusion model for detecting and classifying tonsils and adenoids, making it our preferred model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The deep learning model combining YOLOv8n and ResNet18 based on lateral nasopharyngeal X-rays demonstrates significant advantages in diagnosing pediatric tonsillar and adenoid hypertrophy.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2025.1508525","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T05:12:28Z","timestamp":1741669948000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimized deep learning model for diagnosing tonsil and adenoid hypertrophy through X-rays"],"prefix":"10.3389","volume":"15","author":[{"given":"Zhiqing","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Zhuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(05)71141-7","article-title":"Long-term cardiovascular outcomes in men with obstructive sleep apnoea-hypopnoea with or without treatment with continuous positive airway pressure: an observational study","volume":"365","author":"Marin","year":"2005","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2007.11.003","article-title":"Pediatric obstructive sleep apnea and quality of life: a meta-analysis","volume":"138","author":"Baldassari","year":"2008","journal-title":"Otolaryngol Head Neck Surg"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fped.2022.900216","article-title":"Analysis of the risk factors associated with obstructive sleep apnea syndrome in chinese children","volume":"10","author":"Xiao","year":"2022","journal-title":"Front Pediatr"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2014.12.013","article-title":"Are distinct etiologies of upper airway obstruction in mouth-breathing children associated with different cephalometric patterns","volume":"79","author":"Franco","year":"2015","journal-title":"Int J Pediatr Otorhinolaryngol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajodo.2005.05.050","article-title":"Assessment of lateral cephalometric diagnosis of adenoid hypertrophy and posterior upper airway obstruction: a systematic review","volume":"130","author":"Major","year":"2006","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijporl.2019.01.011","article-title":"Accuracy of lateral cephalogram for diagnosis of adenoid hypertrophy and posterior upper airway obstruction: A meta-analysis","volume":"119","author":"Duan","year":"2019","journal-title":"Int J Pediatr Otorhinolaryngol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"836","DOI":"10.1186\/s12903-023-03573-z","article-title":"Role of the tonsil-oropharynx ratio on lateral cephalograms in assessing tonsillar hypertrophy in children seeking orthodontic treatment","volume":"23","author":"Lv","year":"2023","journal-title":"BMC Oral Health"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.2214\/ajr.133.3.401","article-title":"Radiographic evaluation of adenoidal size in children: adenoidal-nasopharyngeal ratio","volume":"133","author":"Fujioka","year":"1979","journal-title":"AJR Am J Roentgenol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3955(16)36806-7","article-title":"Modern assessment of tonsils and adenoids","volume":"36","author":"Brodsky","year":"1989","journal-title":"Pediatr Clin North Am"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoto.2014.2338","article-title":"The reliability of clinical tonsil size grading in children","volume":"140","author":"Kumar","year":"2014","journal-title":"JAMA Otolaryngol Head Neck Surg"},{"key":"B11","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.amjoto.2017.10.013","article-title":"Pediatric airway study: Endoscopic grading system for quantifying tonsillar size in comparison to standard adenotonsillar grading systems","volume":"39","author":"Patel","year":"2018","journal-title":"Am J Otolaryngol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2009.09.007","article-title":"Palatine tonsil size and its correlation with subjective tonsil size in patients with sleep-disordered breathing","volume":"141","author":"Wang","year":"2009","journal-title":"Otolaryngol Head Neck Surg"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/s00405-014-2944-3","article-title":"Objective versus subjective measurements of palatine tonsil size in adult patients with obstructive sleep apnea\/hypopnea syndrome","volume":"271","author":"Lai","year":"2014","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.5664\/jcsm.8736","article-title":"Effect of adenoids and tonsil tissue on pediatric obstructive sleep apnea severity determined by computational fluid dynamics","volume":"16","author":"Iwasaki","year":"2020","journal-title":"J Clin Sleep Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-021-03163-z","article-title":"Ultrasound-based radiomics score: a potential biomarker for the prediction of progression-free survival in ovarian epithelial cancer","volume":"46","author":"Yao","year":"2021","journal-title":"Abdom Radiol (NY)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.3390\/s22031285","article-title":"Fracture detection in wrist X-ray images using deep learning-based object detection models","volume":"22","author":"Hardalac","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1186\/s13244-023-01497-4","article-title":"The diagnostic performance and clinical value of deep learning-based nodule detection system concerning influence of location of pulmonary nodule","volume":"14","author":"You","year":"2023","journal-title":"Insights Imaging"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.211367","article-title":"Deep learning prediction of ovarian Malignancy at US compared with O-RADS and expert assessment","volume":"304","author":"Chen","year":"2022","journal-title":"Radiology"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.200912-1930OC","article-title":"Adenotonsillectomy outcomes in treatment of obstructive sleep apnea in children: a multicenter retrospective study","volume":"182","author":"Bhattacharjee","year":"2010","journal-title":"Am J Respir Crit Care Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach Learn Knowledge Extraction"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.1109\/ADICS58448.2024.10533619","article-title":"YOLOv8: A novel object detection algorithm with enhanced performance and robustness","author":"Varghese","year":"2024"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2024.1355857","article-title":"YOLOv8-ACU: improved YOLOv8-pose for facial acupoint detection","volume":"18","author":"Yuan","year":"2024","journal-title":"Front Neurorobot"},{"key":"B23","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/s00432-024-05872-6","article-title":"Developing a deep learning model for predicting ovarian cancer in Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) Category 4 lesions: A multicenter study","volume":"150","author":"Xie","year":"2024","journal-title":"J Cancer Res Clin Oncol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.3390\/biomedicines11061723","article-title":"A comparative analysis of optimization algorithms for gastrointestinal abnormalities recognition and classification based on ensemble xcepNet23 and resNet18 features","volume":"11","author":"Naz","year":"2023","journal-title":"Biomedicines"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.74","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/s00247-015-3505-7","article-title":"Tonsil ultrasound: technical approach and spectrum of pediatric peritonsillar infections","volume":"46","author":"Bandarkar","year":"2016","journal-title":"Pediatr Radiol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-020-01168-0","article-title":"Normal palatine tonsil size in healthy children: a sonographic study","volume":"125","author":"Aydin","year":"2020","journal-title":"Radiol Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-025-01423-8","article-title":"Automatic identification of adenoid hypertrophy via ensemble deep learning models employing X-ray adenoid images","author":"Orenc","year":"2025","journal-title":"J Imaging Inform Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.ajodo.2022.11.011","article-title":"Automatic detection of adenoid hypertrophy on cone-beam computed tomography based on deep learning","volume":"163","author":"Dong","year":"2023","journal-title":"Am J Orthod Dentofacial Orthop"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.21037\/tp-24-194","article-title":"Automatic detection of adenoid hypertrophy on lateral nasopharyngeal radiographs of children based on deep learning","volume":"13","author":"Guo","year":"2024","journal-title":"Transl Pediatr"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14063","article-title":"A deep-learning-based approach for adenoid hypertrophy diagnosis","volume":"47","author":"Shen","year":"2020","journal-title":"Med Phys"},{"key":"B32","doi-asserted-by":"publisher","first-page":"18619","DOI":"10.1038\/s41598-024-69827-0","article-title":"Automated diagnosis of adenoid hypertrophy with lateral cephalogram in children based on multi-scale local attention","volume":"14","author":"Rao","year":"2024","journal-title":"Sci Rep"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1386","DOI":"10.3390\/diagnostics11081386","article-title":"Automated adenoid hypertrophy assessment with lateral cephalometry in children based on artificial intelligence","volume":"11","author":"Zhao","year":"2021","journal-title":"Diagnostics (Basel)"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1508525\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T05:12:35Z","timestamp":1741669955000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1508525\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,11]]},"references-count":33,"alternative-id":["10.3389\/fonc.2025.1508525"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1508525","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,11]]},"article-number":"1508525"}}