{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T03:25:42Z","timestamp":1792466742100,"version":"4.5.0"},"reference-count":53,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"48","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,28]]},"abstract":"<jats:p>Otitis media (OM) is a globally prevalent health issue that poses significant threats to hearing and overall health. However, traditional diagnostic methods rely heavily on subjective interpretation of otoscopic images, which often leads to inconsistent outcomes and high misdiagnosis rates. This study evaluated 5 deep learning models (ResNet-18, GoogLeNet, AlexNet, MobileNet-V3, and VGGNet-19) for classifying 819 otoscopic images into 4 categories: normal, acute otitis media, otitis media with effusion, and chronic suppurative otitis media. Specifically, the dataset was split into training (60%), validation (20%), and test (20%) sets. Subsequently, model performance was assessed using accuracy, sensitivity, specificity, precision, F1 score, and receiver operating characteristic\u2013area under the curve analysis. The results showed that VGGNet-19 demonstrated superior performance, achieving the highest scores in accuracy (94.51%), sensitivity (94.18%), specificity (98.10%), and precision (93.86%), with particularly outstanding performance in chronic suppurative otitis media identification. While other models delivered competitive results, their metrics were consistently lower in comparison. Therefore, the study confirms VGGNet-19\u2019s potential as an accurate, automated diagnostic tool for OM classification. Future research should address dataset imbalances and validate findings across diverse clinical settings to enhance generalizability.<\/jats:p>","DOI":"10.1097\/md.0000000000046218","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T14:01:02Z","timestamp":1764597662000},"page":"e46218","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":5,"title":["Deep learning for otitis media classification using otoscopic image"],"prefix":"10.1097","volume":"104","author":[{"given":"Qingqing","family":"Guo","sequence":"first","affiliation":[{"name":"Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangzhen","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, The First Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9778-125X","authenticated-orcid":false,"given":"Ling","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, The First Affiliated Hospital of Heilongjiang University of Chinese Medicine, Harbin, Heilongjiang, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20260121","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ijporl.2017.12.027","article-title":"Risk of childhood otitis media with focus on potentially modifiable factors: a Danish follow-up cohort study.","volume":"106","author":"K\u00f8rvel-Hanquist","year":"2018","journal-title":"Int J Pediatr Otorhinolaryngol"},{"key":"R3-20260121","doi-asserted-by":"crossref","first-page":"e405","DOI":"10.7717\/peerj-cs.405","article-title":"Otitis media detection using tympanic membrane images with a novel multi-class machine learning algorithm.","volume":"7","author":"Alhudhaif","year":"2021","journal-title":"PeerJ Comput Sci"},{"key":"R4-20260121","doi-asserted-by":"crossref","first-page":"e964","DOI":"10.1542\/peds.2012-3488","article-title":"The diagnosis and management of acute otitis media.","volume":"131","author":"Lieberthal","year":"2013","journal-title":"Pediatrics"},{"key":"R5-20260121","doi-asserted-by":"crossref","first-page":"e941350","DOI":"10.12659\/MSM.941350","article-title":"Audiometric outcomes of ventilation drainage treatment for otitis media with effusion in children: implications for speech development and hearing loss.","volume":"29","author":"Partycka-Pietrzyk","year":"2023","journal-title":"Med Sci Monit"},{"key":"R6-20260121","doi-asserted-by":"crossref","first-page":"3561","DOI":"10.1007\/s00405-025-09277-0","article-title":"Does Helicobacter pylori have a role in the pathogenesis of otitis media with effusion, or is it a fallacy??","volume":"282","author":"Gunduz","year":"2025","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"R7-20260121","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1017\/S0022215116000943","article-title":"Aetiology and pathology of otitis media with effusion in adult life.","volume":"130","author":"Mills","year":"2016","journal-title":"J Laryngol Otol"},{"key":"R8-20260121","doi-asserted-by":"crossref","first-page":"e36226","DOI":"10.1371\/journal.pone.0036226","article-title":"Burden of disease caused by otitis media: systematic review and global estimates.","volume":"7","author":"Monasta","year":"2012","journal-title":"PLoS One"},{"key":"R9-20260121","doi-asserted-by":"crossref","first-page":"16063","DOI":"10.1038\/nrdp.2016.63","article-title":"Otitis media.","volume":"2","author":"Schilder","year":"2016","journal-title":"Nat Rev Dis Primers"},{"key":"R10-20260121","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.neunet.2020.03.023","article-title":"Automatic detection of tympanic membrane and middle ear infection from oto-endoscopic images via convolutional neural networks.","volume":"126","author":"Khan","year":"2020","journal-title":"Neural Netw"},{"key":"R11-20260121","doi-asserted-by":"crossref","first-page":"1289736","DOI":"10.1080\/16549716.2017.1289736","article-title":"Survey of ENT services in sub-Saharan Africa: little progress between 2009 and 2015.","volume":"10","author":"Mulwafu","year":"2017","journal-title":"Glob Health Action"},{"key":"R12-20260121","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1016\/j.ijporl.2008.01.030","article-title":"Recognition of paediatric otopathology by General Practitioners.","volume":"72","author":"Buchanan","year":"2008","journal-title":"Int J Pediatr Otorhinolaryngol"},{"key":"R13-20260121","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1111\/j.1651-2227.2005.tb01912.x","article-title":"Accuracy of acute otitis media diagnosis in community and hospital settings.","volume":"94","author":"Asher","year":"2005","journal-title":"Acta Paediatr"},{"key":"R14-20260121","doi-asserted-by":"crossref","first-page":"28","DOI":"10.21053\/ceo.2022.00675","article-title":"Deep learning techniques for ear diseases based on segmentation of the normal tympanic membrane.","volume":"16","author":"Park","year":"2023","journal-title":"Clin Exp Otorhinolaryngol"},{"key":"R15-20260121","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":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"R16-20260121","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":"Esteva","year":"2017","journal-title":"Nature"},{"key":"R19-20260121","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/s41592-018-0261-2","article-title":"U-Net: deep learning for cell counting, detection, and morphometry.","volume":"16","author":"Falk","year":"2019","journal-title":"Nat Methods"},{"key":"R20-20260121","doi-asserted-by":"crossref","first-page":"1827","DOI":"10.3390\/app9091827","article-title":"Automated classification of the tympanic membrane using a convolutional neural network.","volume":"9","author":"Lee","year":"2019","journal-title":"Appl Sci"},{"key":"R21-20260121","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1007\/s10439-023-03422-8","article-title":"Insight into automatic image diagnosis of ear conditions based on optimized deep learning approach.","volume":"52","author":"Afify","year":"2024","journal-title":"Ann Biomed Eng"},{"key":"R22-20260121","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.ebiom.2019.06.050","article-title":"Automated diagnosis of ear disease using ensemble deep learning with a big otoendoscopy image database.","volume":"45","author":"Cha","year":"2019","journal-title":"EBioMedicine"},{"key":"R23-20260121","doi-asserted-by":"crossref","first-page":"10643","DOI":"10.1038\/s41598-021-89588-4","article-title":"Analysing wideband absorbance immittance in normal and ears with otitis media with effusion using machine learning.","volume":"11","author":"Grais","year":"2021","journal-title":"Sci Rep"},{"key":"R24-20260121","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1097\/MAO.0000000000001897","article-title":"Development of an automatic diagnostic algorithm for pediatric otitis media.","volume":"39","author":"Tran","year":"2018","journal-title":"Otol Neurotol"},{"key":"R25-20260121","first-page":"435","article-title":"Otitis media: diagnosis and treatment.","volume":"88","author":"Harmes","year":"2013","journal-title":"Am Fam Physician"},{"key":"R26-20260121","doi-asserted-by":"crossref","first-page":"2339","DOI":"10.1016\/S0140-6736(24)00259-9","article-title":"Chronic suppurative otitis media.","volume":"403","author":"Bhutta","year":"2024","journal-title":"Lancet"},{"key":"R27-20260121","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1002\/sim.9694","article-title":"Simulating and estimating agreement in the presence of multiple raters and covariates.","volume":"42","author":"McKenzie","year":"2023","journal-title":"Stat Med"},{"key":"R28-20260121","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition.","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc IEEE"},{"key":"R29-20260121","doi-asserted-by":"crossref","first-page":"2470","DOI":"10.3390\/electronics10202470","article-title":"CNN variants for computer vision: history, architecture, application, challenges and future scope.","volume":"10","author":"Bhatt","year":"2021","journal-title":"Electronics"},{"key":"R30-20260121","first-page":"92","article-title":"Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training.","volume":"23","author":"Narayanan","year":"2015","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"R31-20260121","doi-asserted-by":"crossref","first-page":"108582","DOI":"10.1016\/j.asoc.2022.108582","article-title":"Feature fusion and kernel selective in Inception-v4 network.","volume":"119","author":"Chen","year":"2022","journal-title":"Appl Soft Comput"},{"key":"R32-20260121","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1049\/ipr2.12419","article-title":"Medical image segmentation using deep learning: a survey.","volume":"16","author":"Wang","year":"2022","journal-title":"IET Image Process"},{"key":"R36-20260121","doi-asserted-by":"crossref","first-page":"13111","DOI":"10.3390\/app132413111","article-title":"A deep learning review of ResNet architecture for lung disease identification in CXR image.","volume":"13","author":"Hasanah","year":"2023","journal-title":"Appl Sci"},{"key":"R38-20260121","first-page":"104","article-title":"Automatic pancreas segmentation using ResNet-18 deep learning approach.","volume":"2022","author":"Kakarwal","year":"2022","journal-title":"Syst Res Inf Technol"},{"key":"R40-20260121","doi-asserted-by":"crossref","first-page":"565","DOI":"10.32604\/cmc.2023.036317","article-title":"Robust multi-watermarking algorithm for medical images based on GoogLeNet and Henon map.","volume":"75","author":"Zhang","year":"2023","journal-title":"Comput Mater Continua"},{"key":"R42-20260121","doi-asserted-by":"crossref","first-page":"1331","DOI":"10.32604\/iasc.2022.020918","article-title":"Classification similarity network model for image fusion using Resnet50 and GoogLeNet.","volume":"31","author":"Sreedhar","year":"2022","journal-title":"Intell Autom Soft Comput"},{"key":"R43-20260121","first-page":"84","article-title":"Imagenet classification with deep convolutional neural networks.","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"R44-20260121","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":"R45-20260121","first-page":"101490","article-title":"Alexnet architecture variations with transfer learning for classification of wound images.","volume":"45","author":"Eldem","year":"2023","journal-title":"Eng Sci Technol Int J"},{"key":"R46-20260121","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting.","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"R47-20260121","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":"Russakovsky","year":"2015","journal-title":"Int J Comput Vis"},{"key":"R48-20260121","doi-asserted-by":"crossref","first-page":"99282","DOI":"10.1109\/ACCESS.2024.3428700","article-title":"Artificial intelligence-driven advancements in otitis media diagnosis: a systematic review.","volume":"12","author":"Rony","year":"2024","journal-title":"IEEE Access"},{"key":"R54-20260121","doi-asserted-by":"crossref","first-page":"5457","DOI":"10.3390\/app14135457","article-title":"Diagnosis of tympanic membrane disease and pediatric hearing using convolutional neural network models with multi-layer perceptrons.","volume":"14","author":"Lee","year":"2024","journal-title":"Appl Sci"},{"key":"R55-20260121","doi-asserted-by":"crossref","first-page":"27518","DOI":"10.1109\/ACCESS.2024.3367774","article-title":"Lumbar disease classification using an involutional neural based VGG Nets (INVGG).","volume":"12","author":"Abuhayi","year":"2024","journal-title":"IEEE Access"},{"key":"R56-20260121","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1080\/24699322.2019.1649071","article-title":"Lung segmentation method with dilated convolution based on VGG-16 network.","volume":"24","author":"Geng","year":"2019","journal-title":"Comput Assist Surg (Abingdon)"},{"key":"R57-20260121","doi-asserted-by":"crossref","first-page":"729","DOI":"10.32604\/iasc.2021.016569","article-title":"Improved model of eye disease recognition based on VGG model.","volume":"28","author":"Mu","year":"2021","journal-title":"Intell Autom Soft Comput"},{"key":"R58-20260121","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1111\/coa.13925","article-title":"Artificial intelligence to classify ear disease from otoscopy: a systematic review and meta\u2010analysis.","volume":"47","author":"Habib","year":"2022","journal-title":"Clin Otolaryngol"},{"key":"R59-20260121","doi-asserted-by":"crossref","first-page":"e0118432","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets.","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS One"},{"key":"R60-20260121","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1093\/bioinformatics\/16.5.412","article-title":"Assessing the accuracy of prediction algorithms for classification: an overview.","volume":"16","author":"Baldi","year":"2000","journal-title":"Bioinformatics"},{"key":"R61-20260121","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1109\/TKDE.2005.50","article-title":"Using AUC and accuracy in evaluating learning algorithms.","volume":"17","author":"Huang","year":"2005","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"R62-20260121","doi-asserted-by":"crossref","first-page":"77809","DOI":"10.1007\/s11042-024-18631-z","article-title":"An ensemble approach for classification of tympanic membrane conditions using soft voting classifier.","volume":"83","author":"Akyol","year":"2024","journal-title":"Multimedia Tools Appl"},{"key":"R63-20260121","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","article-title":"An introduction to ROC analysis.","volume":"27","author":"Fawcett","year":"2006","journal-title":"Pattern Recognit Lett"},{"key":"R64-20260121","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1177\/0194599818809337","article-title":"Emerging technologies for the diagnosis of otitis media.","volume":"160","author":"Marom","year":"2019","journal-title":"Otolaryngol Head Neck Surg"},{"key":"R65-20260121","doi-asserted-by":"crossref","first-page":"102034","DOI":"10.1016\/j.media.2021.102034","article-title":"Deep metric learning for otitis media classification.","volume":"71","author":"Sundgaard","year":"2021","journal-title":"Med Image Anal"},{"key":"R66-20260121","doi-asserted-by":"crossref","first-page":"3198","DOI":"10.3390\/jcm10153198","article-title":"An assistive role of a machine learning network in diagnosis of middle ear diseases.","volume":"10","author":"Byun","year":"2021","journal-title":"J Clin Med"},{"key":"R67-20260121","doi-asserted-by":"crossref","first-page":"1337","DOI":"10.3390\/bioengineering10111337","article-title":"Improving the accuracy of otitis media with effusion diagnosis in pediatric patients using deep learning.","volume":"10","author":"Shim","year":"2023","journal-title":"Bioengineering (Basel)"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000046218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T11:02:40Z","timestamp":1768993360000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000046218"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":53,"journal-issue":{"issue":"48","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000046218","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"2025-04-22","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-20","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}