{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T14:50:54Z","timestamp":1785768654473,"version":"3.56.0"},"reference-count":24,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Defense Medical University","award":["TSGH_D_115076"],"award-info":[{"award-number":["TSGH_D_115076"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Otitis media (OM), including acute otitis media (AOM) and chronic otitis media (COM), is a common middle ear disease that can lead to significant morbidity if not accurately diagnosed. Otoscopic interpretation remains subjective and operator-dependent, underscoring the need for objective and reproducible diagnostic support. Recent advances in artificial intelligence (AI) offer promising solutions for automated otoscopic image analysis. Methods: We developed an AI-based diagnostic framework consisting of three sequential steps: (1) semi-supervised learning for automatic recognition and semantic segmentation of tympanic membrane structures, (2) region-based feature extraction, and (3) disease classification. A total of 607 clinical otoscopic images were retrospectively collected, including normal ears (n = 220), AOM (n = 157), and COM with tympanic membrane perforation (n = 230). Among these, 485 images were used for training and 122 for independent testing. Semantic segmentation of five anatomically relevant regions was performed using multiple convolutional neural network architectures, including U-Net, PSPNet, HRNet, and DeepLabV3+. Following segmentation, color and texture features were extracted from each region and used to train a neural network-based classifier to differentiate disease states. Results: Among the evaluated segmentation models, U-Net demonstrated superior performance, achieving an overall pixel accuracy of 96.76% and a mean Dice similarity coefficient of 71.68%. The segmented regions enabled reliable extraction of discriminative chromatic and texture features. In the final classification stage, the proposed framework achieved diagnostic accuracies of 100% for normal ears, 100% for AOM, and 91.3% for COM on the independent test set, with an overall accuracy of 96.72%. Conclusions: This study demonstrates that a semi-supervised, segmentation-driven AI pipeline integrating feature extraction and classification can achieve high diagnostic accuracy for otitis media. The proposed framework offers a clinically interpretable and fully automated approach that may enhance diagnostic consistency, support clinical decision-making, and facilitate scalable otoscopic assessment in diverse healthcare screening settings for disease prevention and health education.<\/jats:p>","DOI":"10.3390\/diagnostics16030467","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T16:12:37Z","timestamp":1770048757000},"page":"467","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Learning-Based Semantic Segmentation and Classification of Otoscopic Images for Otitis Media Diagnosis and Health Promotion"],"prefix":"10.3390","volume":"16","author":[{"given":"Chien-Yi","family":"Yang","sequence":"first","affiliation":[{"name":"Division of General Surgery, Department of Surgery, Tri-Service General Hospital Songshan Branch, National Defense Medical University, Taipei 105309, Taiwan"},{"name":"Department of Health Promotion and Health Education, National Taiwan Normal University, Taipei 106308, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Che-Jui","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology-Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical University, No. 325, Sec. 2, Cheng-Gong Road, Neihu District, Taipei 114202, Taiwan"},{"name":"Department of Otolaryngology-Head and Neck Surgery, School of Medicine, College of Medicine, National Defense Medical University, Taipei 114202, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2214-9781","authenticated-orcid":false,"given":"Wen-Sen","family":"Lai","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology-Head and Neck Surgery, School of Medicine, College of Medicine, National Defense Medical University, Taipei 114202, Taiwan"},{"name":"Department of Otolaryngology-Head and Neck Surgery, Taichung Armed Forces General Hospital, Taichung 411228, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuan-Yu","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Material Science & Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9025-8755","authenticated-orcid":false,"given":"Chung-Feng","family":"Kuo","sequence":"additional","affiliation":[{"name":"Department of Material Science & Engineering, National Taiwan University of Science and Technology, Taipei 106335, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chieh Hsing","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Health Promotion and Health Education, National Taiwan Normal University, Taipei 106308, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9730-1798","authenticated-orcid":false,"given":"Shao-Cheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology-Head and Neck Surgery, Tri-Service General Hospital, National Defense Medical University, No. 325, Sec. 2, Cheng-Gong Road, Neihu District, Taipei 114202, Taiwan"},{"name":"Department of Otolaryngology-Head and Neck Surgery, School of Medicine, College of Medicine, National Defense Medical University, Taipei 114202, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1080\/14712598.2020.1740677","article-title":"Unsolved problems and new medical approaches to otitis media","volume":"20","author":"Principi","year":"2020","journal-title":"Expert Opin. Biol. Ther."},{"key":"ref_2","unstructured":"Danishyar, A., and Ashurst, J.V. (2017). Acute Otitis Media, StatPearls Publishing."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1097\/MAO.0000000000001099","article-title":"Type I tympanoplasty meta-analysis: A single variable analysis","volume":"37","author":"Tan","year":"2016","journal-title":"Otol. Neurotol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103751","DOI":"10.1016\/j.amjoto.2022.103751","article-title":"Mastoid obliteration versus canal wall down or canal wall up mastoidectomy for cholesteatoma: Systematic review and meta-analysis","volume":"44","author":"Salem","year":"2023","journal-title":"Am. J. Otolaryngol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1097\/AUD.0000000000001453","article-title":"Global, regional, and national burdens of otitis media from 1990 to 2019: A population based study","volume":"45","author":"Jin","year":"2024","journal-title":"Ear Hear."},{"key":"ref_6","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":"ref_7","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":"ref_8","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":"ref_9","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1001\/archpedi.155.10.1137","article-title":"Assessing diagnostic accuracy and tympanocentesis skills in the management of otitis media","volume":"155","author":"Pichichero","year":"2001","journal-title":"Arch. Pediatr. Adolesc. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1097\/MAO.0000000000003484","article-title":"An artificial intelligence computer-vision algorithm to triage otoscopic images from Australian Aboriginal and Torres Strait Islander children","volume":"43","author":"Habib","year":"2022","journal-title":"Otol. Neurotol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Krithika Alias AnbuDevi, M., and Suganthi, K. (2022). Review of semantic segmentation of medical images using modified architectures of UNET. Diagnostics, 12.","DOI":"10.3390\/diagnostics12123064"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sandstr\u00f6m, J., Myburgh, H., Laurent, C., Swanepoel, D.W., and Lundberg, T. (2022). A machine learning approach to screen for otitis media using digital otoscope images labelled by an expert panel. Diagnostics, 12.","DOI":"10.3390\/diagnostics12061318"},{"key":"ref_13","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":"ref_14","unstructured":"Shie, C.-K., Chang, H.-T., Fan, F.-C., Chen, C.-J., Fang, T.-Y., and Wang, P.-C. A hybrid feature-based segmentation and classification system for the computer aided self-diagnosis of otitis media. Proceedings of the 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, USA, 26\u201330 August 2014, IEEE."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"102065","DOI":"10.1016\/j.artmed.2021.102065","article-title":"EAR-UNet: A deep learning-based approach for segmentation of tympanic membranes from otoscopic images","volume":"115","author":"Pham","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"56225","DOI":"10.1109\/ACCESS.2023.3281693","article-title":"Development of ResNet152 UNet++-based segmentation algorithm for the tympanic membrane and affected areas","volume":"11","author":"Kim","year":"2023","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s11760-020-01772-7","article-title":"Tympanic membrane segmentation in otoscopic images based on fully convolutional network with active contour loss","volume":"15","author":"Pham","year":"2021","journal-title":"Signal Image Video Process."},{"key":"ref_18","first-page":"919","article-title":"Determination of Tympanic Membrane Region in the Middle Ear Otoscope Images with Convolutional Neural Network Based YOLO Method","volume":"22","author":"Velappan","year":"2020","journal-title":"DEUFMD"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"6027","DOI":"10.1007\/s00521-021-06810-0","article-title":"Neighbourhood component analysis and deep feature-based diagnosis model for middle ear otoscope images","volume":"34","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Song, D., Kim, T., Lee, Y., and Kim, J. (2023). Image-based artificial intelligence technology for diagnosing middle ear diseases: A systematic review. J. Clin. Med., 12.","DOI":"10.3390\/jcm12185831"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1001\/jamapediatrics.2024.0011","article-title":"Development and validation of an automated classifier to diagnose acute otitis media in children","volume":"178","author":"Shaikh","year":"2024","journal-title":"JAMA Pediatr."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"q572","DOI":"10.1136\/bmj.q572","article-title":"AI app that can diagnose acute otitis media may cut antibiotic use, say researchers","volume":"384","author":"Wilkinson","year":"2024","journal-title":"Br. Med. J. Publ. Group"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ding, X., Huang, Y., Tian, X., Zhao, Y., Feng, G., and Gao, Z. (2023). Diagnosis, treatment, and management of otitis media with artificial intelligence. Diagnostics, 13.","DOI":"10.3390\/diagnostics13132309"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2050312121993287","DOI":"10.1177\/2050312121993287","article-title":"The role of health promotion in the development of ear and hearing health services in the Pacific Islands: A literature review","volume":"9","author":"Kaspar","year":"2021","journal-title":"SAGE Open Med."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/3\/467\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T05:10:41Z","timestamp":1770613841000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/3\/467"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":24,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["diagnostics16030467"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16030467","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]}}}