{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T20:05:53Z","timestamp":1778702753594,"version":"3.51.4"},"reference-count":43,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["82301330"],"award-info":[{"award-number":["82301330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: The variable accuracy of middle ear disease diagnosis based on oto-endoscopy underscores the need for improved decision support. Although convolutional Neural Networks (CNNs) are currently a mainstay of computer-aided diagnosis (CAD), their constraints in global feature integration persist. We therefore systematically benchmarked state-of-the-art CNNs and Transformers to establish a performance baseline. Beyond this benchmark, our primary contribution is the development of a probability-guided Top-K clinical decision framework that balances high accuracy with complete case coverage for practical deployment. Methods: Using a multicenter dataset of 6361 images (five categories), we implemented a two-stage validation strategy (fixed-split followed by 5-fold cross-validation). A comprehensive comparison was performed among leading CNNs and Transformer variants assessed by accuracy and Macro-F1 score. Results: The Swin Transformer model demonstrated superior performance, achieving an accuracy of 95.53% and a Macro-F1 score of 93.37%. It exhibited exceptional stability (95.61% \u00b1 0.38% in cross-validation) and inherent robustness to class imbalance. A probability-guided Top-2 decision framework was developed, achieving 93.25% accuracy with 100% case coverage. Conclusions: This rigorous benchmark established Swin Transformer as the most effective architecture. Consequently, this study delivers not only a performance benchmark but also a clinically actionable decision-support framework, thereby facilitating the deployment of AI-assisted diagnosis for chronic middle ear conditions in specialist otology.<\/jats:p>","DOI":"10.3390\/diagnostics16030482","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:13:01Z","timestamp":1770289981000},"page":"482","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Benchmark-Driven Clinical Decision Framework for Multi-Class Middle Ear Disease Diagnosis: Superiority of Swin Transformer in Accuracy and Stability"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8016-8740","authenticated-orcid":false,"given":"Guoping","family":"Chen","sequence":"first","affiliation":[{"name":"The First Clinical Medical College, Jinan University, Guangzhou 510632, China"},{"name":"Department of Otolaryngology-Head and Neck Surgery, Zhongshan People\u2019s Hospital, Zhongshan 528403, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Information, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junbo","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, 107 Yanjiang West Road, Guangzhou 510120, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexin","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, 107 Yanjiang West Road, Guangzhou 510120, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Information, South China Agricultural University, Guangzhou 510642, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology Head and Neck Surgery, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology Head and Neck Surgery, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1600-8539","authenticated-orcid":false,"given":"Yiqing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, 107 Yanjiang West Road, Guangzhou 510120, China"},{"name":"Shenshan Medical Center, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Shanwei 518000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, H., Zeng, X., Miao, X., Yang, B., Zhang, S., Fu, Q., Zhang, Q., and Tang, M. (2025). Global, regional, and national epidemiology of otitis media in children from 1990 to 2021. Front. Pediatr., 13.","DOI":"10.3389\/fped.2025.1513629"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1016\/S1473-3099(24)00430-4","article-title":"Global, regional, and national burden of upper respiratory infections and otitis media, 1990\u20132021: A systematic analysis from the Global Burden of Disease Study 2021","volume":"25","author":"Sirota","year":"2025","journal-title":"Lancet Infect. Dis."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2959","DOI":"10.1007\/s00405-024-09165-z","article-title":"Trends in the incidence and burden of otitis media in children: A global analysis from 1990 to 2021","volume":"282","author":"Dong","year":"2025","journal-title":"Eur. Arch. Oto-Rhino-Laryngol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Monasta, L., Ronfani, L., Marchetti, F., Montico, M., Vecchi, B.L., Bavcar, A., Grasso, D., Barbiero, C., and Tamburlini, G. (2012). Burden of disease caused by otitis media: Systematic review and global estimates. PLoS ONE, 7.","DOI":"10.1371\/journal.pone.0036226"},{"key":"ref_5","first-page":"S1","article-title":"Clinical Practice Guideline: Otitis Media with Effusion (Update)","volume":"154","author":"Rosenfeld","year":"2016","journal-title":"Otolaryngol.-Head Neck Surg. Off. J. Am. Acad. Otolaryngol.-Head Neck Surg."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jsurg.2015.07.011","article-title":"Objective Evaluation of Otoscopy Skills Among Family and Community Medicine, Pediatric, and Otolaryngology Residents","volume":"73","author":"Oyewumi","year":"2016","journal-title":"J. Surg. Educ."},{"key":"ref_7","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_8","doi-asserted-by":"crossref","first-page":"32","DOI":"10.2174\/1874609810666170712145332","article-title":"Acute Otitis Media in Children","volume":"11","author":"Leung","year":"2017","journal-title":"Recent Pat. Inflamm. Allergy Drug Discov."},{"key":"ref_9","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-analysis","volume":"47","author":"Habib","year":"2022","journal-title":"Clin. Otolaryngol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"101734","DOI":"10.1016\/j.bspc.2019.101734","article-title":"Convolutional neural network approach for automatic tympanic membrane detection and classification","volume":"56","author":"Basaran","year":"2020","journal-title":"Biomed. Signal Proces."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e1382","DOI":"10.1097\/MAO.0000000000003210","article-title":"A Web-Based Deep Learning Model for Automated Diagnosis of Otoscopic Images","volume":"42","author":"Tsutsumi","year":"2021","journal-title":"Otol. Neurotol."},{"key":"ref_12","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_13","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1002\/lary.28292","article-title":"Otoscopic diagnosis using computer vision: An automated machine learning approach","volume":"130","author":"Livingstone","year":"2020","journal-title":"Laryngoscope"},{"key":"ref_14","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":"ref_15","doi-asserted-by":"crossref","first-page":"104036","DOI":"10.1016\/j.compbiomed.2020.104036","article-title":"A comparative study of pre-trained convolutional neural networks for semantic segmentation of breast tumors in ultrasound","volume":"126","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e35150","DOI":"10.2196\/35150","article-title":"Assessing the Generalizability of Deep Learning Models Trained on Standardized and Nonstandardized Images and Their Performance Against Teledermatologists: Retrospective Comparative Study","volume":"5","author":"Oloruntoba","year":"2022","journal-title":"JMIR Dermatol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/JBHI.2023.3329231","article-title":"AD-CAM: Enhancing Interpretability of Convolutional Neural Networks with a Lightweight Framework-From Black Box to Glass Box","volume":"28","author":"Iqbal","year":"2023","journal-title":"IEEE J. Biomed. Health"},{"key":"ref_18","unstructured":"Wu, M., Yang, E., Qi, X., Xie, R., and Bai, Z. (2019). High-performance medicine: The convergence of human and artificial intelligence. J. Alloys Compd."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2688","DOI":"10.1007\/s10278-024-01362-w","article-title":"Development and Validation of a Modality-Invariant 3D Swin U-Net Transformer for Liver and Spleen Segmentation on Multi-Site Clinical Bi-parametric MR Images","volume":"38","author":"Zhang","year":"2025","journal-title":"J. Imaging Inform. Med."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, M., Ma, J., and Zhao, J. (2025). LKDA-Net: Hierarchical transformer with large Kernel depthwise convolution attention for 3D medical image segmentation. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0329806"},{"key":"ref_21","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_22","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2023, January 2\u20136). Swin Transformer: Hierarchical Vision Transformer using Shifted Windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1398","DOI":"10.1109\/JBHI.2023.3348436","article-title":"Is Attention all You Need in Medical Image Analysis? A Review","volume":"28","author":"Papanastasiou","year":"2024","journal-title":"IEEE J. Biomed. Health"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1109\/TMI.2023.3326188","article-title":"Slim UNETR: Scale Hybrid Transformers to Efficient 3D Medical Image Segmentation Under Limited Computational Resources","volume":"43","author":"Pang","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_25","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":"ref_26","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11263-017-1004-z","article-title":"Holistically-Nested Edge Detection","volume":"125","author":"Xie","year":"2015","journal-title":"Int. J. Comput. Vision"},{"key":"ref_27","first-page":"13","article-title":"An introduction to image analysis using mathematical morphology","volume":"19","author":"Banerji","year":"2000","journal-title":"IEEE Eng. Med. Biol. Mag. Q. Mag. Eng. Med. Biol. Soc."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1007\/978-3-319-46478-7_29","article-title":"Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks","volume":"Volume 9911","author":"Shen","year":"2016","journal-title":"Computer Vision\u2013ECCV 2016"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mahajan, D., Girshick, R., Ramanathan, V., He, K., and Maaten, L.V.D. (2018, January 8\u201314). Exploring the Limits of Weakly Supervised Pretraining. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 21\u201326). Focal Loss for Dense Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jia, M., Lin, T.Y., Song, Y., and Belongie, S. (2019, January 16\u201320). Class-balanced loss based on effective number of samples. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref_32","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (July, January 26). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_35","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_36","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., and J\u00e9gou, H. (2021, January 18\u201324). Training Data-Efficient Image Transformers & Distillation through Attention. Proceedings of the International Conference on Machine Learning, Virtual."},{"key":"ref_37","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":"ref_38","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s42519-024-00422-2","article-title":"Advances in Deep Learning for Medical Image Analysis: A Comprehensive Investigation","volume":"19","author":"Kumar","year":"2025","journal-title":"J. Stat. Theory Pract."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Choi, Y., Chae, J., Park, K., Hur, J., Kweon, J., and Ahn, J.H. (2022). Automated multi-class classification for prediction of tympanic membrane changes with deep learning models. PLoS ONE, 17.","DOI":"10.1371\/journal.pone.0275846"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sandstr\u00f6m, J., Myburgh, H., Laurent, C., Swanepoel, 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_42","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1136\/jim-2021-001870","article-title":"Artificial intelligence to diagnose ear disease using otoscopic image analysis: A review","volume":"70","author":"Canares","year":"2022","journal-title":"J. Investig. Med."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Koyama, H., Kashio, A., and Yamasoba, T. (2024). Application of Artificial Intelligence in Otology: Past, Present, and Future. J. Clin. Med., 13.","DOI":"10.3390\/jcm13247577"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/3\/482\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T05:12:53Z","timestamp":1770441173000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/3\/482"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":43,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["diagnostics16030482"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16030482","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]}}}