{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T09:16:38Z","timestamp":1785402998577,"version":"3.56.0"},"reference-count":28,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["782213D00807"],"award-info":[{"award-number":["782213D00807"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"award":["782213D00807"],"award-info":[{"award-number":["782213D00807"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004863","name":"Scientific Research Project of Zhejiang Chinese Medical University","doi-asserted-by":"publisher","award":["781100E035"],"award-info":[{"award-number":["781100E035"]}],"id":[{"id":"10.13039\/501100004863","id-type":"DOI","asserted-by":"publisher"}]},{"award":["781100E035"],"award-info":[{"award-number":["781100E035"]}],"id":[{"id":"https:\/\/ror.org\/04epb4p87","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biology"],"abstract":"<jats:p>Early non-invasive correction of neonatal auricular deformities is highly dependent on timely and precise diagnosis. However, clinical practice is often compromised by the subjectivity of visual assessments and the lack of objective tracking metrics, which frequently leads to missed optimal treatment windows. To address these challenges, we developed an interpretable deep learning-based diagnostic system for the automated screening and fine-grained classification of these deformities. Methodologically, a large-scale, multi-source dataset (n = 4644) was curated to support model training. The system pairs an automated object detector (YOLOv11) for background-reduced region-of-interest isolation with a cascaded classification pipeline optimized via ConvNeXt-Tiny. Crucially, we introduced a supervised contrastive learning module to project high-dimensional morphological features into a continuous severity score, enabling quantitative longitudinal tracking of therapeutic efficacy. To evaluate generalization and robustness, the framework underwent rigorous evaluation across three independent real-world cohorts and one controlled synthetic stress test. The system achieved 88.2% accuracy (Area Under the Curve (AUC): 0.949) in binary screening and 87.4% accuracy (macro-AUC: 0.976) in multi-class subtyping on the internal baseline. To enhance interpretability and build clinical trust, Gradient-weighted Class Activation Mapping (Grad-CAM) was utilized to explore the spatial distribution of the model\u2019s attention, which frequently aligned with key anatomical landmarks. Furthermore, the learned severity scores robustly quantified post-intervention improvements (p = 0.0004), effectively capturing subtle anatomical normalization. While validation for rare subtypes remains underpowered, and the severity score currently functions mainly as a learned morphological similarity index requiring future clinical calibration, this study ultimately provides an objective and standardized web-based tool to facilitate the early intervention and precision management of neonatal auricular anomalies.<\/jats:p>","DOI":"10.3390\/biology15130985","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:41:38Z","timestamp":1782909698000},"page":"985","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Interpretable Deep Learning System for Fine-Grained Classification and Longitudinal Tracking of Neonatal Auricular Deformities"],"prefix":"10.3390","volume":"15","author":[{"given":"Yihui","family":"Feng","sequence":"first","affiliation":[{"name":"School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xujun","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2873-3620","authenticated-orcid":false,"given":"Xiaobao","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology-Head and Neck Surgery, Xinhua Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200092, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6749-9566","authenticated-orcid":false,"given":"Jialin","family":"Xie","sequence":"additional","affiliation":[{"name":"The Second School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianyong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Otorhinolaryngology-Head and Neck Surgery, Xinhua Hospital, Shanghai Jiaotong University School of Medicine, Shanghai 200092, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yangyang","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Medical Technology and Information Engineering, Zhejiang Chinese Medical University, Hangzhou 310053, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1097\/PRS.0000000000003443","article-title":"A morphometric study of the newborn ear and an analysis of factors related to congenital auricular deformities","volume":"140","author":"Zhao","year":"2017","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1007\/s00266-008-9179-x","article-title":"Psychosocial effects of otoplasty in children with prominent ears","volume":"32","author":"Gasques","year":"2008","journal-title":"Aesthetic Plast. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2111","DOI":"10.1016\/j.bjps.2020.05.075","article-title":"The psychological, social and educational impact of prominent ears: A systematic review","volume":"73","author":"Jones","year":"2020","journal-title":"J. Plast. Reconstr. Aesthetic Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0272-7358(97)00047-0","article-title":"The psychology of cosmetic surgery: A review and reconceptualization","volume":"18","author":"Sarwer","year":"1998","journal-title":"Clin. Psychol. Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2705","DOI":"10.1016\/j.bjps.2021.03.023","article-title":"A longitudinal study of changes of congenital auricular deformity regarding self-correction","volume":"74","author":"Kim","year":"2021","journal-title":"J. Plast. Reconstr. Aesthetic Surg."},{"key":"ref_6","first-page":"Doc05","article-title":"Classification and diagnosis of ear malformations","volume":"6","author":"Wulke","year":"2007","journal-title":"GMS Curr. Top. Otorhinolaryngol. Head Neck Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"109999","DOI":"10.1016\/j.ijporl.2020.109999","article-title":"Implementation of auricular malformation screenings in the newborn population","volume":"133","author":"Liu","year":"2020","journal-title":"Int. J. Pediatr. Otorhinolaryngol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1016\/j.bjps.2009.01.020","article-title":"Non-surgical correction of congenital deformities of the auricle: A systematic review of the literature","volume":"62","author":"Breugem","year":"2009","journal-title":"J. Plast. Reconstr. Aesthetic Surg."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"577e","DOI":"10.1097\/PRS.0000000000000999","article-title":"The newborn butterfly project: A shortened treatment protocol for ear molding","volume":"135","author":"Doft","year":"2015","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1007\/s00266-025-05271-3","article-title":"Efficacy analysis of ear molding correction for congenital auricular deformities at different ages","volume":"50","author":"Liu","year":"2025","journal-title":"Aesthetic Plast. Surg."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"205e","DOI":"10.1097\/PRS.0000000000006997","article-title":"Management of congenital auricular anomalies","volume":"146","author":"Joukhadar","year":"2020","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, H., Lv, K., Wu, X., Zhang, Y., Ouyang, Y., Lv, Y., Jiang, Y., Fan, Y., Chen, X., and Meng, H. (2025). Two-dimensional and three-dimensional ultrasonographic diagnosis of congenital auricular anomalies. Front. Med., 12.","DOI":"10.3389\/fmed.2025.1500895"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"657","DOI":"10.14245\/ns.1938396.198","article-title":"Deep learning in medical imaging","volume":"16","author":"Kim","year":"2019","journal-title":"Neurospine"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10916-018-1088-1","article-title":"Medical image analysis using convolutional neural networks: A review","volume":"42","author":"Anwar","year":"2018","journal-title":"J. Med. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"18198","DOI":"10.1038\/s41598-019-54779-7","article-title":"Identifying ear abnormality from 2D photographs using convolutional neural networks","volume":"9","author":"Hallac","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2413","DOI":"10.1002\/lary.30499","article-title":"Use of convolutional neural networks to evaluate auricular reconstruction outcomes for microtia","volume":"133","author":"Tolba","year":"2023","journal-title":"Laryngoscope"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, D., Chen, X., Wu, Y., Tang, H., and Deng, P. (2022). Artificial intelligence for assessing the severity of microtia via deep convolutional neural networks. Front. Surg., 9.","DOI":"10.3389\/fsurg.2022.929110"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103124","DOI":"10.1016\/j.eclinm.2025.103124","article-title":"Artificial intelligence assisted identification of newborn auricular deformities via smartphone application","volume":"81","author":"Ren","year":"2025","journal-title":"eClinicalMedicine"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"17875","DOI":"10.1038\/s41598-021-97310-7","article-title":"Assessing outcomes of ear molding therapy by health care providers and convolutional neural network","volume":"11","author":"Hallac","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1038\/s41597-023-02834-4","article-title":"A publicly available newborn ear shape dataset for medical diagnosis of auricular deformities","volume":"11","author":"Ren","year":"2024","journal-title":"Sci. Data"},{"key":"ref_21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., and Xie, S. (2022, January 18\u201324). A ConvNet for the 2020s. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"101630","DOI":"10.1016\/j.bjorl.2025.101630","article-title":"Efficacy analysis of non-invasive correction for congenital cryptotia with auricular cartilage deformities","volume":"91","author":"Zhou","year":"2025","journal-title":"Braz. J. Otorhinolaryngol."},{"key":"ref_24","first-page":"e106159","article-title":"An empirical study of dataset size effects on fine-tuning depth in transfer learning for chest X-ray classification","volume":"18","author":"Sarkodie","year":"2026","journal-title":"Cureus"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"23948","DOI":"10.1038\/s41598-025-03459-w","article-title":"Reweighting balanced representation learning for long tailed image recognition in multiple domains","volume":"15","author":"Fu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1097\/PRS.0000000000009335","article-title":"Evolution of anomaly-specific techniques in infant ear molding: A 10-year retrospective study","volume":"150","author":"Charipova","year":"2022","journal-title":"Plast. Reconstr. Surg."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"104033","DOI":"10.1016\/j.media.2026.104033","article-title":"PCa-Mamba: Spatiotemporal state space models for prostate cancer detection in multi-parametric MRI","volume":"111","author":"Zhao","year":"2026","journal-title":"Med. Image Anal."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"473","DOI":"10.26599\/CVM.2025.9450512","article-title":"Open-vocabulary camouflaged object segmentation with cascaded vision language models","volume":"12","author":"Zhao","year":"2026","journal-title":"Comput. Vis. Media"}],"container-title":["Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-7737\/15\/13\/985\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T14:49:54Z","timestamp":1782917394000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-7737\/15\/13\/985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":28,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["biology15130985"],"URL":"https:\/\/doi.org\/10.3390\/biology15130985","relation":{},"ISSN":["2079-7737"],"issn-type":[{"value":"2079-7737","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]}}}