Assessing outcomes of ear molding therapy by health care providers and convolutional neural network
Open accessAbstract
Ear molding therapy is a nonsurgical technique to correct certain congenital auricular deformities. While the advantages of nonsurgical treatments over otoplasty are well-described, few studies have assessed aesthetic outcomes. In this study, we compared assessments of outcomes of ear molding therapy for 283 ears by experienced healthcare providers and a previously developed deep learning CNN model. 2D photographs of ears were obtained as a standard of care in our onsite photography studio. Physician assistants (PAs) rated the photographs using a 5-point Likert scale ranging from 1(poor) to 5(excellent) and the CNN assessment was categorical, classifying each photo as either “normal” or “deformed”. On average, the PAs classified 75.6% of photographs as good to excellent outcomes (scores 4 and 5). Similarly, the CNN classified 75.3% of the photographs as normal. The inter-rater agreement between the PAs ranged between 72 and 81%, while there was a 69.6% agreement between the machine model and the inter-rater majority agreement between at least two PAs (i.e., when at least two PAs gave a simultaneous score < 4 or ≥ 4). This study shows that noninvasive ear molding therapy has excellent outcomes in general. In addition, it indicates that with further training and validation, machine learning techniques, like CNN, have the capability to accurately mimic provider assessment while removing the subjectivity of human evaluation making it a robust tool for ear deformity identification and outcome evaluation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Nonsurgical approaches, such as newborn auricular molding, leverage early cartilage plasticity with promising outcomes.
“Nonsurgical approaches, such as newborn auricular molding, leverage early cartilage plasticity with promising outcomes.70–73”
From Otoplasty Surgical Techniques and Clinical Outcomes: A Practical Review (2026) · cites this paper as [71]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · see citing works
(2016) · Cited by 11,679 · see citing works
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447 · see citing works
Ear Molding in Newborn Infants with Auricular Deformities
Byrd, H. S., Langevin, C.-J., & Ghidoni, L. A. (2010) · Plastic and Reconstructive Surgery · doi:10.1097/prs.0b013e3181e617bb · Cited by 178 · see citing works
Fleet, D. J., Tuytelaars, T., Schiele, B., & Pajdla, T. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9 · Cited by 173 · see citing works
Ensembles of Deep Learning Models and Transfer Learning for Ear Recognition
Alshazly, H. A., Linse, C., Barth, E., & Martinetz, T. (2019) · Sensors · doi:10.3390/s19194139 · Cited by 85 · see citing works
Daniali, L. N., Rezzadeh, K., Shell, C., Trovato, M., Ha, R., & Byrd, H. S. (2017) · Plastic & Reconstructive Surgery · doi:10.1097/prs.0000000000003150 · Cited by 82 · see citing works
Deep Convolutional Neural Networks for Unconstrained Ear Recognition
Alshazly, H. A., Linse, C., Barth, E., & Martinetz, T. (2020) · IEEE Access · doi:10.1109/access.2020.3024116 · Cited by 72 · see citing works
Handcrafted versus CNN Features for Ear Recognition
Alshazly, H. A., Linse, C., Barth, E., & Martinetz, T. (2019) · Symmetry · doi:10.3390/sym11121493 · Cited by 64 · see citing works
A brief review of the ear recognition process using deep neural networks
Galdámez, P. L., Raveane, W., & Arrieta, A. G. (2016) · Journal of Applied Logic · doi:10.1016/j.jal.2016.11.014 · Cited by 63 · see citing works
Cho, M., Hallac, R. R., Effendi, M., Seaward, J. R., & Kane, A. A. (2018) · Scientific Reports · doi:10.1038/s41598-018-24756-7 · Cited by 46 · see citing works
Self-citationIdentifying Ear Abnormality from 2D Photographs Using Convolutional Neural Networks
Hallac, R. R., Lee, J., Pressler, M. P., Seaward, J. R., & Kane, A. A. (2019) · Scientific Reports · doi:10.1038/s41598-019-54779-7 · Cited by 46 · see citing works
Self-citationNeonatal ear molding: timing and technique.
Anstadt, E. E., Johns, D. N., Kwok, A. C.-M., Siddiqi, F., & Gociman, B. (2016) · PEDIATRICS · doi:10.1542/peds.2015-2831 · Cited by 44 · see citing works
Metopic “ridge” vs. “craniosynostosis”: Quantifying severity with 3D curvature analysis
Cho, M., Kane, A. A., Seaward, J. R., & Hallac, R. R. (2016) · Journal of Cranio-Maxillofacial Surgery · doi:10.1016/j.jcms.2016.06.019 · Cited by 34 · see citing works
Self-citationNewborn ear deformities: early recognition and novel nonoperative techniques
Schultz, K., Guillen, D., & Maricevich, R. (2017) · Seminars in Plastic Surgery · doi:10.1055/s-0037-1603958 · Cited by 34 · see citing works
Petersson, R. S., Recker, C. A., Martin, J. R. K., Driscoll, C. L. W., & Friedman, O. (2012) · International Journal of Pediatric Otorhinolaryngology · doi:10.1016/j.ijporl.2012.06.011 · Cited by 33 · see citing works
(2012) · PubMed · Cited by 31 · see citing works
Deformations of the Ear and Their Nonsurgical Correction
Chang, C. S., & Bartlett, S. P. (2019) · Clinical Pediatrics · doi:10.1177/0009922819844296 · Cited by 30 · see citing works
A simplified nonsurgical method for the correction of neonatal deformational auricular anomalies.
Chang, C. S., & Bartlett, S. P. (2017) · Clinical Pediatrics · doi:10.1177/0009922816641368 · Cited by 30 · see citing works
Non-surgical Correction of Congenital Ear Anomalies: A Review of the Literature
Feijen, M. M. W., van Cruchten, C., Payne, P. E., & van der Hulst, R. R. W. J. (2020) · Plastic and Reconstructive Surgery - Global Open · doi:10.1097/gox.0000000000003250 · Cited by 22 · see citing works
Correction of Cryptotia Using an External Stretching Device
Park, C. (2002) · Annals of Plastic Surgery · doi:10.1097/00000637-200205000-00015 · Cited by 14 · see citing works
Effectiveness of ear splint therapy for ear deformities.
Woo, J. E., Park, Y.-H., Park, E. J., Park, K. Y., Kim, S. H., & Yim, S.-Y. (2017) · Annals of Rehabilitation Medicine · doi:10.5535/arm.2017.41.1.138 · Cited by 14 · see citing works
Reply: “Nonsurgical Correction of Congenital Ear Anomalies: A Review of the Literature”
Feijen, M. M. W., van Cruchten, C., & van der Hulst, R. R. W. J. (2021) · Plastic & Reconstructive Surgery Global Open · doi:10.1097/gox.0000000000003562 · Cited by 9 · see citing works
Hallac, R. R., Dumas, B. M., Seaward, J. R., Herrera, R., Menzies, C., & Kane, A. A. (2018) · The Cleft Palate-Craniofacial Journal · doi:10.1177/1055665618787399 · Cited by 9 · see citing works
Self-citation
Flagged first, then by citations
3 of the 27 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- [17]Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2921–2929.
- [18]Selvaraju, R. R. et al. in 2017 IEEE International Conference on Computer Vision (ICCV). 618–626.
- [25]Wetz, E. et al. in The American Cleft Palate-Craniofacial Association Vol. 56, 1–130 (Cleft Palate Craniofac J, Tucson, Arizona, 2019).
Cited by
Sorted by citations
Atiyeh, B. S., Emsieh, S., Hakim, C. A., & Chalhoub, R. S. (2023) · Aesthetic Plastic Surgery · doi:10.1007/s00266-023-03328-9 · Cited by 42 · see citing works
“Furthermore, a study conducted by Hallac et al. [23] comparing outcome assessment of ear molding therapy by experienced healthcare providers to assessment by a deep learning CNN model in 283 ears has demonstrated that ML techniques have the capability to accurately mimic provider assessment of…”
Artificial Intelligence Applications in Pediatric Craniofacial Surgery
Harrison, L. M., Edison, R. L., & Hallac, R. R. (2025) · Diagnostics · doi:10.3390/diagnostics15070829 · Cited by 28 · see citing works
“Pediatric craniofacial surgery stands to benefit substantially from these technologies [12,13].”
Self-citationExploring the Utility of ChatGPT in Cleft Lip Repair Education
Mahedia, M., Rohrich, R. N., Sadiq, K. O., Bailey, L., Harrison, L. M., & Hallac, R. R. (2025) · Journal of Clinical Medicine · doi:10.3390/jcm14030993 · Cited by 19 · see citing works
Self-citationWang, D., Chen, X., Wu, Y., Tang, H., & Deng, P. (2022) · Frontiers in Surgery · doi:10.3389/fsurg.2022.929110 · Cited by 18 · see citing works
“Besides, CNN was demonstrated to be a robust tool for assessing outcomes of ear molding therapy by removing the subjectivity of human evaluation (14).”
MethodArtificial Intelligence in Facial Plastics and Reconstructive Surgery
Park, K. W., Diop, M., Hewett, S., & Pepper, J. (2024) · Otolaryngologic Clinics of North America · doi:10.1016/j.otc.2024.05.002 · Cited by 17 · see citing works
A novel method to accurately locate the reconstructed auricle
Sun, P., Wang, C., Huang, X., & Pan, B. (2022) · Translational Pediatrics · doi:10.21037/tp-21-453 · Cited by 10 · see citing works
A publicly available newborn ear shape dataset for medical diagnosis of auricular deformities
Ren, L., Luo, F., Yang, Z., Chen, L., Wang, X., Li, C., Xie, Y., Wang, J., Zhang, T., Wang, S., et al. (2024) · Scientific Data · doi:10.1038/s41597-023-02834-4 · Cited by 8 · see citing works
“Researches have also been conducted to identify the auricular deformities and evaluate the corrective effects using convolutional neural networks 14,15 .”
MethodRen, L., Yang, R.-J., Chen, L., Wang, S., Li, C., Huang, Y., Zhang, T., Fu, Y., & Wang, S. (2025) · EClinicalMedicine · doi:10.1016/j.eclinm.2025.103124 · Cited by 6 · see citing works
Applications of Machine Learning in Facial Cosmetic Surgeries: A Scoping Review
Ahmadi, N., Niazmand, M., Ghasemi, A., Mohaghegh, S., & Motamedian, S. R. (2023) · Aesthetic Plastic Surgery · doi:10.1007/s00266-023-03379-y · Cited by 6 · see citing works
“Image pre-processing stages were resizing to a similar size [19, 27, 47], normalization [24, 26, 34], crop region of interest [19, 22, 25, 26, 31, 36, 37], landmark detection [20, 21, 22, 24, 26, 27, 31–33, 37, 43], image augmentation [34], mesh generation [43], and feature extraction 166 EMBASE…”
BackgroundMethodInfluentialYoussef, B., Alksas, A., Shalaby, A. M., Mahmoud, A. H., van Bogaert, E., Contractor, S. G., Ghazal, M. A., Elmaghraby, A. S., & El-Baz, A. S. (2023) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi53787.2023.10230705 · Cited by 5 · see citing works
Ear Molding in Children—Timing, Technique, and Follow-up: A Systematic Review
Sulibhavi, A., Reddy, S. P., Butts, S. C., & Schmalbach, C. E. (2024) · Facial Plastic Surgery & Aesthetic Medicine · doi:10.1089/fpsam.2023.0321 · Cited by 4 · see citing works
“56 Several studies did include blinded ratings of posttreatment photographs that can offer strength to the reported judgments and minimize bias.”
Motie, P., Hemmati, G., Hazrati, P., Lazar, M., Varzaneh, F. A., Mohammad‐Rahimi, H., Golkar, M., & Motamedian, S. R. (2023) · Springer eBooks · doi:10.1007/978-981-19-8602-4_15 · Cited by 4 · see citing works
Efficiency of ear molding for treating constricted ears of different severity
Zhang, L., Huang, J., Lei, Y., & Li, X. (2024) · American Journal of Otolaryngology · doi:10.1016/j.amjoto.2024.104397 · Cited by 1 · see citing works
Shalaby, A. M., Dekhil, O., Chitta, K. K., Lee, H., German, D. C., & Lee, J. (2024) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi62660.2024.10913719 · Cited by 1 · see citing works
“One of the major problems facing medical applications of machine learning is the imbalance between the large number of features and the limited number of subjects [25], [26].”
Self-citationOtoplasty Surgical Techniques and Clinical Outcomes: A Practical Review
Kaleeny, J. D., & Janis, J. E. (2026) · Plastic and Reconstructive Surgery - Global Open · doi:10.1097/gox.0000000000007404
Enhancing AI Diagnosis of Congenital Auricular Deformities With Multicenter Data Sets
Li, H., Zhou, X., & Qi, X. (2025) · Journal of Craniofacial Surgery · doi:10.1097/scs.0000000000010826
Feng, Y., Hu, X., Zhang, X., Ma, X., Xie, J., Chen, J., & Yuan, Y. (2026) · Biology · doi:10.3390/biology15130985
“Prior research has predominantly relied on the prediction confidence of classification networks as a proxy metric for deformity severity [16,19].”
- Authors
- Hallac, R. R., Jackson, S. A., Grant, J., Fisher, K., Scheiwe, S., Wetz, E., Perez, J., Lee, J., Chitta, K., Seaward, J. R., & Kane, A. A.
- Affiliations
- Children's Medical Center (US)
- The University of Texas Southwestern Medical Center (US)
- Corresponding author
- Hallac, Rami R.
- Venue
- Scientific Reports
- Published
- 2021-09-09
- Volume
- 11
- Issue
- 1
- Pages
- 17875-17875
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC8429730
- OpenAlex
- W3198893119
- Cited by
- 17
- References
- 27
- Citations by year
- 2026: 2 · 2025: 4 · 2024: 5 · 2023: 4 · 2022: 2
- FWCI
- 2.58
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Cancer Prevention and Research Institute of Texas (RP150596)
- Topics
- Health Sciences › Medicine › Surgery › Reconstructive Facial Surgery Techniques
- Health Sciences › Medicine › Genetics › Congenital Ear and Nasal Anomalies
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Craniofacial Disorders and Treatments
- Keywords
- congenital auricular deformities, aesthetic outcome assessment, convolutional neural networks, interobserver agreement
- MeSH terms
- Ear Diseases, Ear, External, Esthetics, Health Personnel, Hearing Aids, Humans, Photography, Neural Networks, Computer, Outcome Assessment, Health Care, Plastic Surgery Procedures
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
