EUVIMEDEUVIMED entdecken
Crossref

Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model

Kyubaek Yoon, Yiseul Choi iD, Myoungho Lee, Jaeyeon Kim, Jun-Young Kim, Jin-Woo Kim, Jongeun Choi, Wonse Park iD

Dentomaxillofacial Radiology · 01.02.2026 · 55 (2) · 150-157

DOI: 10.1093/dmfr/twaf069 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 27.09.2025. Verfasst von Kyubaek Yoon und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence and Software, College of Artificial Intelligence, Ewha Womans University, Seoul 03766, Republic of Korea. Hauptthemen laut MEDLINE: Cone-Beam Computed Tomography, Molar, Third, Deep Learning, Tooth Extraction. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Yonsei University College of Dentistry Fund, National Research Foundation of Korea, MSIT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Inferior alveolar nerve (IAN) injury is a critical complication of mandibular third-molar extraction. This study aimed to construct and evaluate a deep learning framework that integrates contrastive learning and Bayesian optimization to enhance predictive performance using cone-beam computed tomography (CBCT) and panoramic radiographs.

Methods

A retrospective dataset of 902 panoramic radiographs and 1,500 CBCT images was used. Five deep learning architectures (MobileNetV2, ResNet101D, Vision Transformer, Twins-SVT, and SSL-ResNet50) were trained with and without contrastive learning and Bayesian optimization. Model performance was evaluated using accuracy, F1-score, and comparison with oral and maxillofacial surgeons (OMFSs).

Results

Contrastive learning significantly improved the F1-scores across all models (e.g., MobileNetV2: 0.302 to 0.740; ResNet101D: 0.188 to 0.689; Vision Transformer: 0.275 to 0.704; Twins-SVT: 0.370 to 0.719; SSL-ResNet50: 0.109 to 0.576). Bayesian optimization further enhanced the F1-scores for MobileNetV2 (from 0.740 to 0.923), ResNet101D (from 0.689 to 0.857), Vision Transformer (from 0.704 to 0.871), Twins-SVT (from 0.719 to 0.857), and SSL-ResNet50 (from 0.576 to 0.875). The AI model outperformed OMFSs on CBCT cross-sectional images (F1-score: 0.923 vs. 0.667) but underperformed on panoramic radiographs (0.666 vs. 0.730).

Conclusions

The proposed single-step deep learning approach effectively predicts IAN injury, with contrastive learning addressing data imbalance and Bayesian optimization enhancing model performance. While artificial intelligence surpasses human performance on CBCT images, panoramic radiograph analysis still benefits from expert interpretation. Future work should focus on multi-center validation and explainable artificial intelligence for broader clinical adoption.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cone-Beam Computed TomographyMolar, ThirdDeep LearningTooth ExtractionMandibular Nerve InjuriesHumansBayes TheoremRetrospective StudiesRadiography, PanoramicMandibleFemaleMaleAdultMandibular Nerve

Stichwörter der Autor:innen

cone-beam computed tomographydeep learningmandibular nervemolaroral surgical proceduresthird

Autor:innen und Institutionen

  • Department of Artificial Intelligence and Software, College of Artificial Intelligence, Ewha Womans University, Seoul 03766, Republic of Korea.
  • Department of Advanced General Dentistry, Yonsei University College of Dentistry, Seoul 03722, Republic of Korea.
  • Yonsei Institute for Digital Health, Yonsei University, Seoul 03722, Republic of Korea.
  • Department of Oral and Maxillofacial Surgery, Yonsei University College of Dentistry, Seoul 03722, Republic of Korea.
  • Department of Oral and Maxillofacial Surgery, School of Medicine, Ewha Womans University, Seoul 07804, Republic of Korea.
  • School of Mechanical Engineering, Yonsei University, Seoul 03722, Republic of Korea.

ORCID-Profile: Yiseul Choi, Wonse Park

Förderung

  • Yonsei University College of Dentistry Fund
  • National Research Foundation of Korea
  • MSIT
  • Institute of Information & Communications Technology Planning & Evaluation

Zitieren

APA

Yoon, K., Choi, Y., Lee, M., Kim, J., Kim, J. Y., Kim, J. W., Choi, J., & Park, W. (2026). Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model. Dentomaxillofacial Radiology, 55(2), 150-157. https://doi.org/10.1093/dmfr/twaf069

Vancouver

Yoon K, Choi Y, Lee M, Kim J, Kim JY, Kim JW, et al. Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model. Dentomaxillofacial Radiology. 2026;55(2):150-157. doi:10.1093/dmfr/twaf069

BibTeX
@article{Yoon2026,
  author = {Yoon, Kyubaek and Choi, Yiseul and Lee, Myoungho and Kim, Jaeyeon and Kim, Jun-Young and Kim, Jin-Woo and Choi, Jongeun and Park, Wonse},
  title = {Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive learning and Bayesian auto-tuned deep learning model},
  journal = {Dentomaxillofacial Radiology},
  year = {2026},
  volume = {55},
  number = {2},
  pages = {150--157},
  doi = {10.1093/dmfr/twaf069}
}
Kostenlos starten →