Single-step prediction of inferior alveolar nerve injury after mandibular third-molar extraction using contrastive
Kyubaek Yoon1, Yiseul Choi2,3, Myoungho Lee2
1Department of Artificial Intelligence and Software, College of Artificial Intelligence, Ewha Womans University, Seoul 03766, Republic of Korea.
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.
