Assessing the spatial relationship between mandibular third molars and the inferior alveolar canal using a deep learning-based approach: a proof-of-concept study.
Authors
Affiliations (9)
Affiliations (9)
- Department of Oral and Maxillofacial Surgery, Affiliated Stomatology Hospital of Guangzhou Medical University, Guangdong Engineering Research Center of Oral Restoration and Reconstruction, Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou, Guangdong, 510182, China.
- Department of Stomatology, Shenzhen Guangming District People's Hospital, Shenzhen, Guangdong, 518107, China.
- Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China.
- Department of Oral Implantology, School and Hospital of Stomatology, Guangdong Engineering Research Center of Oral Restoration and Reconstruction & Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou Medical University, Guangzhou, Guangdong, 510182, China.
- The Affiliated Guangdong Second Provincial General Hospital of Jinan University, Guangzhou, Guangdong, 510317, China.
- Guangzhou Panyu Polytechnic, Guangzhou, 511483, China.
- Department of Chemical & Materials Engineering, University of Auckland, Auckland, 1010, New Zealand.
- Department of Stomatology, the Seventh Affiliated Hospital, Sun Yat-Sen University, Shenzhen, Guangdong, 518107, China. [email protected].
- Department of Oral and Maxillofacial Surgery, Affiliated Stomatology Hospital of Guangzhou Medical University, Guangdong Engineering Research Center of Oral Restoration and Reconstruction, Guangzhou Key Laboratory of Basic and Applied Research of Oral Regenerative Medicine, Guangzhou, Guangdong, 510182, China. [email protected].
Abstract
The distance between the mandibular third molar (M3) and the mandibular canal (MC) is a key factor in assessing the risk of injury to the inferior alveolar nerve (IAN). However, existing deep learning systems have not yet been able to accurately quantify the M3-MC distance in 3D space. The aim of this study was to develop and validate a deep learning-based system for accurate measurement of M3-MC spatial relationships in cone-beam computed tomography (CBCT) images and to evaluate its accuracy against conventional methods. We propose an innovative approach for low-resource environments, using DeeplabV3 + for semantic segmentation of CBCT-extracted 2D images, followed by multi-category 3D reconstruction and visualization. Based on the reconstruction model, we applied the KD-Tree algorithm to measure the spatial minimum distance between M3 and MC. Through internal validation with randomly selected CBCT images, we compared the differences between the AI system, conventional measurement methods on the CBCT, and the gold standard measured by senior experts. Statistical analysis was performed using one-way ANOVA with Tukey HSD post-hoc tests (p < 0.05), employing multiple error metrics for comprehensive evaluation. One-way ANOVA revealed significant differences among measurement methods. Subsequent Tukey HSD post-hoc tests showed significant differences between the AI reconstruction model and conventional methods. The measurement accuracy of the AI system compared to the gold standard was 0.19 for mean error (ME), 0.18 for mean absolute error (MAE), 0.69 for mean square error (MSE), 0.83 for root mean square error (RMSE), and 0.96 for coefficient of determination (R<sup>2</sup>) (p < 0.01). These results indicate that the proposed AI system is highly accurate and reliable in M3-MC distance measurement and provides a powerful tool for preoperative risk assessment of M3 extraction.