AI-based 3D measurement of root canal curvature from CBCT: Validation of an automated Schneider angle analysis.
Authors
Affiliations (3)
Affiliations (3)
- Department of Endodontics, Faculty of Dentistry, Akdeniz University, Antalya, Turkey.
- Department of Endodontics, Faculty of Dentistry, Burdur Mehmet Akif Ersoy University, Burdur, Turkey. Electronic address: [email protected].
- Department of Restorative, Preventive and Pediatric Dentistry, School of Dental Medicine, University of Bern, Bern, Switzerland.
Abstract
Conventional 2D curvature assessment methods are insufficient to capture the complex 3D geometry of root canals. This study aimed to develop and validate a deep learning-based pipeline for automated 3D Schneider angle measurement from cone-beam computed tomography (CBCT) images of mandibular molar mesial roots and to evaluate its agreement with expert manual measurements. A 3D nnU-Net segmentation model was developed using 331 training/validation CBCT volumes and evaluated on an independent held-out test set of 50 cases comprising 127 canal segments. Automated Schneider angles were compared with reference measurements obtained by 2 experienced endodontists performing blinded, repeated measurements across 2 sessions. Agreement was assessed using intraclass correlation coefficients (ICC), Bland-Altman analysis, and quadratic weighted kappa. The equivalence margin was set at ±5°. Overall, AI-manual agreement was good (ICC = 0.890; 95% CI: 0.840-0.920), with a mean bias of +0.88° (limits of agreement: -6.51° to +8.27°). Agreement was highest for common segments in Vertucci Type II configurations (ICC = 0.947). Mesiobuccal canals showed a small but statistically significant positive bias (+1.45°; p < 0.05). Schneider category agreement was substantial (quadratic weighted κ = 0.717). Mean-difference equivalence was demonstrated within the prespecified ±5° margin for all canal types (all p < 0.05), although the 95% limits of agreement extended beyond the ±5° margin at the individual-measurement level. This internal validation study suggests that the AI-assisted workflow can approximate expert 3D Schneider angle measurements at the mean-difference level; however, external validation and stronger individual-level agreement are required before clinical implementation.