Validation of a novel tool for automated tooth modelling by fusion of CBCT-derived roots with the respective IOS-derived crowns
Issued Date
2025-02-01
Resource Type
ISSN
03005712
Scopus ID
2-s2.0-85214339577
Journal Title
Journal of Dentistry
Volume
153
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Dentistry Vol.153 (2025)
Suggested Citation
Baldini B., Papasratorn D., Fagundes F.B., Fontenele R.C., Jacobs R. Validation of a novel tool for automated tooth modelling by fusion of CBCT-derived roots with the respective IOS-derived crowns. Journal of Dentistry Vol.153 (2025). doi:10.1016/j.jdent.2024.105546 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/102952
Title
Validation of a novel tool for automated tooth modelling by fusion of CBCT-derived roots with the respective IOS-derived crowns
Corresponding Author(s)
Other Contributor(s)
Abstract
Objectives: To validate a novel artificial intelligence (AI)-based tool for automated tooth modelling by fusing cone beam computed tomography (CBCT)-derived roots with corresponding intraoral scanner (IOS)-derived crowns. Methods: A retrospective dataset of 30 patients, comprising 30 CBCT scans and 55 IOS dental arches, was used to evaluate the fusion model at full arch and single tooth levels. AI-fused models were compared with CBCT tooth segmentation using point-to-point surface distances—reported as median surface distance (MSD), root mean square distance (RMSD), and Hausdorff distance (HD)— alongside visual assessments. Qualitative assessment included visual inspection of CBCT multiplanar views. The automated fused model was also compared to expert-manual fusions for single tooth analysis in terms of accuracy, time efficiency, and consistency. Results: AI-based fusion evaluation showed mean values of MSD, RMSD, and HD of 4 μm, 114 μm, and 940 μm for full arch; 5 μm, 104 μm, and 503 μm for single tooth analysis. Qualitative assessment showed discrepancies between fused tooth outline and CBCT tooth margin lower than 1 voxel for 59% of cases. AI-based fusion showed high similarity with expert-manual fusions with median MSD, RMSD, and HD values of 28 μm, 104 μm, and 576 μm, respectively. However, AI-based fusion was 32 times faster than manual fusion. Considering the time required for manual fusion, intra-observer agreement was high (ICC 0.93), while inter-observer agreement was moderate (ICC 0.48). Conclusion: The AI-based CBCT/IOS fusion demonstrated clinically acceptable accuracy, efficiency, and consistency, offering substantial time savings and robust performance across different patients and imaging devices. Clinical significance: Manual CBCT/IOS fusion performed by experts is effective but labor-intensive and time-consuming. AI algorithms show a remarkable ability to minimize human variability, resulting in more reliable and efficient fusion. This capability demonstrates the potential to provide a more personalized, precise and standardized approach for treatment planning and dental procedures.