Artificial Intelligence-Based CBCT Segmentation in the Presence of Metallic Artefacts for 3D Virtual Orofacial Patient Generation.
Authors
Affiliations (5)
Affiliations (5)
- Division of Oral Radiology, Department of Oral Diagnosis, Piracicaba Dental School, University of Campinas (UNICAMP), Piracicaba, São Paulo, Brazil.
- Department of Stomatology, Public Health and Forensic Dentistry, Division of Oral Radiology, School of Dentistry of Ribeirão Preto, University of São Paulo, Ribeirão Preto, São Paulo, Brazil; OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven, Leuven, Belgium; Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium. Electronic address: [email protected].
- OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven, Leuven, Belgium; Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium; Department of Prosthodontics, Faculty of Dentistry, Tanta University, 31511 Tanta, Egypt.
- Department of Oral Health Science, Research unit Periodontology and Oral Microbiology/UZ Leuven, Restorative Dentistry, Leuven, Belgium.
- OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven, Leuven, Belgium; Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium; Department of Dental Medicine, Karolinska Institute, Stockholm, Sweden.
Abstract
To evaluate the feasibility of utilising artificial intelligence (AI)-based segmentation of cone-beam computed tomography (CBCT) images in the generation of three-dimensional virtual patients, particularly in contexts complicated by the presence of metallic artefacts. Crown preparations were performed on the mandibular second premolars of a validated human head phantom, followed by intraoral scanning with a TRIOS scanner. Custom zirconia crowns were digitally designed and milled. The phantom was scanned using two CBCT units under four conditions simulating different crown placements. CBCT datasets were processed using an AI-driven platform for automatic segmentation of mandibular teeth, mandible, and zirconia crowns. Segmentation accuracy was evaluated by registering intraoral scan, crown design, CBCT without zirconia crowns, and AI-segmented models, followed by quantitative surface comparison using root mean square (RMS) and median surface deviation (MSD). AI-based segmentation was generally accurate across all experimental conditions and CBCT units, with complete 3D models showing RMS values of 0.17-0.30 mm and near-zero MSD values, indicating minimal spatial misalignment. Segmentation accuracy was highest for mandibular teeth and mandible (RMS: 0.03-0.34 mm), while zirconia crowns exhibited greater deviations (RMS: 0.66-0.95 mm), likely due to metallic artefacts. AI-based CBCT segmentation for generating 3D virtual patients is feasible, even in cases complicated by metallic artefacts. Zirconia crowns had minimal impact on segmentation accuracy for mandibular teeth and the mandible, though zirconia crown segmentation was more affected. Expert clinical supervision remains essential to ensure the reliability and accuracy of these virtual models. AI-based CBCT segmentation can reliably generate 3D models of the mandible and teeth, even in the presence of zirconia crowns. This suggests a promising alternative to intraoral scanning in specific clinical scenarios, provided that expert validation is ensured.