Performance assessment of five artificial intelligence‐based algorithms for automated tooth segmentation and labeling on intraoral scans
Journal of Prosthodontics · 2026-08 · 35 (7) · 1046-1057
DOI: 10.1111/jopr.70117 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Journal of Prosthodontics, online erschienen am 22.04.2026. Verfasst von Germán Del Cacho-Salvador und 7 weiteren Autor:innen. Beteiligte Einrichtung: Doctoral Programme in Research in Information Technologies, Artificial Intelligence Area, University of Santiago de Compostela, Madrid, Spain. Hauptthemen laut MEDLINE: Algorithms, Artificial Intelligence, Tooth, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Ortodentis dental laboratory.
Abstract (Originalsprache)
Purpose
This study aimed to evaluate and compare the performance of five AI algorithms for tooth segmentation and labeling on intraoral scans, as their performance remains unclear. Materials and Methods A total of 100 intraoral scans in the STL file format were classified into two main groups: complete dentition (C) and partial dentition (P, fewer than 12 teeth). Each group was further divided by arch into four subgroups ( n = 25 each): complete maxillary (Mx‐C), complete mandibular (Md‐C), partial maxillary (Mx‐P), and partial mandibular (Md‐P). The algorithms tested were the Tooth Group Network (Team CGIP), Dentbird Studio (Dentbird), Medit Ortho Simulation (Medit), NemoSmile 3D (Nemotec), and MovumStudio (MovumTech). Manual segmentations by an expert operator served as the ground truth. Performance was assessed using Python and five metrics, with Intersection over Union (IOU) as the primary indicator. Statistical analysis included permutation tests with the Bonferroni–Holm correction ( α = 0.05).
Results
Significant differences were observed between groups and algorithms ( P < 0.05). IOU scores ranged from 0.72 to 0.92 in complete dentition and showed greater variability in partial dentition (0–0.928). The Tooth Group Network and MovumStudio consistently outperformed the others, with MovumStudio achieving the highest performance across all metrics and groups. Its performance matched that of a human expert when compared against a subset of the data.
Conclusions
Tooth segmentation and labeling performance vary depending on dentition completeness and algorithm choice. MovumStudio demonstrated the most robust and consistent results, comparable to expert human annotation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Doctoral Programme in Research in Information Technologies, Artificial Intelligence Area, University of Santiago de Compostela, Madrid, Spain.
- MovumTech, Madrid, Spain.
- Director and Dental Laboratory Technician, Ortodentis, Madrid, Spain.
- Faculty of Restorative Dentistry and Biomaterials Sciences, Harvard School of Dental Medicine, Boston, Massachusetts, USA.
- Faculty of Periodontology, Complutense University of Madrid, Madrid, Spain.
- Affiliate Faculty Graduate in Esthetic Dentistry Program, Complutense University of Madrid, Madrid, Spain.
ORCID-Profile: Xavier Paolo Burgos-Artizzu, Joaquín García-Arranz, Óscar González-Martín, Carlos Oteo-Morilla, Wenceslao Piedra-Cascón
Förderung
- Ortodentis dental laboratory
Zitieren
APA
Cacho-Salvador, G. D., Burgos-Artizzu, X. P., García-Arranz, J., González-Martín, Ó., Oteo-Morilla, C., Gallas-Torreira, M., Cernadas, E., & Piedra-Cascón, W. (2026). Performance assessment of five artificial intelligence‐based algorithms for automated tooth segmentation and labeling on intraoral scans. Journal of Prosthodontics, 35(7), 1046-1057. https://doi.org/10.1111/jopr.70117
Vancouver
Cacho-Salvador GD, Burgos-Artizzu XP, García-Arranz J, González-Martín Ó, Oteo-Morilla C, Gallas-Torreira M, et al. Performance assessment of five artificial intelligence‐based algorithms for automated tooth segmentation and labeling on intraoral scans. Journal of Prosthodontics. 2026;35(7):1046-1057. doi:10.1111/jopr.70117
BibTeX
@article{CachoSalvador2026,
author = {Cacho-Salvador, Germán Del and Burgos-Artizzu, Xavier Paolo and García-Arranz, Joaquín and González-Martín, Óscar and Oteo-Morilla, Carlos and Gallas-Torreira, Mercedes and Cernadas, Eva and Piedra-Cascón, Wenceslao},
title = {Performance assessment of five artificial intelligence‐based algorithms for automated tooth segmentation and labeling on intraoral scans},
journal = {Journal of Prosthodontics},
year = {2026},
volume = {35},
number = {7},
pages = {1046--1057},
doi = {10.1111/jopr.70117}
}
EUVIMED