Real-Time Markerless Tooth Detection Towards Dynamic Robot-Assisted Dental Implant Navigation
Dentistry Journal · 05.06.2026 · 14 (6) · 345
DOI: 10.3390/dj14060345 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentistry Journal, online erschienen am 05.06.2026. Verfasst von Vasile Bulbucan und 11 weiteren Autor:innen. Beteiligte Einrichtung: CESTER, (Research Center for Industrial Robots Simulation and Testing), Department of Mechanical Systems Engineering, Faculty of Industrial Engineeri…. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Romanian Hub for Artificial Intelligence-HRIA, Technologically Enabled Advancements in Dental Medicine.
Abstract (Originalsprache)
Background/Objectives: Dynamic navigation and robot-assisted implant workflows depend on robust intraoral perception. Marker-based tracking introduces workflow complexity and is sensitive to occlusions, motivating markerless alternatives. This study evaluates whether a single-stage YOLO instance segmentation model (YOLO-seg) can provide a practical markerless perception layer for dental navigation, combining accurate per-tooth delineation with low, predictable inference latency.
Methods
YOLO-seg was trained end to end on an intraoral RGB corpus of 400 training, 20 validation, and 100 testing images, combining a public source and a partner-hospital in-house set. A two-stage YOLO + SAM baseline was implemented for comparison. Segmentation quality was evaluated on a 50-image held-out clinical test set at three complementary levels (per-instance matching, per-class union, and global union), with paired Wilcoxon signed-rank tests, Cliff’s delta effect sizes, and 95% bootstrap confidence intervals. Runtime was assessed under matched inference-only and end-to-end conditions on N = 100 frames at a 640 × 640 resolution on an NVIDIA RTX A2000 GPU.
Results
YOLO-seg significantly outperformed YOLO + SAM across all primary metrics, with very large effect sizes (Cliff’s delta: 0.76–0.94; Wilcoxon p < 10−8 on every metric except precision at IoU ≥ 0.5). YOLO-seg reached AP50 = 0.716 and recall = 0.973 versus 0.383 and 0.398 for YOLO + SAM. Under matched inference-only timing, YOLO-seg ran at 27.08 ms per frame (36.9 FPS) versus 1302.78 ms (0.77 FPS), an approximately 48-fold latency gap intrinsic to the two-stage forward pass.
Conclusions
YOLO-seg shows strong potential as a 2D perception module for dental navigation, balancing per-instance segmentation fidelity with real-time feasibility under the tested conditions. These results support its use as a 2D perception front-end for future integration with stereo-based 3D reconstruction and robot-assisted navigation; 3D registration accuracy, implant-placement error, and robotic execution remain outside the scope of the present study.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- CESTER, (Research Center for Industrial Robots Simulation and Testing), Department of Mechanical Systems Engineering, Faculty of Industrial Engineering, Robotics and Production Management, Technical University of Cluj-N…
- European University of Technology, European Union.
- Department of Maxillofacial Surgery and Radiology, Oral Radiology, "Iuliu Hatieganu" University of Medicine and Pharmacy, 400006 Cluj-Napoca, Romania.
- Department of Maxillofacial Surgery and Radiology, Maxillofacial Surgery and Implantology, "Iuliu Hatieganu" University of Medicine and Pharmacy, 400429 Cluj-Napoca, Romania.
- Technical Sciences Academy of Romania, B-dul Dacia, 26, 030167 Bucharest, Romania.
ORCID-Profile: Daria Pisla, Paul Tucan, Cristian Dinu, Calin Vaida, Sebastian Stoia, Ionut Zima, Doina Pisla
Förderung
- Romanian Hub for Artificial Intelligence-HRIA
- Technologically Enabled Advancements in Dental Medicine
Zitieren
APA
Bulbucan, V., Pisla, D., Tucan, P., Dinu, C., Vaida, C., Mocan, R., Baciut, M., Stoia, S., Hedesiu, M., Zima, I., Pisla, D., & Team Project Group (2026). Real-Time Markerless Tooth Detection Towards Dynamic Robot-Assisted Dental Implant Navigation. Dentistry Journal, 14(6), 345. https://doi.org/10.3390/dj14060345
Vancouver
Bulbucan V, Pisla D, Tucan P, Dinu C, Vaida C, Mocan R, et al. Real-Time Markerless Tooth Detection Towards Dynamic Robot-Assisted Dental Implant Navigation. Dentistry Journal. 2026;14(6):345. doi:10.3390/dj14060345
BibTeX
@article{Bulbucan2026,
author = {Bulbucan, Vasile and Pisla, Daria and Tucan, Paul and Dinu, Cristian and Vaida, Calin and Mocan, Rares and Baciut, Mihaela and Stoia, Sebastian and Hedesiu, Mihaela and Zima, Ionut and Pisla, Doina and Team Project Group},
title = {Real-Time Markerless Tooth Detection Towards Dynamic Robot-Assisted Dental Implant Navigation},
journal = {Dentistry Journal},
year = {2026},
volume = {14},
number = {6},
pages = {345},
doi = {10.3390/dj14060345}
}
EUVIMED