EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluation of the Performance of a YOLOv10-Based Deep Learning Model for Tooth Detection and Numbering on Panoramic Radiographs of Patients in the Mixed Dentition Period

Ramazan Berkay Peker iD, Celal Oguz Kurtoglu iD

Diagnostics · 07.02.2025 · 15 (4) · 405

DOI: 10.3390/diagnostics15040405 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 07.02.2025. Verfasst von Ramazan Berkay Peker und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Trakya University, Edirne 22030, Turkey. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study evaluated the performance of a YOLOv10-based deep learning model in detecting and numbering teeth in the panoramic radiographs of pediatric patients in the mixed dentition period.

Methods

Panoramic radiographic images from 200 pediatric patients in the mixed dentition period, each with at least 10 primary teeth and underlying permanent tooth germs, were included in the study. A total of 8153 teeth in these panoramic radiographs were manually labeled. The dataset was divided for the development of a YOLOv10-based artificial intelligence model, with 70% used for training, 15% for testing, and 15% for validation.

Results

The precision, recall, mAP50, mAP50-95, and F1 score of the model for tooth detection and numbering were found to be 0.90, 0.94, 0.968, 0.696, and 0.919, respectively.

Conclusions

YOLOv10-based deep learning models can be used to accurately detect and number primary and permanent teeth in the panoramic radiographs of pediatric patients in the mixed dentition period, which can support clinicians in their daily practice. Future works may focus on model optimization across varied pediatric cases to enhance clinical applicability.

Schlagwörter

Stichwörter der Autor:innen

YOLOartificial intelligencepanoramic radiographypediatric dentistrytooth classification

Autor:innen und Institutionen

  • Department of Dentomaxillofacial Radiology, Faculty of Dentistry, Trakya University, Edirne 22030, Turkey.
  • Department of Computer Engineering, Faculty of Engineering, Cukurova University, Adana 01330, Turkey.

ORCID-Profile: Ramazan Berkay Peker, Celal Oguz Kurtoglu

Zitieren

APA

Peker, R. B., & Kurtoglu, C. O. (2025). Evaluation of the Performance of a YOLOv10-Based Deep Learning Model for Tooth Detection and Numbering on Panoramic Radiographs of Patients in the Mixed Dentition Period. Diagnostics, 15(4), 405. https://doi.org/10.3390/diagnostics15040405

Vancouver

Peker RB, Kurtoglu CO. Evaluation of the Performance of a YOLOv10-Based Deep Learning Model for Tooth Detection and Numbering on Panoramic Radiographs of Patients in the Mixed Dentition Period. Diagnostics. 2025;15(4):405. doi:10.3390/diagnostics15040405

BibTeX
@article{Peker2025,
  author = {Peker, Ramazan Berkay and Kurtoglu, Celal Oguz},
  title = {Evaluation of the Performance of a YOLOv10-Based Deep Learning Model for Tooth Detection and Numbering on Panoramic Radiographs of Patients in the Mixed Dentition Period},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {4},
  pages = {405},
  doi = {10.3390/diagnostics15040405}
}
Kostenlos starten →