Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance
Journal of Esthetic and Restorative Dentistry · 2025-07 · 37 (7) · 1949-1961
DOI: 10.1111/jerd.13470 ↗At a glance
Vergleichsstudie in Journal of Esthetic and Restorative Dentistry, published online on 2025-04-07. Written by Baturalp Ayhan and 3 co-authors. Institution: Department of Restorative Dentistry, Faculty of Dentistry, Bursa Uludag University, Bursa, Turkey. Major MEDLINE topics: Deep Learning, Dental Caries, Radiography, Bitewing, Dentists. Cited 26 times so far (Crossref); 57 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
Objectives
The application of deep learning techniques for detecting caries in bitewing radiographs has gained significant attention in recent years. However, the comparative performance of various modern deep learning models and strategies to enhance their accuracy remains an area requiring further investigation.
Methods
This study explored the capabilities of 11 widely used YOLO (You Only Look Once) object detection models to automatically identify enamel and dentin caries from bitewing radiographs. To further optimize detection performance, the YOLOv9c model's backbone architecture was refined, reducing both model size and computational requirements. The enhanced model was assessed alongside six dentists, using the same test dataset for direct comparison.
Results
The proposed YOLOv9c model achieved the highest performance among the evaluated models, with recall, precision, specificity, F1‐score, and Youden index values of 0.727, 0.651, 0.726, 0.687, and 0.453, respectively. Notably, the YOLOv9c model surpassed the performance of the dentists, as indicated by its recall and F1‐score values.
Conclusions
The proposed YOLOv9c model proved to be highly effective in detecting enamel and dentin caries, outperforming other models and even clinical evaluations by dentists in this study. Its high accuracy positions it as a valuable tool to augment dentists' diagnostic capabilities. Clinical Significance The results emphasize the potential of the YOLOv9c model to assist dentists in clinical settings, offering accurate and efficient support for caries detection and contributing to improved patient outcomes.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Restorative Dentistry, Faculty of Dentistry, Bursa Uludag University, Bursa, Turkey.
- Department of Computer Engineering, Faculty of Engineering and Architecture, Kırıkkale University, Kırıkkale, Turkey.
- Department of Restorative Dentistry, Faculty of Dentistry, Kırıkkale University, Kırıkkale, Turkey.
ORCID profiles: Baturalp Ayhan, Enes Ayan, Gökhan Karadağ, Yusuf Bayraktar
Cite
APA
Ayhan, B., Ayan, E., Karadağ, G., & Bayraktar, Y. (2025). Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance. Journal of Esthetic and Restorative Dentistry, 37(7), 1949-1961. https://doi.org/10.1111/jerd.13470
Vancouver
Ayhan B, Ayan E, Karadağ G, Bayraktar Y. Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance. Journal of Esthetic and Restorative Dentistry. 2025;37(7):1949-1961. doi:10.1111/jerd.13470
BibTeX
@article{Ayhan2025,
author = {Ayhan, Baturalp and Ayan, Enes and Karadağ, Gökhan and Bayraktar, Yusuf},
title = {Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance},
journal = {Journal of Esthetic and Restorative Dentistry},
year = {2025},
volume = {37},
number = {7},
pages = {1949--1961},
doi = {10.1111/jerd.13470}
}
EUVIMED