Hybrid CNN-Transformer Model for Accurate Impacted Tooth Detection in Panoramic Radiographs
Diagnostics · 22.01.2025 · 15 (3) · 244
DOI: 10.3390/diagnostics15030244 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 22.01.2025. Verfasst von Deniz Bora Küçük und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Software Engineering, Faculty of Engineering, Samsun University, 55000 Samsun, Turkey. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fırat University, Firat University, Scientific Research Project Committee.
Abstract (Originalsprache)
Background/Objectives: The integration of digital imaging technologies in dentistry has revolutionized diagnostic and treatment practices, with panoramic radiographs playing a crucial role in detecting impacted teeth. Manual interpretation of these images is time consuming and error prone, highlighting the need for automated, accurate solutions. This study proposes an artificial intelligence (AI)-based model for detecting impacted teeth in panoramic radiographs, aiming to enhance accuracy and reliability.
Methods
The proposed model combines YOLO (You Only Look Once) and RT-DETR (Real-Time Detection Transformer) models to leverage their strengths in real-time object detection and learning long-range dependencies, respectively. The integration is further optimized with the Weighted Boxes Fusion (WBF) algorithm, where WBF parameters are tuned using Bayesian optimization. A dataset of 407 labeled panoramic radiographs was used to evaluate the model’s performance.
Results
The model achieved a mean average precision (mAP) of 98.3% and an F1 score of 96%, significantly outperforming individual models and other combinations. The results were expressed through key performance metrics, such as mAP and F1 scores, which highlight the model’s balance between precision and recall. Visual and numerical analyses demonstrated superior performance, with enhanced sensitivity and minimized false positive rates.
Conclusions
This study presents a scalable and reliable AI-based solution for detecting impacted teeth in panoramic radiographs, offering substantial improvements in diagnostic accuracy and efficiency. The proposed model has potential for widespread application in clinical dentistry, reducing manual workload and error rates. Future research will focus on expanding the dataset and further refining the model’s generalizability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Software Engineering, Faculty of Engineering, Samsun University, 55000 Samsun, Turkey.
- Department of Electrical and Electronic Engineering, Faculty of Engineering, Munzur University, 62000 Tunceli, Turkey.
- Department of Electrical and Electronic Engineering, Faculty of Engineering, Bingol University, 12000 Bingol, Turkey.
- Oral and Maxillofacial Surgery Department, Faculty of Dentistry, Mersin University, 33000 Mersin, Turkey.
- Department of Electrical and Electronic Engineering, Faculty of Technology, Firat University, 23100 Elazig, Turkey.
- A.I. Virtanen Institute for Molecular Sciences, Faculty of Health Sciences, University of Eastern Finland, 70211 Kuopio, Finland.
ORCID-Profile: Deniz Bora Küçük, Andaç Imak, Salih Taha Alperen Özçelik, Muammer Türkoğlu, Abdulkadir Sengur
Förderung
- Fırat University
- Firat University, Scientific Research Project Committee
Zitieren
APA
Küçük, D. B., Imak, A., Özçelik, S. T. A., Çelebi, A., Türkoğlu, M., Sengur, A., & Koundal, D. (2025). Hybrid CNN-Transformer Model for Accurate Impacted Tooth Detection in Panoramic Radiographs. Diagnostics, 15(3), 244. https://doi.org/10.3390/diagnostics15030244
Vancouver
Küçük DB, Imak A, Özçelik STA, Çelebi A, Türkoğlu M, Sengur A, et al. Hybrid CNN-Transformer Model for Accurate Impacted Tooth Detection in Panoramic Radiographs. Diagnostics. 2025;15(3):244. doi:10.3390/diagnostics15030244
BibTeX
@article{Kk2025,
author = {Küçük, Deniz Bora and Imak, Andaç and Özçelik, Salih Taha Alperen and Çelebi, Adalet and Türkoğlu, Muammer and Sengur, Abdulkadir and Koundal, Deepika},
title = {Hybrid CNN-Transformer Model for Accurate Impacted Tooth Detection in Panoramic Radiographs},
journal = {Diagnostics},
year = {2025},
volume = {15},
number = {3},
pages = {244},
doi = {10.3390/diagnostics15030244}
}
EUVIMED