Detection of dental restorations and prosthesis devices in panoramic dental X-ray using fast region-based convolutional neural network
Dentomaxillofacial Radiology · 01.02.2026 · 55 (2) · 207-216
DOI: 10.1093/dmfr/twaf079 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 25.10.2025. Verfasst von Martina Benvenuto und 13 weiteren Autor:innen. Beteiligte Einrichtung: synbrAIn S.r.l., Milan, 20127, Italy. Hauptthemen laut MEDLINE: Radiography, Panoramic, Neural Networks, Computer, Dental Restoration, Permanent, Dental Prosthesis. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 20 Literaturangaben.
Abstract (Originalsprache)
Objectives
This study aimed to develop and evaluate an artificial intelligence (AI) framework for detecting dental restorations and prosthesis devices on panoramic radiographs (PRs). Detecting these elements is essential for enhancing automated reporting, improving the accuracy of dental assessments, and reducing manual examination time.
Methods
A fast region-based convolutional neural network (Fast R-CNN) was trained using 186 PRs for the training set and 42 for validation. The model’s performance was assessed on an external test dataset of 1133 PRs. Seven dental restorations and prosthesis devices were targeted: appliance, bridge, endodontic filling, crown filling, implant, retainer, and single crown. Precision, recall, and F1-score were calculated for each element to measure detection accuracy.
Results
The AI framework achieved high performance across all categories, with precision, recall, and F1-scores as follows: appliance (0.79, 0.96, 0.87), bridge (0.91, 0.86, 0.89), endodontic filling (0.98, 0.98, 0.98), crown filling (0.95, 0.95, 0.95), implant (0.99, 0.97, 0.98), retainer (0.98, 0.98, 0.98), and single crown (0.94, 0.96, 0.95). The system processes one panoramic image in under 30 seconds.
Conclusions
The AI framework demonstrated high recall and efficiency in detecting dental prosthesis and other dental restorations on PRs. Its application could significantly streamline dental diagnostics and automated reporting, enhancing both the speed and accuracy of dental assessments. Advances in knowledge This study highlights the potential of AI in automating the detection of multiple dental restorations and prosthesis on PRs, offering a valuable tool for dental professionals to improve diagnostic workflows.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- synbrAIn S.r.l., Milan, 20127, Italy.
- Centro Diagnostico Italiano S.p.A., Milan, 20147, Italy.
- ASST Fatebenefratelli Sacco, Milan, 20121, Italy.
- Università degli Studi di Milano, Milan, 20122, Italy.
- Bracco Imaging S.p.A., Milan, 20134, Italy.
ORCID-Profile: Michaela Cellina, Marco Alì
Zitieren
APA
Benvenuto, M., Bologna, M., Fortunati, A., Perazzo, C., Cellina, M., Cè, M., Rubiu, G., Martini, I., Sala, D., Di Palma, L., Fazzini, D., Alba, S., Papa, S., & Alì, M. (2026). Detection of dental restorations and prosthesis devices in panoramic dental X-ray using fast region-based convolutional neural network. Dentomaxillofacial Radiology, 55(2), 207-216. https://doi.org/10.1093/dmfr/twaf079
Vancouver
Benvenuto M, Bologna M, Fortunati A, Perazzo C, Cellina M, Cè M, et al. Detection of dental restorations and prosthesis devices in panoramic dental X-ray using fast region-based convolutional neural network. Dentomaxillofacial Radiology. 2026;55(2):207-216. doi:10.1093/dmfr/twaf079
BibTeX
@article{Benvenuto2026,
author = {Benvenuto, Martina and Bologna, Marco and Fortunati, Alice and Perazzo, Chiara and Cellina, Michaela and Cè, Maurizio and Rubiu, Giulia and Martini, Ilaria and Sala, Davide and Di Palma, Luca and Fazzini, Deborah and Alba, Simona and Papa, Sergio and Alì, Marco},
title = {Detection of dental restorations and prosthesis devices in panoramic dental X-ray using fast region-based convolutional neural network},
journal = {Dentomaxillofacial Radiology},
year = {2026},
volume = {55},
number = {2},
pages = {207--216},
doi = {10.1093/dmfr/twaf079}
}
EUVIMED