Automated classification of dental implant brands and prosthetic platform sizes on panoramic radiographs using deep learning
The Journal of Prosthetic Dentistry · 2026-10 · 136 (4) · 1157-1169
DOI: 10.1016/j.prosdent.2026.07.008 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Prosthetic Dentistry, 2026-10. Verfasst von Marcell Mesterházi und 16 weiteren Autor:innen. Beteiligte Einrichtung: Postgraduate student, Artificial Intelligence Laboratory, Institute for Computer Science and Control (HUN-REN SZTAKI), Budapest, Hungary. Hauptthemen laut MEDLINE: Radiography, Panoramic, Dental Implants, Deep Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Development and Innovation Office.
Abstract (Originalsprache)
STATEMENT OF PROBLEM: Incomplete clinical records can be a significant hurdle in implant dentistry, transforming routine maintenance or a restorative task into a complex search. When the primary documentation-such as the implant passport or surgical report-is missing, the clinician is forced to rely on radiographic identification and trial-and-error, which increases the risk of component mismatch and patient dissatisfaction. PURPOSE: The purpose of this study was to develop and validate an artificial intelligence (AI) algorithm capable of detecting dental implants on panoramic radiographs and classifying them by implant brand and prosthetic platform size. MATERIAL AND METHODS: A dataset of 387 panoramic radiographs with 1004 dental implant images was randomly divided into training, validation, and test sets using an 80/10/10 stratified split across 25 independent partitions. Convolutional neural network (CNN) architectures were developed and trained using manually annotated images. Ground truth labels for implant brand and prosthetic platform size were obtained from patient records. RESULTS: Among the evaluated architectures, a Faster region-based CNN (R-CNN) combined with an EfficientNet-B7 backbone demonstrated the highest diagnostic performance. Implant detection achieved a mean Intersection over Union (IoU) of 77.65% ±11.54% and an accuracy of 99.45% ±0.70% with an average of 0.60 ±0.76 false negatives per split (mean ±standard deviation across 25 partitions). Implant brand classification accuracy was 98.93% ±0.91% (Callus Pro), 97.81% ±1.43% (Denti Root Form), 98.85% ±1.19% (NobelReplace Conical Connection partially machined collar [PMC]), and 96.79% ±1.83% for implants of unknown brand, yielding an overall brand-classification accuracy of 95.66% ±2.02%. Platform-size classification accuracy was 87.62% ±2.94% for narrow, 87.78% ±3.15% for regular, and 96.79% ±1.83% for unknown sizes. Combined brand-and-platform classification achieved an overall accuracy of 85.60% ±3.27%. CONCLUSIONS: The 2-stage CNN pipeline demonstrated clinically acceptable accuracy for automated dental implant detection and classification tasks on panoramic radiographs, supporting its potential integration into clinical workflows to improve diagnostic efficiency and standardization.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Postgraduate student, Artificial Intelligence Laboratory, Institute for Computer Science and Control (HUN-REN SZTAKI), Budapest, Hungary.
- Postgraduate student, Department of Public Dental Health, Semmelweis University, Budapest, Hungary.
- Private practice, Budapest, Hungary.
- Assistant Professor, Department of Public Dental Health, Semmelweis University, Budapest, Hungary.
- Software Developer, Artificial Intelligence Laboratory, Institute for Computer Science and Control (HUN-REN SZTAKI), Budapest, Hungary.
- Postdoctoral Researcher, Artificial Intelligence Laboratory, Institute for Computer Science and Control (HUN-REN SZTAKI), Budapest, Hungary.
Förderung
- National Research Development and Innovation Office
Zitieren
APA
Mesterházi, M., Balogh, J., Takács, A., Faragó, J., Orsós, M., Tényi, D., Rácz, D., Ország, A., Könyves, V., Csertán, A., Benczúr, A., Mikesy, G., Joó, T., Pollner, P., Mijiritsky, E., Blum, I. R., & Kivovics, M. (2026). Automated classification of dental implant brands and prosthetic platform sizes on panoramic radiographs using deep learning. The Journal of Prosthetic Dentistry, 136(4), 1157-1169. https://doi.org/10.1016/j.prosdent.2026.07.008
Vancouver
Mesterházi M, Balogh J, Takács A, Faragó J, Orsós M, Tényi D, et al. Automated classification of dental implant brands and prosthetic platform sizes on panoramic radiographs using deep learning. The Journal of Prosthetic Dentistry. 2026;136(4):1157-1169. doi:10.1016/j.prosdent.2026.07.008
BibTeX
@article{Mesterhzi2026,
author = {Mesterházi, Marcell and Balogh, Júlia and Takács, Anna and Faragó, Judit and Orsós, Mercédesz and Tényi, Dorottya and Rácz, Dániel and Ország, Anna and Könyves, Vera and Csertán, András and Benczúr, András and Mikesy, Gergely and Joó, Tamás and Pollner, Péter and Mijiritsky, Eitan and Blum, Igor R and Kivovics, Márton},
title = {Automated classification of dental implant brands and prosthetic platform sizes on panoramic radiographs using deep learning},
journal = {The Journal of Prosthetic Dentistry},
year = {2026},
volume = {136},
number = {4},
pages = {1157--1169},
doi = {10.1016/j.prosdent.2026.07.008}
}
EUVIMED