Automated periodontal assessment in orthodontic patients: a dual CNN framework
Clinical Oral Investigations · 02.06.2025 · 29 (6)
DOI: 10.1007/s00784-025-06410-5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Oral Investigations, online erschienen am 02.06.2025. Verfasst von Ebru Yurdakurban und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Dentistry, Department of Orthodontics, Muğla Sıtkı Koçman University, Muğla, Turkey. ebruyurdakurban@mu.edu.tr. Hauptthemen laut MEDLINE: Neural Networks, Computer, Periodontal Diseases. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Mugla Sitki KocmanUniversity.
Abstract (Originalsprache)
Objective
The aim of this study was to develop convolutional neural network (CNN)-based systems to diagnose calculus, plaque, gingival hyperplasia and gingival inflammation in intraoral images from orthodontic patients. Materials and methods A dataset of 1,000 lateral and frontal intraoral images from orthodontic patients was used to develop CNN-based models. Periodontology specialists annotated areas of dental calculus, plaque, gingival inflammation, and gingival hyperplasia on the teeth and gingiva. The dataset was divided into training (80%), validation (10%), and test (10%) sets for model development. The YOLOv8 and hybrid U-Net + ResNet50 models were examined. Their performance was evaluated on the basis of accuracy, precision, recall, F 1 score, Tversky loss, intersection over union, mean average precision, Dice coefficient, and Cohen’s kappa.
Results
The mean classification accuracy was 0.96 for the YOLOv8 model and 0.93 for the U-Net + ResNet50 model. On the basis of the Dice coefficient, the models performed best in detecting gingival hyperplasia (YOLOv8: 0.78, U-Net + ResNet50: 0.79) and worst in detecting dental calculus (YOLOv8:0.48, U-Net + ResNet50:0.53). Cohen’s kappa coefficient was highest for classifying gingival hyperplasia (YOLOv8: 0.785, U-Net + ResNet50: 0.790). The precision exceeded 0.72 across all the classifications, with the greatest precision in classifying gingival inflammation.
Conclusion
Deep learning-based systems can serve as decision support tools by offering rapid and objective evaluations of dental calculus, plaque, gingival inflammation, and gingival hyperplasia. Nonetheless, the definitive diagnostic conclusion should be based on the clinician’s specialized expertise and professional judgment. Clinical relevance The integration of CNN-based diagnostic models into clinical workflows has the potential to facilitate early periodontal diagnosis and improve accessibility to periodontal assessments in orthodontic patients.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Dentistry, Department of Orthodontics, Muğla Sıtkı Koçman University, Muğla, Turkey. ebruyurdakurban@mu.edu.tr.
- Faculty of Dentistry, Department of Periodontology, Muğla Sıtkı Koçman University, Muğla, Turkey.
- Faculty of Technology, Information Systems Engineering, Muğla Sıtkı Koçman University, Muğla, Turkey.
- Gulhane Faculty of Dentistry, Department of Orthodontics, University of Health Sciences, Ankara, Turkey.
Förderung
- Mugla Sitki KocmanUniversity
Zitieren
APA
Yurdakurban, E., Bayırlı, A. B., Uytun, M., Suçeken, Ö., Karasoy, O., Özkaraca, O., & Topsakal, K. G. (2025). Automated periodontal assessment in orthodontic patients: a dual CNN framework. Clinical Oral Investigations, 29(6). https://doi.org/10.1007/s00784-025-06410-5
Vancouver
Yurdakurban E, Bayırlı AB, Uytun M, Suçeken Ö, Karasoy O, Özkaraca O, et al. Automated periodontal assessment in orthodontic patients: a dual CNN framework. Clinical Oral Investigations. 2025;29(6). doi:10.1007/s00784-025-06410-5
BibTeX
@article{Yurdakurban2025,
author = {Yurdakurban, Ebru and Bayırlı, Ali Batuhan and Uytun, Mehmetcan and Suçeken, Öznur and Karasoy, Onur and Özkaraca, Osman and Topsakal, Kübra Gülnur},
title = {Automated periodontal assessment in orthodontic patients: a dual CNN framework},
journal = {Clinical Oral Investigations},
year = {2025},
volume = {29},
number = {6},
doi = {10.1007/s00784-025-06410-5}
}
EUVIMED