Multi-class anatomical landmark detection in periapical radiographs with deep learning
Odontology · 21.05.2026
DOI: 10.1007/s10266-026-01409-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Odontology, online erschienen am 21.05.2026. Verfasst von Cansu Buyuk und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Istanbul Okan University, Aydıntepe Mah. Prof. Dr. Necmettin Erbakan Cad. No:2,…. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Okan University.
Abstract (Originalsprache)
This study aims to develop a deep learning model for the detection and segmentation of multiple anatomical landmarks on periapical radiographs from the maxilla and mandible. A total of 1930 paralleling-technique periapical radiographs with 21 annotated anatomical landmarks were divided into training (80%), validation (10%), and test (10%) sets. Geometry-preserving preprocessing was applied before dataset splitting, while appearance-based augmentation was performed exclusively on the training subset after the split. A YOLOv8x-seg architecture was trained for multi-class detection and instance segmentation. Performance was evaluated using precision, recall, F1-score, Dice coefficient, Intersection-over-Union, mean average precision, and receiver operating characteristic analysis. The model demonstrated stable training and consistent performance. Overall precision, recall, and F1-score were 0.820, 0.725, and 0.769, respectively, with an overall Dice coefficient of 0.621. High detection accuracy was achieved for well-defined structures such as the maxillary sinus, nasal fossa, nasal fossa floor, and nasal septum, whereas low-contrast landmarks showed reduced performance. Confidence-dependent analysis indicated optimal performance at low confidence thresholds (approximately 0.05–0.10). In conclusion, the proposed model effectively detected major anatomical landmarks on periapical radiographs while demonstrating expected limitations for small or low-contrast structures. Despite substantial anatomical variability across maxillary and mandibular regions, anterior–posterior sites, and projection-dependent appearances of similar structures, these findings demonstrate that deep learning can reliably identify key anatomical landmarks, supporting safer, more consistent, and clinically meaningful radiographic interpretation in routine dental practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Istanbul Okan University, Aydıntepe Mah. Prof. Dr. Necmettin Erbakan Cad. No:2, Istanbul, 34947, Turkey. cansu.buyuk@okan.edu.tr.
- Private Dental Practice, Izmir, 35390, Turkey.
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Istanbul Kent University, Istanbul, 34421, Turkey.
- Department of Mathematics and Computer Science, Eskisehir Osmangazi University, Eskisehir, 26040, Turkey.
- Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Eskisehir Osmangazi University, Eskisehir, 26040, Turkey.
Förderung
- Okan University
Zitieren
APA
Buyuk, C., Saruhan, A., Yuce, F., Celik, O., Bilgir, E., & Bayrakdar, İ. S. (2026). Multi-class anatomical landmark detection in periapical radiographs with deep learning. Odontology. https://doi.org/10.1007/s10266-026-01409-0
Vancouver
Buyuk C, Saruhan A, Yuce F, Celik O, Bilgir E, Bayrakdar İS. Multi-class anatomical landmark detection in periapical radiographs with deep learning. Odontology. 2026. doi:10.1007/s10266-026-01409-0
BibTeX
@article{Buyuk2026,
author = {Buyuk, Cansu and Saruhan, Alperen and Yuce, Fatma and Celik, Ozer and Bilgir, Elif and Bayrakdar, İbrahim Sevki},
title = {Multi-class anatomical landmark detection in periapical radiographs with deep learning},
journal = {Odontology},
year = {2026},
doi = {10.1007/s10266-026-01409-0}
}
EUVIMED