Development of a fully automated dental age estimation framework from panoramic radiographs using tooth-level information with an attention-weighting module
Dentomaxillofacial Radiology · 01.01.2026 · 55 (1) · 88-98
DOI: 10.1093/dmfr/twaf063 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dentomaxillofacial Radiology, online erschienen am 03.09.2025. Verfasst von Witsarut Upalananda und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Sciences and Biomedical Engineering, Faculty of Medicine, Prince of Songkla University, Hatyai, Songkhla 90110, Thailand. Hauptthemen laut MEDLINE: Radiography, Panoramic, Age Determination by Teeth. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Graduate School, Prince of Songkla University.
Abstract (Originalsprache)
Objective
This study aimed to develop a fully automated and explainable framework for dental age estimation from panoramic radiographs in young individuals.
Methods
A dataset of 1639 radiographs from individuals aged 8 to 23 years was used. The proposed 2-stage pipeline involved: (1) oriented tooth detection using the YOLO11-OBB model and (2) age estimation using deep learning-based regression models with an attention-weighting module to aggregate predictions from individual teeth. Auxiliary features, including the presence of deciduous teeth and sex, were also evaluated for their impact on model performance.
Results
For the first stage, the tooth detection model achieved an F1 score of 0.981, demonstrating accurate tooth localization and identification. In the later stage, the best-performing model, DenseNet-121 with the deciduous teeth feature, achieved a mean absolute error (MAE) of 1.05 ± 0.95 years. Compared to traditional methods, the proposed framework significantly reduced the MAE.
Conclusions
This study developed an explainable, high-performing deep learning framework that offers a promising solution for real-world age estimation in the forensic domain.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biomedical Sciences and Biomedical Engineering, Faculty of Medicine, Prince of Songkla University, Hatyai, Songkhla 90110, Thailand.
- Department of Oral Diagnostic Sciences, Faculty of Dentistry, Prince of Songkla University, Hatyai, Songkhla 90110, Thailand.
- Department of Oral Biology and Diagnostic Sciences, Faculty of Dentistry, Chiang Mai University, Mueng Chiang Mai, Chiang Mai 50200, Thailand.
- Dental Hospital, Faculty of Dentistry, Prince of Songkla University, Hatyai, Songkhla 90110, Thailand.
- Dental Department, Bangkaew Hospital, Bangkaew, Phatthalung 93140, Thailand.
ORCID-Profile: Witsarut Upalananda, Sangsom Prapayasatok, Sakarat Na Lampang, Sitthichok Chaichulee
Förderung
- Graduate School, Prince of Songkla University
Zitieren
APA
Upalananda, W., Prapayasatok, S., Na Lampang, S., Dilokrattanaphichit, O., Chairat, C., & Chaichulee, S. (2026). Development of a fully automated dental age estimation framework from panoramic radiographs using tooth-level information with an attention-weighting module. Dentomaxillofacial Radiology, 55(1), 88-98. https://doi.org/10.1093/dmfr/twaf063
Vancouver
Upalananda W, Prapayasatok S, Na Lampang S, Dilokrattanaphichit O, Chairat C, Chaichulee S. Development of a fully automated dental age estimation framework from panoramic radiographs using tooth-level information with an attention-weighting module. Dentomaxillofacial Radiology. 2026;55(1):88-98. doi:10.1093/dmfr/twaf063
BibTeX
@article{Upalananda2026,
author = {Upalananda, Witsarut and Prapayasatok, Sangsom and Na Lampang, Sakarat and Dilokrattanaphichit, Ornicha and Chairat, Chawin and Chaichulee, Sitthichok},
title = {Development of a fully automated dental age estimation framework from panoramic radiographs using tooth-level information with an attention-weighting module},
journal = {Dentomaxillofacial Radiology},
year = {2026},
volume = {55},
number = {1},
pages = {88--98},
doi = {10.1093/dmfr/twaf063}
}
EUVIMED