DentAge : Deep learning for automated age prediction using panoramic dental X‐ray images
Journal of Forensic Sciences · 2024-11 · 69 (6) · 2069-2074
DOI: 10.1111/1556-4029.15629 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Forensic Sciences, online erschienen am 18.09.2024. Verfasst von Žiga Bizjak und 1 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Imaging Technologies, Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia. Hauptthemen laut MEDLINE: Radiography, Panoramic, Age Determination by Teeth, Deep Learning. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Slovenian Research Agency, Javna Agencija za Raziskovalno Dejavnost RS.
Abstract (Originalsprache)
Age estimation plays a crucial role in various fields, including forensic science and anthropology. This study aims to develop and validate DentAge, a deep‐learning model for automated age prediction using panoramic dental X‐ray images. DentAge was trained on a dataset comprising 21,007 panoramic dental X‐ray images sourced from a private dental center in Slovenia. The dataset included subjects aged 4 to 97 years with various dental conditions. Transfer learning was employed, initializing the model with ImageNet weights and fine‐tuning on the dental image dataset. The model was trained using stochastic gradient descent with momentum, and mean absolute error (MAE) served as the objective function. Across the test dataset, DentAge achieved an MAE of 3.12 years, demonstrating its efficacy in age prediction. Notably, the model performed well across different age groups, with MAEs ranging from 1.94 (age group [10–20]) to 13.40 years (age group [90–100]). Visual evaluation revealed factors contributing to prediction errors, including prosthetic restorations, tooth loss, and bone resorption. DentAge represents a significant advancement in automated age prediction within dentistry. The model's robust performance across diverse age groups and dental conditions underscores its potential utility in real‐world scenarios. Our model will be accessible to the public for further adjustments and validation, ensuring DentAge's effectiveness and trustworthiness in practical scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory of Imaging Technologies, Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia.
- Zobozdravstvo Diamant, Celje, Slovenia.
ORCID-Profile: Žiga Bizjak
Förderung
- Slovenian Research Agency
- Javna Agencija za Raziskovalno Dejavnost RS
Zitieren
APA
Bizjak, Ž., & Robič, T. (2024). DentAge : Deep learning for automated age prediction using panoramic dental X‐ray images. Journal of Forensic Sciences, 69(6), 2069-2074. https://doi.org/10.1111/1556-4029.15629
Vancouver
Bizjak Ž, Robič T. DentAge : Deep learning for automated age prediction using panoramic dental X‐ray images. Journal of Forensic Sciences. 2024;69(6):2069-2074. doi:10.1111/1556-4029.15629
BibTeX
@article{Bizjak2024,
author = {Bizjak, Žiga and Robič, Tina},
title = {DentAge : Deep learning for automated age prediction using panoramic dental X‐ray images},
journal = {Journal of Forensic Sciences},
year = {2024},
volume = {69},
number = {6},
pages = {2069--2074},
doi = {10.1111/1556-4029.15629}
}
EUVIMED