Related Experiment Video
Updated: May 19, 2026
08:03
Midface Hypoplasia and Cranial Base Morphology in Syndromic Craniosynostosis: A Comparative Analysis Study Using a Predictive Regression Model
Published on: November 4, 2025
Neural Network Technologies for Age Estimation in Children from Orthopantomograms (a Pilot Study).
M P Poletaeva1, Yu V Vasilevsky2, D K Valetov3
1MD, PhD, Associate Professor, Department of Forensic Medicine, N.V. Sklifosovsky Institute of Clinical Medicine; I.M. Sechenov First Moscow State Medical University (Sechenov University), 8/2 Trubetskaya St., Moscow, 119991, Russia.
Sovremennye Tekhnologii V Meditsine
|May 18, 2026
Summary
Artificial intelligence accurately estimates children's ages using dental radiographs. This machine learning model achieved a mean absolute error of 0.92 years, outperforming manual methods.
Area of Science:
- Dentistry
- Artificial Intelligence
- Machine Learning
Background:
- Accurate age estimation in children is crucial for clinical and forensic applications.
- Traditional methods for age estimation from dental radiographs can be time-consuming and subjective.
Purpose of the Study:
- To evaluate the efficacy of artificial intelligence (AI) for estimating chronological age in children using dental radiographs.
- To develop and validate a machine learning model for pediatric age assessment.
Main Methods:
- A retrospective analysis of 322 children's orthopantomograms (ages 4-16) was performed.
- A neural network was trained using PyTorch on annotated permanent mandibular teeth, with data split 80:20 for training and testing.
- Five-fold cross-validation was employed to assess prediction accuracy using R², MSE, and MAE.
Main Results:
- The developed machine learning model demonstrated high accuracy in pediatric age estimation.
- The mean absolute error (MAE) across cross-validation was 0.92 years.
- This AI-driven approach significantly reduced the error compared to traditional manual methods.
Conclusions:
- AI technologies show significant potential for accurate and efficient age estimation in children from dental radiographs.
- The developed neural network model offers a reliable alternative to conventional age assessment techniques.
- This study highlights the value of machine learning in improving diagnostic accuracy in pediatric dentistry.
