Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Teeth

Teeth

The formation of teeth, also known as odontogenesis, is a complex process that begins in utero, around the sixth week of embryonic development. There are three stages to this process: the bud stage, the cap stage, and the bell stage.
In the bud stage, the tooth germ (an aggregation of cells) starts to form in the developing jawbone. During the cap stage, the tooth germ differentiates into enamel organ, dental papilla, and dental sac, which will later develop into the tooth's enamel, dentin...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Development of an expert-annotated chest X-ray dataset to support AI validation in tuberculosis diagnosis.

Insights into imaging·2026

Same author

Exploring the application of Artificial Intelligence in palliative care and its practical, technical and ethical considerations: a scoping review.

BMC palliative care·2026

Same author

Virtual Reality-Based Training in Radiologic Technology for Contrast-Enhanced Computed Tomography Brain Imaging: Randomized Controlled Trial.

JMIR formative research·2026

Same author

Time-Series Forecasting of Radiotherapy Utilization in Older Adults in Southern Thailand's Largest Quaternary Hospital: A Retrospective Study.

Asian Pacific journal of cancer prevention : APJCP·2026

Same author

Enhancing Dental Caries Classification with Adversarial Training on Bitewing Radiographs.

Journal of imaging informatics in medicine·2025

Same author

A fully automated deep learning framework for age estimation in adults using periapical radiographs of canine teeth.

International journal of legal medicine·2025

Search research articles

Related Experiment Video

Updated: Jan 7, 2026

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

End-to-end vs. human-defined feature extraction: comparing deep learning approaches for age classification using

Witsarut Upalananda¹, Arnon Charuakkra², Sitthichok Chaichulee³

¹Department of Oral Diagnostic Sciences, Faculty of Dentistry, Prince of Songkla University, Songkhla, Thailand.

The Journal of Forensic Odonto-Stomatology

|December 26, 2025

Summary

Forensic age estimation using mandibular third molars shows deep learning can improve accuracy. A human-defined feature extraction method balances specificity and interpretability for reliable age classification.

Keywords:

Deep learning Dental age estimation Forensic odontology Mandibular third molar

More Related Videos

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Related Experiment Videos

Last Updated: Jan 7, 2026

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Area of Science:

Forensic Odontology
Radiology
Artificial Intelligence

Background:

Accurate age classification is vital for legal and forensic purposes.
Mandibular third molars are key indicators for age estimation, particularly for individuals under or over 18 years.
Evaluating different age classification methods is essential for improving forensic science.

Purpose of the Study:

To compare the efficacy of traditional human-based methods, end-to-end deep learning, and human-defined feature extraction for age classification using Thai mandibular third molar radiographs.
To determine the optimal approach for age estimation in forensic contexts.

Main Methods:

A dataset of 3,407 mandibular third molar radiographs from individuals aged 14-23 years was analyzed.
Three methods were compared: modified Demirjian classification, end-to-end convolutional neural network (CNN) age prediction, and CNN-based tooth developmental stage estimation for age classification.
Performance metrics included sensitivity, specificity, and Bayes' post-test probability.

Main Results:

The traditional method had high specificity (0.99) but low sensitivity (0.45).
End-to-end deep learning models showed improved sensitivity (0.65-0.74) with good specificity (0.91-0.95).
The human-defined feature extraction approach achieved high specificity (0.95-0.97) and interpretability, with sensitivity ranging from 0.51-0.56.

Conclusions:

While traditional methods offer high specificity, they lack sensitivity for age classification.
Deep learning approaches, particularly human-defined feature extraction, present a balanced and interpretable solution for forensic age estimation.
The human-defined feature extraction method shows significant potential for clinical application in age determination.