Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Timing and Associated Factors to Formation and Detection of Sequestrum in Patients With Medication-Related Osteonecrosis of the Jaw.

Oral diseases·2026
Same author

In Vivo Model of Short-Term Efficacy and Favorable Safety of Botulinum Toxin Type E Compared with Type A.

Toxins·2026
Same author

Reply to the Letter to the Editor: Deep learning TMJ MRI-reader-level equivalence is a foundation, not a finish line.

European radiology·2026
Same author

Deep learning for synthetic contrast-enhanced CT and MRI: a scoping review.

European radiology·2026
Same author

Spectrometer-free time-division multiplexed NIR time-of-flight vision system for visually similar material recognition.

Scientific reports·2026
Same author

Unexpected delayed orofacial symptoms induced by facial cosmetic filler: A report of 3 cases.

Imaging science in dentistry·2026

Related Experiment Video

Updated: Oct 11, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

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

Published on: February 23, 2024

1.0K

Automatic detection of mesiodens on panoramic radiographs using artificial intelligence.

Eun-Gyu Ha1, Kug Jin Jeon1, Young Hyun Kim1

  • 1Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, 50-1 Yonsei-ro Seodaemun-gu, Seoul, 03722, South Korea.

Scientific Reports
|November 30, 2021
PubMed
Summary

An artificial intelligence model using a convolutional neural network (CNN) effectively detects mesiodens on panoramic radiographs across all dentition types. This AI tool shows strong performance, indicating potential for clinical use in dental diagnostics.

More Related Videos

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.7K

Related Experiment Videos

Last Updated: Oct 11, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

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

Published on: February 23, 2024

1.0K
Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

1.9K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.7K

Area of Science:

  • Dentistry
  • Artificial Intelligence
  • Radiology

Background:

  • Mesiodens, the most common supernumerary tooth, can cause various dental issues.
  • Early detection of mesiodens on panoramic radiographs is crucial for timely intervention.
  • Current detection methods may lack efficiency and consistency across different dentition stages.

Purpose of the Study:

  • To develop and evaluate an artificial intelligence (AI) model for detecting mesiodens.
  • To assess the model's performance across primary, mixed, and permanent dentition groups.
  • To investigate the impact of image preprocessing techniques on detection accuracy.

Main Methods:

  • A convolutional neural network (CNN) model based on YOLOv3 was trained on 612 panoramic radiographs.
  • Model performance was evaluated on internal (130 images) and external (118 images) multi-center datasets.
  • Contrast-limited adaptive histogram equalization (CLAHE) was applied to assess its effect on detection accuracy.

Main Results:

  • The AI model achieved high accuracy: 96.2% internally and 89.8% externally on original images.
  • Accuracy varied by dentition: internal (96.7% primary, 97.5% mixed, 93.3% permanent), external (86.7% primary, 95.3% mixed, 86.7% permanent).
  • CLAHE preprocessing showed negligible impact, with original images yielding better results.

Conclusions:

  • The developed AI model demonstrates robust performance in detecting mesiodens across all dentition types.
  • The model shows significant potential for integration into clinical practice for panoramic radiograph analysis.
  • Image preprocessing techniques like CLAHE did not enhance, and sometimes slightly reduced, model accuracy.