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

National Competence Based Catalogue of Learning Objectives for Undergraduate Medical Education (NKLM) - process description over the last 15 years.

GMS journal for medical education·2026
Same author

Understanding the Content and Purpose of S3 Clinical Practice Guidelines in Dentistry.

International endodontic journal·2026
Same author

Experts' Willingness to Restore With Direct Composite: Complexity, Cuspal Coverage, and Techniques.

The journal of adhesive dentistry·2026
Same author

Staging in Gerodontology: A Framework.

Gerodontology·2026
Same author

Grading in Gerodontology: A Framework.

Gerodontology·2026
Same author

Coronal and Root Caries in Older Adults: Associated Factors, Quality of Life Impact, and Treatment-A Scoping Review.

Gerodontology·2026

Related Experiment Video

Updated: Jul 10, 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

867

Detection of Periodontal Bone Loss on Periapical Radiographs-A Diagnostic Study Using Different Convolutional Neural

Patrick Hoss1, Ole Meyer2, Uta Christine Wölfle1

  • 1Department of Conservative Dentistry and Periodontology, LMU University Hospital, LMU Munich, 80336 Munich, Germany.

Journal of Clinical Medicine
|November 25, 2023
PubMed
Summary

Machine learning models, specifically convolutional neural networks (CNNs), show promise for classifying periodontal bone loss (PBL) from dental radiographs. Diagnostic performance varied by tooth location, indicating potential for automated PBL assessment.

Keywords:
artificial intelligencebone lossconvolutional neural networksdeep learningdental radiographymachine learningperiodontitis

More Related Videos

In situ Compressive Loading and Correlative Noninvasive Imaging of the Bone-periodontal Ligament-tooth Fibrous Joint
07:09

In situ Compressive Loading and Correlative Noninvasive Imaging of the Bone-periodontal Ligament-tooth Fibrous Joint

Published on: March 7, 2014

13.4K
Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model
06:14

Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model

Published on: February 17, 2023

4.0K

Related Experiment Videos

Last Updated: Jul 10, 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

867
In situ Compressive Loading and Correlative Noninvasive Imaging of the Bone-periodontal Ligament-tooth Fibrous Joint
07:09

In situ Compressive Loading and Correlative Noninvasive Imaging of the Bone-periodontal Ligament-tooth Fibrous Joint

Published on: March 7, 2014

13.4K
Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model
06:14

Induction of Periodontitis via a Combination of Ligature and Lipopolysaccharide Injection in a Rat Model

Published on: February 17, 2023

4.0K

Area of Science:

  • Dentistry
  • Artificial Intelligence
  • Medical Imaging

Background:

  • The application of machine learning models, particularly convolutional neural networks (CNNs), is gaining traction in dentistry for diagnostic applications.
  • CNNs offer potential for accurate classification of periodontal bone loss (PBL) on dental radiographs.

Purpose of the Study:

  • To analyze the diagnostic performance of five distinct CNNs in detecting and classifying periodontal bone loss (PBL) using periapical radiographs.
  • To evaluate the accuracy, sensitivity, specificity, and AUC of CNNs in identifying different grades of PBL.

Main Methods:

  • A dataset of 21,819 anonymized periapical radiographs was utilized.
  • Trained dentists classified radiographs into categories: no PBL, mild, moderate, or severe PBL.
  • Five CNNs were trained over five epochs, and their diagnostic performance was statistically analyzed using ACC, SE, SP, and AUC.

Main Results:

  • Overall diagnostic performance across the five CNNs showed similar results, with accuracy ranging from 82.0% to 84.8%.
  • Sensitivity ranged from 88.8-90.7%, specificity from 66.2-71.2%, and AUC from 0.884-0.913.
  • Significant performance variations were observed across different dental sextants, with the highest diagnostic accuracy in the mandibular anterior teeth (94.9-96.0%) and the lowest in the maxillary posterior teeth (78.0-80.7%).

Conclusions:

  • Automatic assessment of periodontal bone loss (PBL) using CNNs appears feasible.
  • The diagnostic accuracy of CNNs for PBL detection is location-dependent within the dentition.
  • Further research is necessary to enhance the performance of CNNs across all tooth regions for comprehensive PBL assessment.