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

Sex Prediction From the Clavicle Using Computerized Tomography Images via Traditional and Hybrid Deep Learning Models.

Clinical anatomy (New York, N.Y.)·2026
Same author

Performance evaluation of deep learning models for overbite classification on cephalometric radiographs.

European oral research·2026
Same author

Use of X means and C4.5 algorithms on lateral cephalometric measurements to identify craniofacial patterns.

BMC oral health·2025
Same author

XAI-XGBoost: an innovative explainable intrusion detection approach for securing internet of medical things systems.

Scientific reports·2025
Same author

Classification of Intraoral Photographs with Deep Learning Algorithms Trained According to Cephalometric Measurements.

Diagnostics (Basel, Switzerland)·2025
Same author

Profile Photograph Classification Performance of Deep Learning Algorithms Trained Using Cephalometric Measurements: A Preliminary Study.

Diagnostics (Basel, Switzerland)·2024

Related Experiment Video

Updated: Jan 18, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

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

Published on: September 8, 2023

3.6K

Classification Performance of Deep Learning Models for the Assessment of Vertical Dimension on Lateral Cephalometric

Mehmet Birol Özel1, Sultan Büşra Ay Kartbak1, Muhammet Çakmak2

  • 1Department of Orthodontics, Faculty of Dentistry, Kocaeli University, Kocaeli 41190, Türkiye.

Diagnostics (Basel, Switzerland)
|September 13, 2025
PubMed
Summary

Deep learning models can classify vertical skeletal growth patterns from cephalometric radiographs, potentially simplifying orthodontic diagnosis. A hybrid model achieved the highest accuracy, demonstrating AI

Keywords:
artificial intelligencecephalometrydeep learningvertical discrepancies

More Related Videos

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

1.4K
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

2.2K

Related Experiment Videos

Last Updated: Jan 18, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

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

Published on: September 8, 2023

3.6K
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

1.4K
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

2.2K

Area of Science:

  • Orthodontics
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Vertical growth patterns significantly impact facial aesthetics and orthodontic treatment planning.
  • Lateral cephalograms are standard for assessing vertical jaw relationships.
  • Accurate classification of vertical skeletal patterns is crucial for effective orthodontic diagnosis.

Purpose of the Study:

  • To evaluate deep learning (DL) algorithms for classifying cephalometric radiographs based on vertical skeletal growth patterns.
  • To assess DL model performance without requiring anatomical landmark identification.
  • To compare the efficacy of various DL models in orthodontic diagnosis.

Main Methods:

  • Utilized lateral cephalometric radiographs from 1050 patients.
  • Classified radiographs into three vertical growth pattern subgroups (FMA, SN-GoGn, Cant of Occlusal Plane).
  • Employed and compared six DL models: ResNet101, DenseNet 201, EfficientNet B0, EfficientNet V2 B0, ConvNetBase, and a hybrid model, assessing metrics like accuracy, precision, and F1-Score.

Main Results:

  • The hybrid DL model achieved the highest classification accuracy: 86.67% for FMA, 87.29% for SN-GoGn, and 82.71% for Cant of Occlusal Plane.
  • ConvNet showed the lowest accuracy, ranging from 65% to 79.58% across the different classifications.
  • Overall DL algorithm success rates ranged from 65% to 87.29%.

Conclusions:

  • Deep learning algorithms demonstrate significant potential for classifying vertical skeletal growth patterns from cephalometric radiographs.
  • The hybrid DL model exhibited superior performance, suggesting its utility in orthodontic diagnosis.
  • These AI-driven approaches may enable direct skeletal orthodontic diagnosis, bypassing traditional cephalometric landmark detection steps.