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

3D-driven alveolar ridge augmentation based on reverse planning: a retrospective case series study.

BMC oral health·2026
Same author

Deep learning-based identification, classification and segmentation of infraosseous periodontal defects using a YOLOv8 neural network.

BMC oral health·2026
Same author

FKBP10 mitigates osteoporosis by restraining the HSPA5-coupled ERS-pyroptosis axis to enhance osteogenic differentiation in BMSCs.

International immunopharmacology·2026
Same author

Clinical, Volumetric and Microcirculatory Outcomes of Multiple Gingival Recession Treatment with a Porcine Acellular Dermal Matrix: A Case Series.

The International journal of periodontics & restorative dentistry·2026
Same author

Deep learning cone-beam computed tomography image segmentation for the 3D visualization of mandibular infraosseous periodontal defects.

Journal of periodontology·2026
Same author

The Effect of Orthodontic Tooth Movement on Intrabony Periodontal Defects After Guided Tissue Regeneration-Part I: Human Histologic Evaluation of 20 Consecutive Cases.

Journal of clinical periodontology·2026

Related Experiment Video

Updated: Jun 17, 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

801

[Automatic segmentation of dental cone-beam computed tomography scans using a deep learning framework].

Alexandra Hegyi1, Kristóf Somodi1, Csaba Pintér2,3

  • 11 Semmelweis Egyetem, Fogorvostudományi Kar, Parodontológiai Klinika Budapest, Szentkirályi u. 47., 4. em., 1088 Magyarország.

Orvosi Hetilap
|August 11, 2024
PubMed
Summary

A new deep learning model accurately segments mandible structures in cone-beam computed tomography (CBCT) scans. This artificial intelligence approach offers reliable 3D models for planning reconstructive oral and periodontal surgeries.

Keywords:
artificial intelligencecomputer-generated 3D imagingcone-beam computed tomographycone-beam számítógépes tomográfiaconvolutional neural networksdeep learningkonvolúciós neuralis hálókmandiblemandibulamesterséges intelligenciamélytanulásszámítógépes 3D leképezés

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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

1.7K

Related Experiment Videos

Last Updated: Jun 17, 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

801
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
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

1.7K

Area of Science:

  • Dental Imaging and Diagnostics
  • Artificial Intelligence in Medicine
  • Oral and Maxillofacial Surgery

Background:

  • Accurate 3D reconstruction of cone-beam computed tomography (CBCT) images is crucial for surgical planning in oral surgery and periodontology.
  • Traditional segmentation methods like threshold-based are fast but inaccurate, while semi-automatic methods are accurate but time-consuming.
  • Deep learning offers a promising avenue for automatic and efficient CBCT image segmentation.

Purpose of the Study:

  • To develop and evaluate a deep learning segmentation model for CBCT images obtained from clinical practice.
  • To assess the accuracy and efficiency of the deep learning model compared to semi-automatic segmentation methods.
  • To determine the suitability of AI-driven 3D models for digital surgical planning.

Main Methods:

  • A deep learning model, based on the SegResNet architecture within the MONAI framework, was developed.
  • A training dataset was established using CBCT images from 70 partially edentulous patients.
  • The model's accuracy was verified by comparing its segmentation results against semi-automatic segmentation on 15 CBCT scans.

Main Results:

  • The deep learning model achieved high similarity with semi-automatic segmentation, with an average intersection over union of 0.91 ± 0.02 and a Dice similarity coefficient of 0.95 ± 0.01.
  • The average Hausdorff (95%) distance was 0.67 mm ± 0.22 mm, indicating precise boundary detection.
  • No statistically significant difference was found in the segmented 3D model volumes between the deep learning and semi-automatic methods (p = 0.31).

Conclusions:

  • The developed deep learning model accurately segments the mandible in dental CBCT scans.
  • The AI-based segmentation demonstrated reliability comparable to existing artificial intelligence systems.
  • The accurate 3D models generated by deep learning are suitable for digital planning of reconstructive oral and periodontal surgeries.