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

Comprehensive assessment of mandibular condyle adaptation following mandibular advancement versus mandibular setback surgery.

BMC oral health·2026
Same author

Effectiveness of 0.1% triamcinolone acetonide compared with those of other therapies for minor recurrent aphthous stomatitis: a systematic review and meta-analysis of randomized controlled trials.

BMC oral health·2025
Same author

Educational and clinical training gaps in dental implantology among undergraduate dental students: a multicenter cross-sectional study.

BMC medical education·2025
Same author

Deep learning approaches for quantitative and qualitative assessment of cervical vertebral maturation staging systems.

PloS one·2025
Same author

Deep learning based quantitative cervical vertebral maturation analysis.

Head & face medicine·2025
Same author

Development and validation of a polyfit approach for assessing alveolar bone loss using panoramic radiography.

BMC oral health·2025

Related Experiment Video

Updated: Apr 13, 2026

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

1.7K

Automated detection and classification of maxillary sinus variations using slice-based and full-volume CBCT deep

Zainab Abdulkader Said1,2, Abbas Ahmed Abdulqader3, Fayu Liu4,5

  • 1School and Hospital of Stomatology, China Medical University, Liaoning Provincial Key Laboratory of Oral Diseases, China Medical University, Shenyang, 110002, China.

BMC Oral Health
|April 11, 2026
PubMed
Summary

This study developed deep learning models for classifying maxillary sinus variations on cone-beam computed tomography (CBCT) scans. A 3D volume model showed higher accuracy than a 2D slice-based model, highlighting AI

Keywords:
Artificial IntelligenceCone-beam computed tomographyMaxillary sinus variations

More Related Videos

A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth
10:50

A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth

Published on: April 8, 2020

10.4K
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

2.4K

Related Experiment Videos

Last Updated: Apr 13, 2026

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

1.7K
A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth
10:50

A Finite Element Approach for Locating the Center of Resistance of Maxillary Teeth

Published on: April 8, 2020

10.4K
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

2.4K

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Medicine
  • Deep Learning for Medical Diagnosis

Background:

  • Maxillary sinus variations are common and can impact diagnosis and treatment.
  • Accurate classification of these variations is crucial for clinical decision-making.
  • Automated analysis of cone-beam computed tomography (CBCT) scans can improve efficiency and accuracy.

Purpose of the Study:

  • To develop and compare two deep learning models for automated detection and classification of maxillary sinus variations.
  • To evaluate a 2D slice-based model using sagittal CBCT images.
  • To assess a 3D volume-based model using full CBCT volumetric scans.

Main Methods:

  • CBCT scans from 452 patients (631 sinuses) were analyzed.
  • Six sinus radiographic variations were categorized: normal anatomy, hypoplasia, mucosal thickening, polypoid lesions, septa, and sinus opacification.
  • Two deep learning models (2D slice-based and 3D volume-based) were developed and evaluated using standard classification metrics.

Main Results:

  • The 2D slice-based model achieved 83.2% accuracy, with high sensitivity for septa and normal anatomy.
  • The 3D volume-based model demonstrated superior performance with 87.2% accuracy.
  • The 3D model showed improved sensitivity for hypoplasia and mucosal thickening, and perfect classification for sinus opacification.

Conclusions:

  • Both 2D and 3D deep learning models show potential for automated classification of maxillary sinus variations on CBCT.
  • The 3D volume-based model offers enhanced spatial representation and higher diagnostic precision compared to the 2D model.
  • Artificial intelligence can serve as a valuable adjunctive tool in the radiographic assessment of the maxillary sinus.