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

Smartphone-Assisted Placido Ring Imaging for K1 Stratification in Keratoconus: A Deep Learning Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Influence of incisor display and lower lip height on smile esthetics and perceived age.

Dental press journal of orthodontics·2026
Same author

Plastic deformation evaluation of clear aligners exposed to different cleaning solutions.

The Angle orthodontist·2026
Same author

Surgical-orthodontic treatment of skeletal Class III malocclusion with asymmetrical extractions.

Journal of clinical orthodontics : JCO·2026
Same author

Diagnostic challenge: Case 14, part 1.

Journal of clinical orthodontics : JCO·2026
Same author

Diagnostic challenge: Case 14, part 2.

Journal of clinical orthodontics : JCO·2026

Related Experiment Video

Updated: May 22, 2025

Image Acquisition using Portable Sonography for Emergency Airway Management
07:31

Image Acquisition using Portable Sonography for Emergency Airway Management

Published on: September 28, 2022

2.2K

Explainable artificial intelligence to quantify adenoid hypertrophy-related upper airway obstruction using 3D Shape

Claudia Trindade Mattos1, Lucie Dole2, Sergio Luiz Mota-Júnior3

  • 1Department of Orthodontics, Faculdade de Odontologia, Universidade Federal Fluminense, Rua Mário Santos Braga, 30, 2° andar, sala 214, Centro, Niterói, RJ, CEP 24020-140, Brazil; Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, 1011 North University Avenue, Ann Arbor, Michigan, 48104, USA.

Journal of Dentistry
|March 16, 2025
PubMed
Summary

An explainable AI model accurately classifies and quantifies upper airway obstruction from 3D CBCT scans. This tool aids clinicians in assessing adenoid hypertrophy, improving diagnosis and treatment planning for pediatric patients.

Keywords:
3D shape analysisAdenoid hypertrophyArtificial Intelligence (AI)Cone-beam computed tomography (CBCT)Upper airway obstruction

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

1.7K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.0K

Related Experiment Videos

Last Updated: May 22, 2025

Image Acquisition using Portable Sonography for Emergency Airway Management
07:31

Image Acquisition using Portable Sonography for Emergency Airway Management

Published on: September 28, 2022

2.2K
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
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.0K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Anatomy

Background:

  • Adenoid hypertrophy frequently causes upper airway obstruction in children.
  • Accurate assessment of obstruction severity is crucial for effective treatment planning.
  • Current methods for evaluating airway obstruction can be subjective and time-consuming.

Purpose of the Study:

  • To develop and validate an explainable Artificial Intelligence (AI) model for classifying and quantifying upper airway obstruction related to adenoid hypertrophy.
  • To utilize three-dimensional (3D) shape analysis of cone-beam computed tomography (CBCT) scans for this purpose.
  • To enhance diagnostic accuracy and streamline the assessment process.

Main Methods:

  • Analysis of 400 CBCT scans from patients aged 5-18 years.
  • Calculation of Nasopharyngeal Airway Obstruction (NAO) ratio for ground truth labeling.
  • Training a deep learning model with multiview and point-cloud approaches for 3D shape analysis, classification, and quantification.
  • Utilizing Surface Gradient-weighted Class Activation Mapping (SurfGradCAM) for explainability.

Main Results:

  • The AI model showed strong performance in both classification (AUC 0.77-0.94) and quantification tasks.
  • Excellent discriminative ability for severe obstruction (Grades 3 & 4: AUC 0.88 & 0.94).
  • High correlation (0.854) and R² (0.728) in predicting NAO ratio, with explainability heatmaps highlighting key regions.

Conclusions:

  • The explainable AI model effectively classifies and quantifies adenoid hypertrophy-related upper airway obstruction using 3D CBCT analysis.
  • This automated tool offers a reliable method for standardized assessment, enhancing clinical confidence.
  • The model's explainability improves diagnostic workflow and patient communication, aiding treatment planning.