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

COVID-19 mRNA vaccines: a prospective outlook from technological innovation to clinical practice.

Frontiers in immunology·2026
Same author

A nationwide analysis of hospitalised patients with lower respiratory infections in China: life-stage-specific pathogen spectra, co-detection networks, and sex disparities.

Science bulletin·2026
Same author

PWD: Prior-Aware Wavelet Diffusion for Efficient Dental Limited-Angle CT Reconstruction.

IEEE transactions on medical imaging·2026
Same author

Segmentation-Guided Preprocessing Improves Deep Learning Diagnostic Accuracy and Confidence of Ameloblastoma and Odontogenic Keratocyst in Cone Beam CT Images-A Preliminary Study.

Diagnostics (Basel, Switzerland)·2026
Same author

Application and Challenges of Deep Learning in Pulmonary Vessels Segmentation of CTPA Images.

IEEE journal of biomedical and health informatics·2025
Same author

Multi-stage image pyramid network for coarse-to-fine segmentation of temporomandibular joint in CBCT images.

Biomedizinische Technik. Biomedical engineering·2025

Related Experiment Video

Updated: Jun 11, 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

784

Optimal Training Positive Sample Size Determination for Deep Learning with a Validation on CBCT Image Caries

Yanlin Wang1, Gang Li1, Xinyue Zhang1

  • 1National Center for Stomatology & National Clinical Research Center for Oral Diseases & National Engineering Research Center of Oral Biomaterials and Digital Medical Device & Beijing Key Laboratory of Digital Stomatology & NHC Key Laboratory of Digital Stomatology, Department of Oral and Maxillofacial Radiology, Peking University School and Hospital of Stomatology, Beijing 100080, China.

Diagnostics (Basel, Switzerland)
|September 28, 2024
PubMed
Summary

Determining the optimal number of carious teeth for deep learning training is crucial. A new method using single-arm objective performance criteria (OPC) predicts this sample size, improving caries recognition accuracy.

Keywords:
CBCTdeep learningdental cariesoral radiologytraining set

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
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

Related Experiment Videos

Last Updated: Jun 11, 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

784
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
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

Area of Science:

  • Artificial Intelligence in Dentistry
  • Medical Imaging Analysis
  • Machine Learning for Diagnostics

Background:

  • Deep learning model training requires balancing sample size, resources, and time.
  • Accurate caries detection in dental imaging is critical for diagnosis and treatment planning.

Purpose of the Study:

  • To propose and validate a method for determining the optimal positive sample size for training deep learning models in caries recognition.
  • To evaluate the performance of deep learning models against dental radiologists in detecting caries from cone-beam computed tomography (CBCT) images.

Main Methods:

  • Applied single-arm objective performance criteria (OPC) with specified sensitivity values to calculate the optimal training set size.
  • Trained and validated U-Net, YOLOv5n, and CariesDetectNet models on CBCT images with varying numbers of carious teeth.
  • Assessed model performance and compared it with two dental radiologists using an independent dataset.

Main Results:

  • Optimal model performance was achieved with approximately 250 carious teeth in the training set.
  • U-Net achieved superior performance with high accuracy (0.9929), sensitivity (0.9307), specificity (0.9989), F1-Score (0.9590), and Dice similarity (0.9435).
  • The deep learning models demonstrated higher accuracy in caries recognition than dental radiologists.

Conclusions:

  • The positive sample size for training deep learning models on CBCT images for caries detection is predictable.
  • Single-arm objective performance criteria (OPC) provide a reliable method for calculating the optimal sample size, enhancing diagnostic accuracy.