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

Obesity-Related Insulin Resistance Indices and CKD Risk in Patients with Diabetes and Coronary Heart Disease: A Multicenter Cohort Analysis.

Diabetes, metabolic syndrome and obesity : targets and therapy·2026
Same author

Inflammation Mediates the Relationship Between Serum Uric Acid and New-Onset Diabetes Risk in Patients with Coronary Heart Disease: Results from a Multicenter Cohort Study.

Diabetes, metabolic syndrome and obesity : targets and therapy·2026
Same author

Sulfur-Substituted SAMs Induce Pb─S Antibonding Hybridization for Efficient and Durable Perovskite-Silicon Tandems.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Single B-Cell-Based Generation of Porcine Anti-CSFV E<sup>rns</sup> Monoclonal Antibodies and Application in a Blocking ELISA Assay.

International journal of molecular sciences·2026
Same author

JMJD3-driven epigenetic reprogramming of p16<sup>INK4a</sup>-positive cells promotes tendon regeneration.

Bone research·2026
Same author

Comparative physiological and transcriptomic analysis of rapid post-midday photosynthetic recovery in Saccharum spontaneum reveals candidate pathways for sugarcane improvement.

BMC plant biology·2026

Related Experiment Video

Updated: Jul 6, 2025

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

1.8K

Mask refinement network for tooth segmentation on panoramic radiographs.

Li Niu1, Shengwei Zhong2, Zhiyu Yang1

  • 1Nanjing Stomatological Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, Jiangsu Province 210008, China.

Dento Maxillo Facial Radiology
|January 2, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces a deep learning algorithm for precise tooth segmentation in panoramic radiographs. The novel mask refinement network significantly improves accuracy for clinical diagnosis and automated dental applications.

Keywords:
edge lossmask refinementpanoramic radiographstooth segmentationweighted mask

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

9.6K
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

865

Related Experiment Videos

Last Updated: Jul 6, 2025

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

1.8K
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

9.6K
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

865

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Instance-level tooth segmentation in panoramic radiographs (PRs) is crucial for extracting detailed localization and shape information.
  • Accurate segmentation aids in clinical diagnosis and treatment planning.

Purpose of the Study:

  • To evaluate a mask refinement network designed for precise tooth edge extraction from PRs.
  • To assess the performance of a novel deep learning algorithm for individual tooth segmentation.

Main Methods:

  • Utilized a public dataset of 543 PRs with 16211 labeled teeth.
  • Employed a Mask Region-based Convolutional Neural Network (Mask RCNN) as a baseline.
  • Developed a novel loss function for accurate mask edge generation and compared it with three existing methods.

Main Results:

  • The proposed mask refinement network achieved high performance with an Average Precision (AP) of 0.686, precision of 0.979, and recall of 0.952.
  • The mean Intersection over Union (mIoU) was 0.941, and the mean Hausdorff distance (mHAU) was 9.7.
  • The algorithm demonstrated significantly superior results compared to existing tooth segmentation methods.

Conclusions:

  • An efficient deep learning algorithm was developed for accurate individual tooth mask extraction from PRs.
  • Precise tooth masks serve as valuable references for clinical diagnosis and treatment.
  • This algorithm provides a foundational basis for advanced automated processing in dentistry.