Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

[Clinical symptoms and cone beam computed tomography imaging analysis of patients with temporomandibular joint osteoarthritis with chewing side preference before and after treatment of stabilization splint].

Hua xi kou qiang yi xue za zhi = Huaxi kouqiang yixue zazhi = West China journal of stomatology·2026

Same author

KLF11 interacts with MDM2 to stabilize E2F1 and promotes DNA damage repair to induce radioresistance in esophageal cancer cells.

Pathology, research and practice·2026

Same author

Healthy Sleep Patterns, Mortality, and Life Expectancy in Adults With and Without Atherosclerotic Cardiovascular Disease.

JACC. Advances·2026

Same author

Model sensitivity of Tibetan plateau surface potential vorticity and the Asian summer monsoon system to Asian orographic perturbation in FGOALS-f2.

Fundamental research·2025

Same author

Historical Neighborhood Redlining and Fertility in a Cohort of US Black Women.

Epidemiology (Cambridge, Mass.)·2025

Same author

Dual-Triggered Release Mechanisms in Calcium Alginate/Fe<sub>3</sub>O<sub>4</sub> Capsules for Asphalt Self-Healing: Cyclic Load-Induced Sustained Release and Microwave-Activated On-Demand Delivery.

Polymers·2025

Same journal

Preface to the Special Topic on Computer Mathematics.

Journal of systems science and complexity·2024

Same journal

Economic Policy Uncertainty: Cross-Country Linkages and Spillover Effects on Economic Development in Some Belt and Road Countries.

Journal of systems science and complexity·2023

Same journal

Empirical Likelihood for a First-Order Generalized Random Coefficient Integer-Valued Autoregressive Process.

Journal of systems science and complexity·2023

Same journal

Business Environment and Resource Allocation Based on the Perspective of the National Value Chain.

Journal of systems science and complexity·2023

Same journal

Optimal Pricing and Return-Freight Insurance: Strategic Analysis of <i>E</i>-Sellers in the Presence of Reputation Differentiation.

Journal of systems science and complexity·2023

Same journal

Illiquidity Comovement and Market Crisis.

Journal of systems science and complexity·2022

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Transformer-Based Deep Learning Network for Tooth Segmentation on Panoramic Radiographs.

Chen Sheng^1,2, Lin Wang^1,2,3, Zhenhuan Huang^1,2,3

¹Medical School of Chinese PLA, Beijing, 100853 China.

Journal of Systems Science and Complexity

|October 19, 2022

Summary

This summary is machine-generated.

This study introduces SWin-Unet for segmenting teeth on panoramic radiographs, improving diagnostic accuracy. The AI model significantly outperforms existing methods on the PLAGH-BH dataset.

Keywords:

Deep convolutional neural network SWin-Unet Tooth segmentation panoramic radiograph

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Aug 25, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

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

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

Published on: November 30, 2022

Area of Science:

Artificial Intelligence in Dentistry
Medical Image Analysis
Deep Learning for Dental Imaging

Background:

Panoramic radiographs are crucial for assessing oral health, but their interpretation relies heavily on dentist expertise, risking misdiagnosis.
Accurate tooth detection and localization on radiographs are vital for pathology identification and automated diagnostic systems.
The subjective nature of manual interpretation highlights the need for AI-driven solutions in dental radiography.

Purpose of the Study:

To introduce and evaluate the SWin-Unet model for automated tooth segmentation on panoramic radiographs.
To assess the performance of SWin-Unet against established baseline models using a dedicated dataset.
To explore the potential of AI in enhancing the accuracy and efficiency of dental radiographic analysis.

Main Methods:

Utilized SWin-Unet, a transformer-based U-shaped encoder-decoder architecture with skip-connections, for panoramic radiograph segmentation.
Introduced the PLAGH-BH dataset specifically for evaluating tooth segmentation performance.
Employed F1 score, mean Intersection over Union (IoU), and accuracy (Acc) as key performance metrics.

Main Results:

SWin-Unet demonstrated superior performance in tooth segmentation compared to U-Net, Link-Net, and FPN baselines on the PLAGH-BH dataset.
Quantitative evaluation showed significantly better results for SWin-Unet across the chosen metrics (F1 score, IoU, Acc).
The model's effectiveness suggests a strong potential for improving automated analysis of dental radiographs.

Conclusions:

SWin-Unet is a highly feasible and effective deep learning model for segmenting teeth in panoramic radiographs.
The proposed method offers a valuable tool for potential clinical applications, aiding dentists in diagnosis and treatment planning.
This AI-driven approach can lead to more objective and reliable interpretation of dental images, reducing diagnostic errors.