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

A cell lines derived microfluidic liver model for investigation of hepatotoxicity induced by drug-drug interaction.

Biomicrofluidics·2019

Same author

Metformin inhibits the proliferation of rheumatoid arthritis fibroblast-like synoviocytes through IGF-IR/PI3K/AKT/m-TOR pathway.

Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie·2019

Same author

A MAPbBr<sub>3</sub>:poly(ethylene oxide) composite perovskite quantum dot emission layer: enhanced film stability, coverage and device performance.

Nanoscale·2019

Same author

Evidence for relaxed selection of mitogenome in rapid-flow cyprinids.

Genes & genomics·2019

Same author

Change in albuminuria as a surrogate endpoint in chronic kidney disease.

The lancet. Diabetes & endocrinology·2019

Same author

Long-term prognostic utility of computed tomography coronary angiography in older populations.

European heart journal. Cardiovascular Imaging·2019

Same journal

Towards haplotypes of blood group genes: the impact of long-read sequencing in molecular immunohematology.

Annals of translational medicine·2026

Same journal

Development of pharmacological interventions for the treatment of sarcopenia.

Annals of translational medicine·2026

Same journal

Fertility preservation in young women with breast cancer: a narrative review of effectiveness, oncologic safety, and clinical practice implications.

Annals of translational medicine·2026

Same journal

Propofol-based total intravenous anesthesia and recurrence-free survival after hepatectomy-does it improve outcomes?

Annals of translational medicine·2026

Same journal

Is pulmonary hypertension still a contraindication for lung volume reduction?-a narrative review of contemporary evidence.

Annals of translational medicine·2026

Same journal

Calcium montmorillonite clay: a clinically oriented narrative review of emerging perioperative and supportive applications.

Annals of translational medicine·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 9, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

Tracking-based deep learning method for temporomandibular joint segmentation.

Yi Liu¹, Yao Lu², Yubo Fan^3,4

¹School of Biological Science and Medical Engineering, Beihang University, Beijing, China.

Annals of Translational Medicine

|April 14, 2021

Summary

This summary is machine-generated.

This study introduces an AI algorithm for segmenting temporomandibular joint (TMJ) components from low-dose CT scans. The method accurately identifies glenoid fossae and condyles, improving diagnosis for TMJ disease.

Keywords:

Biomedical imaging computer-aided diagnosis deep learning image segmentation low-dose computed tomography (low-dose CT)tracking

More Related Videos

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

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

Related Experiment Videos

Last Updated: Nov 9, 2025

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

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

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Outer-Boundary Assisted Segmentation and Quantification of Trabecular Bones by an Imagej Plugin

Published on: March 14, 2018

Area of Science:

Medical imaging analysis
Artificial intelligence in healthcare
Anatomy and diagnostics

Background:

Accurate segmentation of temporomandibular joint (TMJ) components is crucial for diagnosis and treatment.
TMJ disease can cause surface abrasion, leading to fuzzy edges in computed tomography (CT) imaging, complicating segmentation, especially with low-dose CT.

Purpose of the Study:

To develop an automatic deep learning-based algorithm for simultaneous segmentation of TMJ glenoid fossae and condyles.
To address the challenges posed by low-dose CT imaging in TMJ segmentation.

Main Methods:

A U-Net deep learning model was employed for initial image segmentation into glenoid fossae, condyles, and background.
A post-processing step utilized a snake model with internal force constraints and tracking-based boundary initialization to refine segmentation and repair fractures.
The algorithm was validated on 206 low-dose CT cases using Dice coefficient (DC) and mean surface distance (MSD) metrics.

Main Results:

The proposed algorithm achieved state-of-the-art performance.
High Dice coefficients were reported: 0.92±0.03 for condyles and 0.90±0.04 for glenoid fossae.
Low mean surface distances were observed: 0.20±0.19 mm for condyles and 0.19±0.08 mm for glenoid fossae.

Conclusions:

This research presents the first simultaneous segmentation of TMJ glenoid fossae and condyles.
The U-Net and tracking-based algorithm demonstrates high segmentation efficiency and accuracy for TMJ analysis.
The developed method offers a promising tool for improved diagnosis and treatment planning in TMJ disorders.