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

Hepatoprotective Effect of <i>Morchella</i> Mycelia Polysaccharides on Alcoholic Liver Injury and Its Mechanism Involving the Modulation of NOD-Like Receptor Signaling Pathway.

Food science & nutrition·2026
Same author

Consensus from the Asian conference on tumor ablation working group on image-guided thermal ablation for lung tumor: 10 key questions and answers.

Journal of cancer research and therapeutics·2025
Same author

The mechanism of <i>Bacillus subtilis</i> regulating the underground system and bamboo shoot quality of Lei bamboo (<i>Phyllostachys praecox</i>) under bamboo charcoal addition.

Frontiers in plant science·2025
Same author

Sustainable silylated bacterial cellulose/MgAl-LDH composite aerogel integrating radiative cooling and thermal insulation for building energy saving.

International journal of biological macromolecules·2025
Same author

Uncertainty-Guided Prototype Reliability Enhancement Network for Few-Shot Medical Image Segmentation.

IEEE transactions on medical imaging·2025
Same author

Uncertainty-Aware Cross-Training for Semi-Supervised Medical Image Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Related Experiment Video

Updated: Sep 29, 2025

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

3.0K

A U-snake based deep learning network for right ventricle segmentation.

Kaiwen Huang1, Lei Xu1, Yingliang Zhu1

  • 1The School of Optical-Electrical & Computer Engineering, University of Shanghai for Science & Technology, Shanghai, China.

Medical Physics
|March 18, 2022
PubMed
Summary

A novel deep learning U-Snake network achieves accurate automatic right ventricular segmentation in MR images, surpassing traditional methods. This AI tool aids in heart condition monitoring but currently serves as an auxiliary aid.

Keywords:
U-snakelevel setright ventricle segmentation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Related Experiment Videos

Last Updated: Sep 29, 2025

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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.7K

Area of Science:

  • Medical Imaging Analysis
  • Deep Learning in Cardiology
  • Computational Anatomy

Background:

  • Manual segmentation of cardiac ventricles is time-consuming and subjective.
  • Accurate segmentation is crucial for monitoring heart conditions.
  • Existing methods struggle with the complex shape of the right ventricle.

Purpose of the Study:

  • To develop an automatic segmentation method for the right ventricle using deep learning.
  • To improve segmentation accuracy and efficiency compared to manual and traditional approaches.

Main Methods:

  • Proposed the U-Snake network, combining deep snake and level set methods.
  • Utilized circular convolution with multiple dilation rates for feature aggregation.
  • Incorporated dice loss function and transferred U-Snake results to level set for enhanced small object segmentation.

Main Results:

  • Achieved a Dice coefficient of 0.911 on the right ventricular test set 2.
  • Demonstrated segmentation speed of 5 frames per second.
  • Outperformed classical deep learning methods like Residual U-net, Inception CNN, and Dilated CNN.

Conclusions:

  • The U-Snake network offers a significant advancement in automatic ventricular segmentation.
  • The method shows superior performance compared to existing deep learning and mathematical approaches.
  • The tool is effective as an auxiliary aid for clinicians in heart condition monitoring.