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

APASL clinical practice guidance: the diagnosis and management of patients with Wilson's disease.

Hepatology international·2026
Same author

Prediction of Coal Spontaneous Combustion Risk under Poor Oxygen Concentration Based on Fuzzy Clustering and Lattice Tightness.

ACS omega·2026
Same author

Multi-omics analysis identifies key genes and functional loci affecting teat number in American Large White and Landrace pigs and their application in optimizing genomic selection models.

BMC genomics·2026
Same author

Regional immunity in the respiratory tract: challenges and opportunities.

Science bulletin·2026
Same author

Correction: Elevated IL-17A level is associated with poor overall survival following immune checkpoint inhibitors combined with targeted therapy in hepatocellular carcinoma with hyperbilirubinemia.

Frontiers in immunology·2026
Same author

Synergistic Regulation of Codonopsis pilosula Growth and Metabolism by Trichoderma, Salicylic Acid, and Methyl Jasmonate.

Physiologia plantarum·2026

Related Experiment Video

Updated: Aug 27, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485

Two-Stage CNN Whole Heart Segmentation Combining Image Enhanced Attention Mechanism and Metric Classification.

Xuchu Wang1, Fusheng Wang2, Yanmin Niu3

  • 1Key Laboratory of Optoelectronic Technology and Systems of Ministry of Education, College of Optoelectronic Engineering, Chongqing University, Chongqing, 400040, China. xcwang@cqu.edu.cn.

Journal of Digital Imaging
|September 29, 2022
PubMed
Summary

This study introduces a novel two-stage convolutional neural network (CNN) for cardiac MRI segmentation. The method enhances tissue feature extraction and boundary refinement for improved computer-aided cardiovascular diagnosis.

Keywords:
Attention mechanismCardiac multi-target segmentationConvolutional neural networkImage enhancementMetric classification

More Related Videos

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

2.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

613

Related Experiment Videos

Last Updated: Aug 27, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

485
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

2.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

613

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Cardiovascular Diagnostics

Background:

  • Accurate segmentation of cardiac tissues and organs in magnetic resonance imaging (MRI) is crucial for computer-aided cardiovascular diagnosis.
  • Challenges include complex tissue distribution, low feature discriminability, and large organ sizes in cardiac MRI slices.
  • Existing methods struggle with segmenting subtle and adherent tissue boundaries.

Purpose of the Study:

  • To develop an advanced segmentation method for cardiac MRI to address current segmentation challenges.
  • To improve the accuracy and robustness of automated cardiac tissue and organ segmentation.
  • To enhance computer-aided diagnosis through precise delineation of cardiac structures.

Main Methods:

  • A two-stage convolutional neural network (CNN) segmentation approach combining a Log-Gabor filter attention mechanism and metric classification.
  • Log-Gabor filterbank enhances tissue texture and contour information.
  • Spatial and channel attention mechanisms with varying kernel sizes adaptively extract features and focus on discriminative information.
  • A metric classification network refines segmentation of difficult boundaries.

Main Results:

  • The proposed method was validated on a cardiac MRI dataset for segmenting 7 cardiac tissues.
  • The approach demonstrated effectiveness in enhancing feature extraction and refining segmentation boundaries.
  • Achieved competitive performance compared to existing deep learning-based segmentation models.

Conclusions:

  • The proposed two-stage CNN method effectively addresses challenges in cardiac MRI segmentation.
  • The integration of Log-Gabor filters, attention mechanisms, and metric classification improves segmentation accuracy, especially for intricate boundaries.
  • This method shows significant potential for advancing computer-aided cardiovascular diagnosis.