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 Experiment Video

Updated: Jun 27, 2026

3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

SSMSNet: Scribble-Supervised Myocardial Scar Segmentation in Late Gadolinium Enhancement Images.

Xuewen Liao1,2, Kangwen Yang3, Xingtao Lin3

  • 1Shengli Clinical Medical College of Fujian Medical University, Fuzhou 350013, China.

Diagnostics (Basel, Switzerland)
|June 26, 2026
PubMed
Summary

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

Trends in cardiovascular mortality among lung cancer patients in the United States: a retrospective study from 1999 to 2023.

Cardio-oncology (London, England)·2026
Same author

Cross-Modality Whole-Heart MRI Reconstruction with Deep Motion Correction and Super-Resolution.

Sensors (Basel, Switzerland)·2026
Same author

Knowledge-Guided Framework for Synthesizing Contrast-Dependent Data from Multi-Sequence Non-Contrast MRI.

Diagnostics (Basel, Switzerland)·2026
Same author

Hydrogels Targeting Mechanical-biological signaling transitions of interleukin-33 alleviates intervertebral-disc degeneration.

Materials today. Bio·2026
Same author

Predicting Axillary Lymph Node Metastasis of Breast Cancer Using Joint Pre-Trained Fine-Tuning and Contrastive Learning for Contrast-Enhanced Ultrasound.

Bioengineering (Basel, Switzerland)·2025
Same author

<i>BCL6</i>, <i>DUSP3</i>, and <i>IL6R</i> Are Identified as Shared Druggable Immune-Regulatory Axis in Atrial Fibrillation and Atherosclerosis Through Integrative In Silico and In Vitro Analysis.

Human mutation·2025

This study introduces SSMSNet, a new framework for segmenting myocardial scars in cardiac MRI. It uses limited annotations to achieve accurate scar segmentation, improving cardiac disease assessment.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Cardiology

Background:

  • Accurate myocardial scar segmentation from LGE CMR images is crucial for cardiac disease assessment.
  • Manual annotation is time-consuming and requires clinical expertise due to scar complexity.
  • Scribble supervision offers a cost-effective alternative but faces challenges with sparse data and ambiguous boundaries.

Purpose of the Study:

  • To develop an efficient and accurate scribble-supervised framework for myocardial scar segmentation.
  • To address the challenges of sparse annotations and ambiguous scar boundaries in LGE CMR images.
  • To improve the clinical utility of cardiac magnetic resonance imaging for scar assessment.

Main Methods:

  • Proposed SSMSNet framework integrating anatomical priors and local distance maps.
Keywords:
cardiac anatomy segmentationlocal distance priorscar segmentationweakly supervised learning

More Related Videos

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images
06:57

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Published on: September 22, 2023

Related Experiment Videos

Last Updated: Jun 27, 2026

3D Whole-heart Myocardial Tissue Analysis
06:53

3D Whole-heart Myocardial Tissue Analysis

Published on: April 12, 2017

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images
06:57

Semi-Automatic Graphical Tool for Measuring Coronary Artery Spatially Weighted Calcium Score from Gated Cardiac Computed Tomography Images

Published on: September 22, 2023

  • Employed teacher-student consistency supervision to leverage spatial correlations for scar recovery.
  • Utilized a detail-aware feature enhancement module with attention mechanisms for improved boundary perception.

    • Main Results:

    • SSMSNet demonstrated superior performance over existing scribble-supervised methods on public datasets.
    • The framework achieved competitive results compared to fully supervised segmentation approaches.
    • Experiments confirmed the effectiveness of anatomical guidance, local distance priors, and consistency learning.

    Conclusions:

    • SSMSNet effectively overcomes limitations of sparse scribble annotations for myocardial scar segmentation.
    • The framework offers an annotation-efficient solution for LGE CMR image analysis.
    • This approach enhances the practical application of cardiac MRI in clinical settings.