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

Search research articles

Related Experiment Video

Updated: May 8, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Adversarial-consistency enhanced implicit segmentation field for weakly supervised 3D cardiac image segmentation.

Weiyuan Lin¹, Juntao Zhong¹, Zhifan Gao¹

¹School of Biomedical Engineering, Sun Yat-sen University, Shenzhen 518107, China.

Medical Image Analysis

|May 6, 2026

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

Myocardial Temporal-Mechanical Self-Supervision Model for Contrast-Free Myocardial Infarction Segmentation with Label-Free Training.

IEEE transactions on medical imaging·2026

Same author

3D Geometry Scanning and Structural Integrity Assessment to Advance Meniscus Allograft Transplantation.

Annals of biomedical engineering·2026

Same author

Layer-by-layer engineered outer membrane vesicles enable oral upadacitinib delivery for inflammation control and fibrosis attenuation in ulcerative colitis.

Journal of nanobiotechnology·2026

Same author

Preoperative identification of deep myometrial invasion in endometrial cancer: a multicenter MRI study with a vision foundation model-enhanced multimodal deep learning framework.

European journal of obstetrics, gynecology, and reproductive biology·2026

Same author

A Computational Framework for Simulating Patient-Specific TMJ Biomechanics Using a Combined Multibody Dynamics and Finite Element Approach.

Annals of biomedical engineering·2026

Same author

Aptamer-functionalized magnetic beads combined with hybridization chain reaction for detection of Bacillus cereus.

NPJ science of food·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

Same journal

Annotation-efficient medical image segmentation via cross-latent graphs and vector-quantized memory.

Medical image analysis·2026

See all related articles

This summary is machine-generated.

This study introduces a new method for 3D cardiac segmentation using limited annotations. The approach improves accuracy in segmenting heart structures, reducing the need for extensive data labeling in disease diagnosis.

Area of Science:

Medical Imaging
Computer Vision
Machine Learning

Background:

Automatic 3D cardiac structure segmentation is vital for diagnosing heart diseases.
Current methods require expensive pixel-level annotations, increasing labeling costs.
Scribble-level supervision offers a cost-effective alternative but faces challenges with accuracy due to data similarity and sparsity.

Purpose of the Study:

To develop an effective method for accurate 3D cardiac segmentation using cost-efficient scribble-level annotations.
To address the challenges of intrinsic similarity and label sparsity in scribble-based segmentation.
To reduce the overall cost and effort associated with annotating cardiac imaging data.

Main Methods:

Proposed the adversarial-consistency enhanced implicit segmentation field (ACISF) model.

Keywords:

3D cardiac segmentation Adversarial learning Neural field Scribble-level annotation Visual foundation model Weakly supervised learning

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

Related Experiment Videos

Last Updated: May 8, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

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

Extended inference from pixel to coordinate space, modeling semantic information via an implicit function.

Introduced adaptive adversarial consistency (AAC) using adversarial learning for robust segmentation under label sparsity.

Main Results:

The ACISF model effectively integrates topological relationships in coordinate space to overcome intrinsic similarity.
AAC provides adaptive sampling for consistency regularization, mitigating issues from sparse labels.
Extensive experiments on four annotation types and 683 patients demonstrated superior performance compared to ten state-of-the-art methods.

Conclusions:

The proposed ACISF method significantly advances scribble-level supervised 3D cardiac segmentation.
This approach offers a more practical and cost-effective solution for automated cardiac analysis.
The findings have implications for improving the efficiency and accuracy of cardiac disease diagnosis.