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

DiffGeo-AOR: Diffusion-Optimized Medical Grading via Geometric Priors enhanced Autoregressive Ordinal Regression.

IEEE transactions on medical imaging·2026
Same author

Real-World Insights in Designing SteatoStat: An End-to-End Deep Learning Pipeline for Hepatic Steatosis Quantification.

Diagnostics (Basel, Switzerland)·2026
Same author

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

Medical image analysis·2026
Same author

DuoMod-Net: Logarithmic balancing and geometric refinement for imbalanced semi-supervised medical image segmentation.

Patterns (New York, N.Y.)·2026
Same author

STAGE challenge: Structural-Functional Transition in Glaucoma Assessment.

Medical image analysis·2026
Same author

Chromosome-level genome assembly of the bird cherry-oat aphid, Rhopalosiphum padi (Hemiptera: Aphididae).

Scientific data·2026

Related Experiment Video

Updated: Jul 6, 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

2.8K

Bilateral Supervision Network for Semi-Supervised Medical Image Segmentation.

Along He, Tao Li, Juncheng Yan

    IEEE Transactions on Medical Imaging
    |December 28, 2023
    PubMed
    Summary

    This study introduces BSNet, a novel semi-supervised learning method for image segmentation. BSNet enhances performance by enabling mutual learning between student and teacher models and improving pseudo-label reliability.

    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

    405
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    8.9K

    Related Experiment Videos

    Last Updated: Jul 6, 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

    2.8K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    405
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    8.9K

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Medical Image Analysis

    Background:

    • Fully-supervised learning for image segmentation demands extensive pixel-level annotations, which are costly and require domain expertise, particularly in medical imaging.
    • Semi-supervised learning (SSL) offers a solution by utilizing abundant unlabeled data to reduce reliance on labeled samples.
    • Existing popular SSL methods like Mean-Teacher (MT) face limitations, including training bottlenecks and inadequate use of unlabeled data information.

    Purpose of the Study:

    • To address the limitations of current semi-supervised learning methods in image segmentation.
    • To propose a novel bilateral supervision network (BSNet) that enhances learning from both labeled and unlabeled data.
    • To improve the accuracy and robustness of image segmentation, especially in medical applications.

    Main Methods:

    • Developed a Bilateral Supervision Network (BSNet) incorporating a bilateral exponential moving average (bilateral-EMA) for model weight updates.
    • Implemented a dual-learning approach where both student and teacher models are trained on labeled data and learn from each other.
    • Utilized pseudo-labels for bilateral supervision on unlabeled data, enhanced by adversarial learning to generate more reliable pseudo-labels.

    Main Results:

    • Extensive experiments on three datasets demonstrated BSNet's effectiveness in semi-supervised image segmentation.
    • BSNet achieved significant performance improvements compared to existing state-of-the-art semi-supervised learning methods.
    • The proposed bilateral supervision and adversarial learning components contributed to enhanced segmentation accuracy.

    Conclusions:

    • BSNet effectively overcomes the limitations of traditional Mean-Teacher models in semi-supervised learning.
    • The proposed method significantly improves image segmentation performance by leveraging unlabeled data more effectively.
    • BSNet represents a promising advancement for semi-supervised image segmentation, particularly in data-scarce domains like medical imaging.