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: Apr 1, 2026

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

3.7K

Bridging the Semantic Gap: Synergistic Feature Fusion and Multi-Scale Adaptation for Medical Image Segmentation.

Shaoqiang Wang, Guiling Shi, Chunxin Cheng

    IEEE Journal of Biomedical and Health Informatics
    |March 30, 2026
    PubMed
    Summary
    This summary is machine-generated.

    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

    Higher-Order Dynamic Disentangled Intent Sensing and Bidirectional Joint Updating Framework for NcRNA-Drug Resistance Association Prediction.

    Journal of chemical information and modeling·2026
    Same author

    Metabolic reprogramming of cancer associated fibroblasts informs stromal heterogeneity and therapeutic targeting.

    Discover oncology·2026
    Same author

    Interface engineering of Co<sub>3</sub>O<sub>4</sub> via phosphate functionalization for boosted peroxymonosulfate activation toward efficient tetracycline degradation.

    Environmental research·2026
    Same author

    Inhaled budesonide and beclomethasone for the prevention and treatment of bronchopulmonary dysplasia in very preterm infants: a prospective randomized controlled trial.

    Frontiers in pediatrics·2026
    Same author

    IL-4 in Alzheimer's Disease-Mechanisms and Therapeutic Potential.

    Molecular neurobiology·2026
    Same author

    Learning stable radiation boundaries for wave simulations via passive neural state-space models.

    iScience·2026

    This study introduces the Synergistic Fusion and Refinement Network (SFR-Net) to improve medical image segmentation. SFR-Net enhances accuracy and robustness by addressing perception and fusion challenges in complex clinical scenarios.

    Area of Science:

    • Medical image analysis
    • Computer vision
    • Machine learning

    Background:

    • Medical image segmentation is crucial for clinical diagnosis.
    • Standard architectures face limitations in complex scenarios due to perception-representation and fusion-adaptation issues.
    • Existing methods struggle with detailed feature extraction and multi-scale target adaptation.

    Purpose of the Study:

    • To propose a novel network, the Synergistic Fusion and Refinement Network (SFR-Net), to overcome limitations in medical image segmentation.
    • To improve the handling of complex scenarios by addressing the perception-representation dilemma and fusion-adaptation misalignment.
    • To achieve state-of-the-art performance in medical image segmentation accuracy and robustness.

    Main Methods:

    • Introduction of a Local-Regional Feature Perception (LRFP) module to integrate fine-grained details with global context.

    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

    866

    Related Experiment Videos

    Last Updated: Apr 1, 2026

    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

    3.7K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    866
  • Implementation of a Channel Refinement and Enhancement Module (CREM) in skip connections to bridge semantic gaps.
  • Utilization of a Feature Mixing Module (FMM) at the bottleneck for dynamic adaptation to multi-scale targets.

    • Main Results:

    • SFR-Net effectively couples local and regional features from the input stage.
    • The CREM and FMM modules successfully address semantic gaps and multi-scale adaptation.
    • Experiments on CVC-ClinicDB, ISIC 2017, TN3K, and MICCAI Tooth datasets show superior performance.

    Conclusions:

    • SFR-Net demonstrates significant improvements in medical image segmentation.
    • The proposed network overcomes systemic limitations of existing architectures.
    • SFR-Net achieves state-of-the-art accuracy and robustness in diverse medical imaging datasets.