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

A natural variation in the promoter of OsPME29 enhances lodging resistance in rice.

Plant communications·2026
Same author

Lateral stability control of distributed drive electric vehicles via controllable-region analysis and adaptive torque distribution.

ISA transactions·2026
Same author

3D point cloud driven organ semantic segmentation to assess maize structural responses along the planting-density gradient.

Plant phenomics (Washington, D.C.)·2026
Same author

Corrigendum to "Associations between multiple metals exposure and cognitive function in the middle-aged and older adults from China: A cross-sectional study" [Environ. Res., 263(Pt 1), 2024, 120038].

Environmental research·2026
Same author

A Self-Immunoregulatory Nanosensitizer for Sonodynamic Cancer Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Ontology-driven dual-channel relational graph convolutional network (DCR-GCN) for lettuce leaf phenotype classification.

Plant methods·2026

Related Experiment Video

Updated: Jan 10, 2026

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

727

SVMB-Net: Local Global Fusion and Multi-Branch Cross-Feature Attention for Skin Lesion Segmentation.

Yuan Zhao, Jinlai Zhang, Wujiao He

    IEEE Journal of Biomedical and Health Informatics
    |November 24, 2025
    PubMed
    Summary

    SVMB-Net, a novel dual-architecture framework, enhances skin lesion segmentation accuracy for early cancer diagnosis by integrating SwinTransformer and CNN. This method significantly improves upon existing techniques, offering a powerful solution for automated clinical analysis.

    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

    3.3K
    SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
    06:34

    SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

    Published on: August 8, 2025

    502

    Related Experiment Videos

    Last Updated: Jan 10, 2026

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    727
    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

    3.3K
    SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
    06:34

    SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

    Published on: August 8, 2025

    502

    Area of Science:

    • Medical image analysis
    • Computer vision
    • Artificial intelligence in healthcare

    Background:

    • Accurate skin lesion segmentation is critical for early skin cancer diagnosis.
    • Challenges include irregular shapes, varied textures, and low contrast in lesions.
    • Existing methods struggle with the complex morphological variations of skin lesions.

    Purpose of the Study:

    • To propose SVMB-Net, a novel dual-architecture framework for improved skin lesion segmentation.
    • To address limitations in current segmentation methods for complex skin lesion characteristics.
    • To provide a robust solution for automated skin lesion analysis in clinical settings.

    Main Methods:

    • Developed SVMB-Net, a hybrid framework integrating SwinTransformer and Convolutional Neural Networks (CNN).
    • Introduced a Super ViT-CNN (SViT-C) hybrid encoder with a global restoration module.
    • Implemented a dual-branch fusion module for synergistic local and global feature extraction.
    • Designed a multi-branch deep cross-feature attention decoder with a multi-scale attention mechanism.

    Main Results:

    • SVMB-Net achieved superior performance on ISIC2018, improving DSC by 7.67% to 93.88% and ACC by 2.21% to 96.97% compared to DINOv2.
    • On ISIC2017 and PH2 datasets, SVMB-Net obtained an IoU of 83.45% and ACC of 97.08%.
    • Outperformed 16 existing methods, including SAM2-UNet and VM-UNet, demonstrating significant advancements.

    Conclusions:

    • SVMB-Net offers a powerful and accurate solution for automated skin lesion segmentation.
    • The proposed architecture effectively handles complex morphological variations in skin lesions.
    • This method holds significant potential for improving early skin cancer detection and clinical analysis.