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

Association of high-sensitivity C-reactive protein-to-hemoglobin ratio with stroke risk: A study based on the China Health and Retirement Longitudinal Study and English Longitudinal Study of Ageing cohorts.

The Journal of international medical research·2026
Same author

Regulatory adaptation of an accessory gene controls fungal halotolerance and niche expansion.

The ISME journal·2026
Same author

Domain-agnostic Unsupervised Domain Adaptation Segmentation from 3D Carotid Artery Ultrasound Image.

IEEE journal of biomedical and health informatics·2026
Same author

Review of Current Advances in Ultrasound Computed Tomography for Medical Imaging.

IEEE reviews in biomedical engineering·2026
Same author

Dual Biocontrol and Plant Growth-Promoting Effects of <i>Trichoderma nordicum</i> V1 Against Oomycete Plant Pathogens.

Journal of fungi (Basel, Switzerland)·2026
Same author

Rational Hapten Engineering Enables a Monoclonal Antibody for the Masked-Mycotoxin Zearalenone-14-Glucoside and Field-Deployable Digital Immunoassays.

Analytical chemistry·2026

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

592

Medical Image Classification Using Light-Weight CNN With Spiking Cortical Model Based Attention Module.

Quan Zhou, Zhiwen Huang, Mingyue Ding

    IEEE Journal of Biomedical and Health Informatics
    |April 6, 2023
    PubMed
    Summary

    A new spiking cortical model based global and local (SCM-GL) attention module enhances light-weight convolutional neural networks (CNNs) for disease diagnosis. This SCM-GL module improves feature extraction, leading to better accuracy in medical image classification.

    More Related Videos

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.7K
    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

    Related Experiment Videos

    Last Updated: Aug 4, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    592
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    42.7K
    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

    Area of Science:

    • Artificial Intelligence
    • Medical Imaging
    • Computational Neuroscience

    Background:

    • Light-weight convolutional neural networks (CNNs) are vital for disease diagnosis with limited medical image datasets, mitigating overfitting and enhancing efficiency.
    • However, light-weight CNNs exhibit weaker feature extraction capabilities compared to heavy-weight models.
    • Existing attention modules lack sufficient non-linearity, hindering the discovery of critical features in medical images.

    Purpose of the Study:

    • To introduce a novel Spiking Cortical Model based Global and Local (SCM-GL) attention module.
    • To enhance the feature extraction capabilities of light-weight CNNs for improved disease diagnosis.
    • To address the limitations of existing attention mechanisms in capturing key image features.

    Main Methods:

    • The SCM-GL module processes input feature maps in parallel, decomposing them into local components based on pixel neighborhood relationships.
    • It generates a global mask by identifying correlations between distant pixels within feature maps.
    • Local and global masks are combined to create a final attention mask, which is applied to highlight important image components.

    Main Results:

    • Experiments integrated the SCM-GL module into popular light-weight CNNs and compared its performance against mainstream attention modules.
    • The SCM-GL module significantly improved classification performance across brain MR, chest X-ray, and osteosarcoma image datasets.
    • The module demonstrated superior accuracy, recall, specificity, and F1 score compared to state-of-the-art attention modules.

    Conclusions:

    • The SCM-GL attention module effectively enhances the ability of light-weight CNNs to detect suspected lesions in medical images.
    • This novel module offers a significant improvement over existing attention mechanisms for disease diagnosis.
    • The SCM-GL module shows great promise for accurate and efficient medical image analysis.