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 Videos

Meta-Learning Coupled with Transfer Learning for Improved Few-Shot Classification of Cardiac MR Images.

Tijana Geroski, Mahyar Bolhassani, Nenad Filipovic

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 3, 2025
    PubMed
    Summary

    Related Concept Videos

    Imaging Studies for Cardiovascular System V: CT01:28

    Imaging Studies for Cardiovascular System V: CT

    261
    Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
    261

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Editorial: Bioresorbable materials: What is new?

    Frontiers in bioengineering and biotechnology·2026
    Same author

    Apoptosis execution is spatially regulated.

    Apoptosis : an international journal on programmed cell death·2026
    Same author

    Differences in clinical presentation between heart failure patients with reduced and preserved ejection fraction - analysis of the INTELHEART database.

    Acta cardiologica·2026
    Same author

    Ionic Extracts of Magnesium Powders Promote In Vitro Lymphangiogenesis.

    Biomedicines·2026
    Same author

    Sustainable Collagen-Based Hydrogel Integrated with Bioactive Glass for Minimally Invasive, Growth Factor-Free Immunomodulatory Maxillofacial Bone Regeneration.

    Advanced healthcare materials·2026
    Same author

    Voice recognition as an innovative method to identify and monitor heart failure - a review.

    Heart failure reviews·2026

    This study introduces a new meta-transfer learning framework for classifying cardiac magnetic resonance (CMR) images with limited data. The method significantly improves diagnostic accuracy for various cardiac conditions, even with few labeled samples.

    Area of Science:

    • Medical Imaging
    • Artificial Intelligence
    • Cardiology

    Background:

    • Limited annotated medical data hinders deep learning for cardiac magnetic resonance (CMR) image classification.
    • Traditional methods struggle with the scarcity of labeled datasets in clinical settings.

    Purpose of the Study:

    • To develop a novel meta-transfer learning framework for few-shot classification of CMR images.
    • To address the challenge of limited annotated medical data in cardiac imaging diagnostics.

    Main Methods:

    • A meta-transfer learning framework combining pre-trained deep neural networks and few-shot classification.
    • Experiments explored same and different classes in pre-training and meta-training phases.
    • Utilized few-shot learning mechanisms across 1-shot, 3-shot, and 5-shot scenarios.

    Related Experiment Videos

    Main Results:

    • Significant improvements in classification accuracy and generalization were observed, even with minimal labeled samples.
    • The model achieved competitive results compared to state-of-the-art methods on the ACDC dataset.
    • Demonstrated effectiveness in both binary (healthy vs. diseased) and 5-class cardiac condition classification.

    Conclusions:

    • Meta-transfer learning shows significant potential for improving diagnostic workflows in cardiac imaging.
    • The proposed framework enhances diagnostic accuracy and generalization for CMR image classification with limited data.
    • Contributes to improved diagnostic and treatment planning for cardiac conditions in data-scarce clinical environments.