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: Nov 29, 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

3.2K

Variation-Aware Federated Learning With Multi-Source Decentralized Medical Image Data.

Zengqiang Yan, Jeffry Wicaksana, Zhiwei Wang

    IEEE Journal of Biomedical and Health Informatics
    |November 24, 2020
    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

    Efficient and accurate neural-field reconstruction using resistive memory.

    Nature·2026
    Same author

    Resistive memory-based neural differential equation solver for score-based diffusion model.

    Nature communications·2026
    Same author

    Pruning random resistive memory for optimizing analog AI.

    Nature communications·2026
    Same author

    FedHAC: Towards Robust Federated Multi-Lesion Segmentation With Heterogeneous Annotation Completeness.

    IEEE journal of biomedical and health informatics·2025
    Same author

    A generalizable pathology foundation model using a unified knowledge distillation pretraining framework.

    Nature biomedical engineering·2025
    Same author

    Continuous-time digital twin with analog memristive neural ordinary differential equation solver.

    Science advances·2025

    Federated learning (FL) addresses privacy in medical imaging by minimizing data variations across institutions. Our variation-aware FL framework enhances privacy-preserving image analysis for better classification outcomes.

    Area of Science:

    • Medical Imaging Analysis
    • Machine Learning
    • Data Privacy

    Background:

    • Medical image datasets are often fragmented across institutions due to privacy concerns, hindering the development of large-scale AI models.
    • Federated learning (FL) offers a privacy-preserving approach for multi-source decentralized data but struggles with cross-client data variations.

    Purpose of the Study:

    • To propose a novel variation-aware federated learning (VAFL) framework to address cross-client data variations in medical imaging.
    • To enable privacy-preserving federated learning for medical image analysis by minimizing data heterogeneity.

    Main Methods:

    • Developed a variation-aware federated learning (VAFL) framework using a privacy-preserving generative adversarial network (PPWGAN-GP) to synthesize common image space data.
    • Employed a modified CycleGAN for each client to translate its local medical images to the shared target image space.

    Related Experiment Videos

    Last Updated: Nov 29, 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

    3.2K
  • Selected a subset of synthesized images that capture raw data characteristics while maintaining distinctness for inter-client sharing.

    • Main Results:

    • The proposed VAFL framework effectively minimizes cross-client variations by transforming images into a common space.
    • VAFL demonstrated stable performance improvements over standard horizontal FL frameworks in automated prostate cancer classification.
    • The framework achieved this using multi-source decentralized apparent diffusion coefficient (ADC) MRI data.

    Conclusions:

    • The VAFL framework successfully addresses the cross-client variation problem in federated medical image analysis while preserving data privacy.
    • VAFL is architecture-agnostic, suggesting broad applicability to various medical image classification tasks beyond prostate cancer detection.