Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 26, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

HYPERBOLIC MODEL AGGREGATION FOR FEDERATED LEARNING IN FMRI.

Jiyao Wang¹, Nicha Dvornek^1,2, Peiyu Duan¹

¹Department of Biomedical Engineering, Yale University, USA.

Proceedings. IEEE International Symposium on Biomedical Imaging

|May 25, 2026

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

Next-gen cryo promises transplant surgeons more time.

Nature biotechnology·2026

Same author

STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.

Proceedings of machine learning research·2026

Same author

<i>MFAP2</i> Promotes Glioblastoma Malignant Phenotypes via Autophagy-Dependent Activation of Wnt/β-Catenin Signaling.

Biomedicines·2026

Same author

Interrelationship Between Socioeconomic Status, Depression, and Neuropathy in People with Diabetes: A Cross-Sectional Study.

Journal of clinical medicine·2026

Same author

Centromere protein I promotes hepatocellular carcinoma progression by activating PI3K/AKT/mTOR-CDK2 cascade.

Cancer biology & therapy·2026

Same author

Chlorzoxazone-based One-Sample Method for Estimating In Vivo CYP2E1 Activity in Mice.

Current drug metabolism·2026

Same journal

LEARNABLE HIERARCHICAL VISUAL CONTEXTS FOR TUMOR SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGES.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Same journal

DUAL CROSS-ATTENTION SIAMESE TRANSFORMER FOR RECTAL TUMOR REGROWTH ASSESSMENT IN WATCH-AND-WAIT ENDOSCOPY.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Same journal

LUMEN: LONGITUDINAL MULTI-MODAL RADIOLOGY MODEL FOR PROGNOSIS AND DIAGNOSIS.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Same journal

OVERVIEW OF THE CXR-LT 2026 CHALLENGE: MULTI-CENTER LONG-TAILED AND ZERO SHOT CHEST X-RAY CLASSIFICATION.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Same journal

CROSS-MODAL FINE-TUNING OF 3D CONVOLUTIONAL FOUNDATION MODELS FOR ADHD CLASSIFICATION WITH LOW-RANK ADAPTATION.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

Same journal

AN IN SILICO STUDY OF LOW-INTENSITY FOCUSED ULTRASOUND DISPLACEMENT MAPPING WITH A 220 KHZ CLINICAL PHASED-ARRAY TRANSDUCER.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

See all related articles

This study introduces a novel hyperbolic geometry approach for federated learning in medical imaging, enhancing model aggregation robustness and accuracy for functional MRI data analysis.

Area of Science:

Medical Imaging
Machine Learning
Computational Neuroscience

Background:

Clinical data privacy concerns limit machine learning in medical imaging, especially for costly modalities like functional MRI (fMRI).
Federated learning (FL) addresses data sharing by training local models and aggregating weights, but requires robust strategies for small, heterogeneous medical imaging datasets.

Purpose of the Study:

To introduce a novel federated aggregation scheme using hyperbolic geometry for robust and flexible integration of federated model weights.
To improve the stability and accuracy of federated learning models in multi-site medical imaging studies.

Main Methods:

Developed a federated aggregation scheme based on hyperbolic geometry.
Integrated the hyperbolic aggregation scheme into standard federated learning loops, making it plug-and-play.

Keywords:

Domain adaptation Federated learning Medical imaging fMRI

Related Experiment Videos

Last Updated: May 26, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

Evaluated the method on multi-site functional MRI data from the ABIDE I dataset.

Main Results:

The proposed hyperbolic geometry-based aggregation scheme demonstrated improved stability and accuracy compared to Euclidean mean and median methods.
Achieved more consistent convergence in federated learning for multi-site fMRI data.
The method is compatible with existing federated learning frameworks.

Conclusions:

Federated learning with hyperbolic geometry offers a robust and flexible approach for integrating model weights in medical imaging.
This method effectively addresses challenges posed by small and heterogeneous datasets in federated medical imaging analysis.
The publicly available code facilitates further research and application in privacy-preserving medical machine learning.