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

Modeling stimulus-induced stress responses in microglia-like cells using a commercial iPSC-dCas9-KRAB line.

Stem cell research·2026
Same author

Innovative Clinical Trial Approach for Evaluating Digital Medical Devices Under European Fast-Track Regulatory Frameworks.

Statistics in medicine·2026
Same author

Causal mediation analysis with one or multiple mediators: A comparative study.

Psychological methods·2026
Same author

Tau seeds induce neurofibrillary tangle formation across brain regions via individual-specific connectivity.

Neuron·2026
Same author

NeuroConText: Contrastive learning for neuroscience meta-analysis with rich text representation.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Early Marrow Microenvironment Immune Patterns After Hematopoietic Stem Cell Transplant in Pediatric Acute Lymphoblastic Leukemia Are Associated with Later Development of Chronic GvHD and Relapse.

International journal of molecular sciences·2026

Related Experiment Video

Updated: Apr 5, 2026

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.7K

Transport on Riemannian Manifold for Connectivity-Based Brain Decoding.

Bernard Ng, Gael Varoquaux, Jean Baptiste Poline

    IEEE Transactions on Medical Imaging
    |August 11, 2015
    PubMed
    Summary

    This study introduces a novel Riemannian approach for brain decoding using functional magnetic resonance imaging (fMRI). The method enhances classification accuracy by addressing statistical dependencies in brain connectivity data, improving the identification of significant brain connections.

    More Related Videos

    Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
    17:06

    Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

    Published on: November 8, 2012

    27.2K
    Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
    09:55

    Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

    Published on: June 13, 2025

    3.1K

    Related Experiment Videos

    Last Updated: Apr 5, 2026

    Modeling the Functional Network for Spatial Navigation in the Human Brain
    05:55

    Modeling the Functional Network for Spatial Navigation in the Human Brain

    Published on: October 13, 2023

    1.7K
    Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
    17:06

    Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

    Published on: November 8, 2012

    27.2K
    Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping
    09:55

    Neuroimaging-Guided TMS–EEG for Real-Time Cortical Network Mapping

    Published on: June 13, 2025

    3.1K

    Area of Science:

    • Neuroimaging
    • Machine Learning
    • Cognitive Neuroscience

    Background:

    • Functional magnetic resonance imaging (fMRI) is increasingly used for decoding naturalistic cognitive states.
    • Traditional methods using Pearson's correlation for brain connectivity features violate classifier assumptions due to inter-related elements in covariance matrices.
    • Small sample sizes further limit the generalizability and interpretability of classifiers in fMRI studies.

    Purpose of the Study:

    • To develop a Riemannian approach for connectivity-based brain decoding to improve classification accuracy and feature interpretability.
    • To address the statistical dependencies inherent in covariance matrices derived from fMRI data.
    • To introduce a robust method for identifying significant brain connections from classifier weights.

    Main Methods:

    • A Riemannian approach was employed, projecting covariance estimates onto a common tangent space to reduce feature dependencies.
    • Matrix whitening transport and parallel transport (Schild's ladder algorithm) were proposed and compared.
    • fMRI data from 24 subjects performing continuous, self-driven tasks were analyzed.
    • A non-parametric scheme combining bootstrapping and permutation testing was developed for identifying discriminative brain connections.

    Main Results:

    • The Riemannian approach significantly outperformed direct use of Pearson's correlation and its regularized variants in classification accuracy.
    • The proposed non-parametric scheme successfully identified neuro-anatomically meaningful brain connections.
    • Pure permutation testing failed to detect significant connections, highlighting the utility of the new scheme.

    Conclusions:

    • The Riemannian approach offers a more effective strategy for brain decoding using fMRI connectivity data.
    • This method improves the generalizability and interpretability of machine learning models applied to neuroimaging.
    • The developed significance testing scheme enhances the identification of biologically relevant brain networks.