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

Ecological Vision Hypothesis: Training Deep Neural Networks for Robustness and Human Alignment.

Annual review of vision science·2026
Same author

Exposure to naturalistic occlusion promotes generalized, human-like robustness in deep neural networks.

bioRxiv : the preprint server for biology·2026
Same author

Suppression of information spreading in MEG source estimation using a functionally-structured Bayesian approach.

NeuroImage·2026
Same author

Inferring relationships among major psychiatric disorders in a resting-state functional connectivity-informed embedding space.

NPJ systems biology and applications·2026
Same author

Channel gain calibrated signal space projection using variational Bayesian estimation for optically pumped magnetometers.

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

Extraction of robust functional connectivity patterns across psychiatric disorders using principal component analysis-based feature selection.

Imaging neuroscience (Cambridge, Mass.)·2026

Related Experiment Video

Updated: Jul 3, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Sparse estimation automatically selects voxels relevant for the decoding of fMRI activity patterns.

Okito Yamashita1, Masa-aki Sato, Taku Yoshioka

  • 1ATR Computational Neuroscience Laboratories, Japan. oyamashi@atr.jp

Neuroimage
|July 5, 2008
PubMed
Summary
This summary is machine-generated.

Sparse Logistic Regression (SLR) improves fMRI decoding by automatically selecting relevant voxels. This method enhances classification performance by handling irrelevant voxels and exploiting correlations for better pattern separation.

More Related Videos

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces
05:36

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces

Published on: March 10, 2026

Related Experiment Videos

Last Updated: Jul 3, 2026

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces
05:36

STFEEG-Tool: A Spatial-Temporal-Frequency EEG Analysis Tool for Motor Imagery Brain-Computer Interfaces

Published on: March 10, 2026

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Computational Neuroscience

Background:

  • Functional magnetic resonance imaging (fMRI) pattern classification decodes task parameters from brain activity.
  • Selecting optimal voxels (features) is crucial for fMRI decoding to prevent overfitting and improve generalization.
  • Univariate voxel selection may miss important information contained in voxel correlations.

Purpose of the Study:

  • To introduce a novel linear classification algorithm, Sparse Logistic Regression (SLR).
  • To enable automatic relevant voxel selection and parameter estimation for fMRI decoding.
  • To enhance classification performance in fMRI data analysis.

Main Methods:

  • Developed Sparse Logistic Regression (SLR), a linear classification algorithm.
  • Tested SLR using simulation data to evaluate its voxel selection and classification capabilities.
  • Applied SLR to real fMRI data from two visual experiments.

Main Results:

  • SLR effectively removed irrelevant voxels, achieving higher classification performance than other methods on simulation data.
  • SLR successfully identified relevant voxels in the visual cortex using real fMRI data.
  • SLR-selected voxels outperformed those chosen by univariate statistics, leveraging inter-voxel correlations.

Conclusions:

  • SLR offers a robust and automated method for voxel selection in fMRI decoding.
  • The algorithm effectively improves classification accuracy by optimizing feature input.
  • SLR can be utilized as a standalone tool for voxel selection in neuroimaging studies.