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

Comparison of neural signal sources for discriminating "crave" and "don't crave" task conditions: Implications for fMRI neurofeedback.

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

Social network analysis of tail-biting interactions among growing-finishing pigs with intact tails housed in two group sizes.

Journal of animal science·2026
Same author

Episodic Future Thinking as an Intervention for Alcohol Use Disorder: Effects on Delay Discounting and Real-World Alcohol Consumption.

Research square·2026
Same author

Generalized Energy Band Alignment Model for van der Waals Heterostructures with a Charge Spillage Dipole.

ACS nano·2025
Same author

Delineating the Effects of Alcohol Use on Cognition in Individuals With Neurocognitive Disorders.

The Journal of clinical psychiatry·2025
Same author

The Relationship between Age and Cognitive Subtypes of Alzheimer Syndrome and Related Dementias.

Dementia and geriatric cognitive disorders·2025

Related Experiment Video

Updated: Jun 12, 2026

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

Support vector machines for temporal classification of block design fMRI data.

Stephen LaConte1, Stephen Strother, Vladimir Cherkassky

  • 1Biomedical Engineering, Georgia Institute of Technology, Emory University, Atlanta, 30322, USA.

Neuroimage
|May 24, 2005
PubMed
Summary

This study compares Support Vector Machine (SVM) classification to Canonical Variates Analysis (CVA) for functional Magnetic Resonance Imaging (fMRI) data. SVM demonstrates robust classification performance and offers novel methods for interpreting neuroimaging results.

More Related Videos

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design
06:18

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design

Published on: December 3, 2020

Related Experiment Videos

Last Updated: Jun 12, 2026

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

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy
12:09

Network Analysis of the Default Mode Network Using Functional Connectivity MRI in Temporal Lobe Epilepsy

Published on: August 5, 2014

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design
06:18

Qualitative and Comparative Cortical Activity Data Analyses from a Functional Near-Infrared Spectroscopy Experiment Applying Block Design

Published on: December 3, 2020

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Biomedical Data Analysis

Background:

  • Functional Magnetic Resonance Imaging (fMRI) is a key tool in neuroscience.
  • Previous work utilized linear discriminant analysis for fMRI data.
  • Support Vector Machine (SVM) classification offers unique properties for data analysis.

Purpose of the Study:

  • To compare the classification performance of SVM against Canonical Variates Analysis (CVA) in block design fMRI.
  • To evaluate the sensitivity of SVM and CVA to various preprocessing choices.
  • To explore the interpretability of SVM models in neuroimaging and propose methods for extracting activation maps.

Main Methods:

  • Applied SVM classification to block design fMRI data, analyzing individual time samples without averaging or feature selection.
  • Compared SVM with CVA across ten combinations of preprocessing steps: spatial smoothing, temporal detrending, and motion correction.
  • Investigated four novel methods for interpreting SVM models and extracting activation maps from neuroimaging data.

Main Results:

  • SVM and CVA were applied to whole-brain fMRI data with approximately 30,000 voxels and a repetition time (TR) of 4 seconds.
  • The study examined the relative sensitivity of both methods to different preprocessing pipelines.
  • SVM demonstrated unique properties for model interpretation, with one activation map extraction method detailed.

Conclusions:

  • SVM classification is a viable and effective method for analyzing fMRI data.
  • SVM offers advantages in model interpretation compared to traditional methods like CVA.
  • The proposed methods for extracting activation maps from SVM models provide new tools for neuroimaging research.