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 Videos

Support vector machine learning-based fMRI data group analysis.

Ze Wang1, Anna R Childress, Jiongjiong Wang

  • 1Center for Functional Neuroimaging, Department of Neurology, University of Pennsylvania, School of Medicine, Philadelphia, PA 19104, USA. zewang@mail.med.upenn.edu

Neuroimage
|May 26, 2007
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

Arterial spin labeling MRI denoising via locally adaptive regularization with structure-guided collaborative data selection.

NeuroImage·2026
Same author

Characterizing the MRI signature of hippocampal sclerosis of aging.

Alzheimer's research & therapy·2026
Same author

An open, fully-processed data resource for studying mood and sleep variability in the developing brain.

Aperture neuro·2026
Same author

Clinicoanatomic localization of iron-rich gliosis in aphasic presentations of globular glial tauopathy.

Brain communications·2026
Same author

Multiple-TE Based Blood-Brain-Barrier Water Exchange Time Measurement Using a TE-Resolved 3D TSE Stack-Of-Spirals Readout.

Magnetic resonance in medicine·2026
Same author

An imaging biomarker to detect non-glucogenic shift in brain energy metabolism in Alzheimer's disease.

Journal of translational medicine·2026
Same journal

Segmentation of the parasagittal dura mater on multi-center 3D-FLAIR MRI.

NeuroImage·2026
Same journal

Spatial frequency channels implement a mental ruler in spatial vision.

NeuroImage·2026
Same journal

Exploring the Link Between Intravoxel Incoherent Motion Measured Brain Diffusivity During Wakefulness and Sleep Macrostructure in the Elderly.

NeuroImage·2026
Same journal

Closed-loop adaptation of transcranial magnetic stimulation intensity with electroencephalography feedback.

NeuroImage·2026
Same journal

Volumetric postmortem MRI of the medial temporal lobe in Alzheimer's disease and related disorders: methodological advances and implications for in vivo biomarker development.

NeuroImage·2026
Same journal

Neural responses to equity and inequity when receiving vicarious rewards for self and charity during adolescence.

NeuroImage·2026
See all related articles

This study introduces novel multivariate methods integrating support vector machine (SVM) and random effect models for fMRI data analysis. These model-free approaches enhance brain response detection and reduce false positives compared to traditional methods.

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Statistical Analysis

Background:

  • Functional magnetic resonance imaging (fMRI) data presents complex multivariate patterns and inter-subject variability.
  • Existing methods often rely on predefined brain response models, limiting comprehensive analysis.

Purpose of the Study:

  • To develop and evaluate multivariate, model-free methods for fMRI data analysis.
  • To address inter-subject brain response discrepancies and improve detection sensitivity.

Main Methods:

  • Integration of Support Vector Machine (SVM) with random effect models for spatial discriminance map (SDM) extraction.
  • Application of random effect analysis (RFX) and permutation testing (PMU) for population inference on SDMs.
  • Comparison with univariate General Linear Model (GLM) approaches.

Related Experiment Videos

Main Results:

  • SDM RFX demonstrated lower false-positive rates and higher sensitivity for synthetic activations compared to GLM RFX.
  • SDM methods yielded comparable activation patterns to GLM but with higher statistical values in a sensory-motor fMRI study.
  • Permutation testing (PMU) incorporated into individual-level analyses provided voxel-wise activation probability inferences.

Conclusions:

  • The proposed multivariate, model-free SVM and random effect methods offer a robust alternative for fMRI analysis.
  • These methods improve sensitivity and reduce false positives, particularly beneficial for arterial spin labeling (ASL) fMRI.
  • Individual-level PMU-based group analysis provides a valuable tool for thresholding fMRI results.