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

High-resolution whole-brain magnetic resonance spectroscopic imaging in youth at risk for psychosis.

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

The microstructure-weighted human connectome: network properties and structure-function correlations across spatial scales.

bioRxiv : the preprint server for biology·2026
Same author

Myo-inositol concentration in the medial prefrontal cortex is associated with changes in brain white matter microstructure in early psychosis.

Translational psychiatry·2026
Same author

Altered structural connectivity in epilepsy with myoclonic atonic seizures.

Epilepsy research·2026
Same author

Blood lactate kinetics as biomarkers of MRI brain injury in neonatal encephalopathy.

Pediatric research·2026
Same author

Spatiotemporal brain dynamics in 8-to-9-year-old children: A comparative study between preterm and term schoolchildren.

NeuroImage. Clinical·2026

Related Experiment Video

Updated: Sep 12, 2025

fMRI Validation of fNIRS Measurements During a Naturalistic Task
10:36

fMRI Validation of fNIRS Measurements During a Naturalistic Task

Published on: June 15, 2015

21.0K

Comparing and Scaling fMRI Features for Brain-Behavior Prediction.

Mikkel Schöttner Sieler1, Thomas A W Bolton1, Jagruti Patel1

  • 1Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland.

Arxiv
|August 6, 2025
PubMed
Summary

Functional connectivity (FC) excels at predicting cognition, age, and sex from resting-state fMRI data. Graph signal processing and variability-based features also show promise for neuroimaging biomarker development.

Keywords:
Behavior PredictionFunctional ConnectivityGraph Signal ProcessingMachine LearningMagnetic Resonance ImagingNeuroimaging Biomarkers

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

12.4K
Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions
10:45

Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions

Published on: July 6, 2011

11.7K

Related Experiment Videos

Last Updated: Sep 12, 2025

fMRI Validation of fNIRS Measurements During a Naturalistic Task
10:36

fMRI Validation of fNIRS Measurements During a Naturalistic Task

Published on: June 15, 2015

21.0K
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

12.4K
Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions
10:45

Brain Imaging Investigation of the Neural Correlates of Observing Virtual Social Interactions

Published on: July 6, 2011

11.7K

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Biostatistics

Background:

  • Predicting behavioral variables from neuroimaging, like magnetic resonance imaging (MRI), can yield biomarkers for neurological and mental health disorders.
  • Feature extraction from neuroimaging data is critical, with varying predictive power and scaling properties related to sample size and scan duration.

Purpose of the Study:

  • To compare nine feature subtypes from resting-state functional MRI for behavior prediction.
  • To evaluate how these features predict mental health, cognition, processing speed, substance use, age, and sex.
  • To investigate the scaling properties of prediction performance with varying sample sizes and scan times.

Main Methods:

  • Analysis of 979 subjects from the Human Connectome Project Young Adult dataset.
  • Extraction and comparison of nine feature subtypes: regional activity, functional connectivity (FC), and graph signal processing (GSP) metrics.
  • Prediction of behavioral variables including cognition, age, and sex.

Main Results:

  • Functional connectivity (FC) was the best predictor for cognition, age, and sex.
  • Graph power spectral density showed promise for predicting cognition and age.
  • Variability-based features were also notable for sex prediction, with graph-filtered FC slightly outperforming simple FC.

Conclusions:

  • FC remains a robust feature for behavior prediction, complemented by the potential of GSP and variability-based measures.
  • Results suggest performance reserves for top features and highlight the importance of balancing sample size and scan time.
  • Findings inform future neuroimaging prediction studies regarding data acquisition and sample composition strategies.