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 Video

Updated: May 15, 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

Interpretable whole-brain prediction analysis with GraphNet.

Logan Grosenick1, Brad Klingenberg, Kiefer Katovich

  • 1Center for Mind, Brain, and Computation, Stanford University, Stanford, CA, USA. logang@gmail.com

Neuroimage
|January 10, 2013
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Objective quality assessment for precision functional MRI data.

Neuron·2026
Same author

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction.

Advances in neural information processing systems·2026
Same author

Contributions of the basolateral amygdala and nucleus accumbens to sustaining not just initiating cognitive effort.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Multimodal Representation Learning for Parsing Biological Heterogeneity in Psychiatric Neuroimaging.

Biological psychiatry·2026
Same author

Objective Quality Assessment for Precision Functional MRI Data.

bioRxiv : the preprint server for biology·2026
Same author

Brain activity reveals how wildlife imagery evokes engagement on social media.

PNAS nexus·2026
Same journal

Investigating the Neural Origins of Ear-EEG: A Correlation Study Using Scalp EEG Source Reconstruction.

NeuroImage·2026
Same journal

Hysteresis effects in visual and auditory perception and the comparison of underlying neural mechanisms - an EEG study.

NeuroImage·2026
Same journal

Short-term audio-tactile training affects cortical auditory speech-envelope tracking for incongruent but not congruent stimuli.

NeuroImage·2026
Same journal

Dissociable Neurocognitive Mechanisms of State and Trait Anxiety in Working Memory: Threat-Induced Alterations in Decision Dynamics and Attenuation of Large-Scale Network Reconfiguration.

NeuroImage·2026
Same journal

Neuro-Ocular Amyloid Characterization in Alzheimer's Disease via Cross-Site PET-MRI and Hierarchical Cross-Attention Driven Multimodal Representation Learning.

NeuroImage·2026
Same journal

Whole-brain network dynamics underlying intolerance of uncertainty.

NeuroImage·2026
See all related articles

New GraphNet methods enhance machine learning for neuroimaging, improving classification accuracy and interpretability in functional magnetic resonance imaging (fMRI) data analysis. These advanced techniques offer robust whole-brain analysis, outperforming traditional methods.

Area of Science:

  • Neuroscience
  • Machine Learning
  • Data Science

Background:

  • Multivariate machine learning methods are increasingly replacing traditional univariate techniques for neuroimaging data analysis.
  • Generic classification and regression methods applied to functional magnetic resonance imaging (fMRI) data can suffer from instability and interpretability issues due to data correlations.
  • Existing methods often require arbitrary thresholding for interpretation, and volume-of-interest (VOI) approaches can introduce bias.

Purpose of the Study:

  • To develop robust and interpretable multivariate machine learning methods for whole-brain fMRI data analysis.
  • To enhance classification and regression accuracy by addressing issues like coefficient instability and outlier sensitivity.
  • To provide a data-driven approach for selecting important brain regions that predict behavior.

Related Experiment Videos

Last Updated: May 15, 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

Main Methods:

  • Development of variants of the Graph-constrained Elastic-Net (GraphNet) for regression and classification.
  • Incorporation of robust loss functions for outlier insensitivity and adaptive penalties for guaranteed variable selection.
  • Introduction of a novel sparse structured Support Vector GraphNet classifier (SVGN).

Main Results:

  • GraphNet methods demonstrated improved classification accuracy compared to traditional VOI-based analyses on previously published fMRI data.
  • The methods identified task-related brain regions not detected by earlier VOI approaches.
  • GraphNet model estimates showed strong generalization to out-of-sample data collected years later.

Conclusions:

  • The developed GraphNet methods offer efficient, robust, and interpretable whole-brain analysis for fMRI data.
  • These techniques overcome limitations of mass univariate and VOI approaches, enabling accurate prediction of single-trial behavior.
  • The methods facilitate data-driven selection of predictive brain areas from large-scale neuroimaging datasets.