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

Bayesian decoding of brain images.

Karl Friston1, Carlton Chu, Janaina Mourão-Miranda

  • 1Wellcome Trust Centre for Neuroimaging, Institute of Neurology, UCL, 12 Queen Square, London WC1N 3BG, UK. k.friston@fil.ion.ucl.ac.uk

Neuroimage
|October 9, 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

Could agentic AI topple grant-funding systems?

Nature·2026
Same author

Distorting anatomy to test MEG models and metrics.

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

Cardiometabolic health and physical robustness map onto distinct patterns of brain structure and neurotransmitter systems.

PLoS biology·2025
Same author

Individualized prescriptive inference in ischaemic stroke.

Nature communications·2025
Same author

SPM-30 years and beyond.

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Performance of computed tomography and magnetic resonance morphometry in evaluating brain atrophy in Down syndrome.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
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
Same journal

Cognitive Strategy-based neuromodulation optimizes neural communication to improve working memory.

NeuroImage·2026
See all related articles

This study presents a multivariate Bayesian (MVB) scheme for decoding brain states from neuroimages. The MVB approach enables robust inference on brain structure-function mappings, outperforming standard pattern classification methods.

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Machine Learning

Background:

  • Decoding brain states from neuroimages presents an ill-posed many-to-one mapping challenge.
  • Existing pattern classification methods often focus on prediction rather than model inference.
  • Understanding structure-function mappings in the brain requires sophisticated analytical tools.

Purpose of the Study:

  • To introduce a multivariate Bayesian (MVB) scheme for decoding brain states from neuroimages.
  • To resolve the ill-posed mapping problem using hierarchical Bayesian models.
  • To enable inference and comparison of different models of brain structure-function relationships.

Main Methods:

  • Utilized a parametric empirical or hierarchical Bayesian model for mapping voxel values to target variables.

Related Experiment Videos

  • Employed standard variational techniques, specifically expectation-maximization, for model inversion.
  • Integrated a greedy search for sparse solutions, drawing parallels with Gaussian process modeling.

    • Main Results:

    • The MVB scheme provides model evidence and conditional density of parameters for hypothesis comparison.
    • Demonstrated superior performance compared to standard pattern classification approaches like support vector machines.
    • Successfully illustrated the MVB scheme using both simulated and real neuroimaging data.

    Conclusions:

    • The MVB scheme offers a powerful framework for inferring and comparing models of brain structure-function mappings.
    • This approach facilitates optimization of the model itself, leading to improved predictive accuracy.
    • MVB is particularly valuable for model comparison, allowing differentiation based on neuronal representations and regional involvement.