Incorporating structured assumptions with probabilistic graphical models in fMRI data analysis

@article{Cai2020IncorporatingSA,
  title={Incorporating structured assumptions with probabilistic graphical models in fMRI data analysis},
  author={M. Cai and Michael Shvartsman and Anqi Wu and Hejia Zhang and Xia Zhu},
  journal={Neuropsychologia},
  year={2020},
  volume={144}
}

Figures from this paper

Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimaging
TLDR
A novel flexible hierarchical Bayesian framework within which the spatio-temporal dynamics of model parameters and noise are modeled to have Kronecker product covariance structure and its highly efficient algorithms exploit the intrinsic Riemannian geometry of temporal autocovariance matrices.
Neural Topographic Factor Analysis for fMRI Data
TLDR
This work proposes Neural Topographic Factor Analysis (NTFA), a probabilistic factor analysis model that infers embeddings for participants and stimuli that improves predictive generalization to unseen data when compared to previous topographic methods.
BrainIAK: The Brain Imaging Analysis Kit
TLDR
The Brain Imaging Analysis Kit (BrainIAK), an open-source, free Python package that provides computationally optimized solutions to key problems in advanced fMRI analysis, is described, to understand how BrainIAK might be useful in their research.
Neural Latents Benchmark '21: Evaluating latent variable models of neural population activity
TLDR
This work introduces a benchmark suite for latent variable modeling of neural population activity, and identifies unsupervised evaluation as a common framework for evaluating models across datasets, and applies several baselines that demonstrate benchmark diversity.
Joint Learning of Full-structure Noise in Hierarchical Bayesian Regression Models
TLDR
H hierarchical Bayesian (type-II maximum likelihood) models for observations with latent variables for source and noise, which are estimated jointly from data are developed and validated in simulations and with real MEG data.
Joint Hierarchical Bayesian Learning of Full-structure Noise for Brain Source Imaging
TLDR
The results demonstrate that the novel framework significantly improves upon state-of-the-art techniques in the real-world scenario with fully-structured noise covariance.

References

SHOWING 1-10 OF 197 REFERENCES
Matrix-normal models for fMRI analysis
TLDR
This work empirically demonstrate advantages of two new methods derived in the matrix-variate normal (MN) formalism, and provides a software prototyping tool for MN models that can flexibly reuse noise covariance assumptions and algorithms across models.
Total Variation Regularization for fMRI-Based Prediction of Behavior
TLDR
This article applies for the first time this method to fMRI data, and shows that TV regularization is well suited to the purpose of brain mapping while being a powerful tool for brain decoding.
Topographic Factor Analysis: A Bayesian Model for Inferring Brain Networks from Neural Data
TLDR
Topographic factor analysis (TFA) is developed, a technique that exploits spatial correlations in fMRI data to recover the underlying structure that the images reflect, and casts each brain image as a weighted sum of spatial functions.
Computational approaches to fMRI analysis
TLDR
These methods highlight the importance of computational techniques in fMRI analysis, especially machine learning, algorithmic optimization and parallel computing, and adoption of these techniques is enabling a new generation of experiments and analyses that could transform the understanding of some of the most complex—and distinctly human—signals in the brain.
Bayesian analysis of neuroimaging data in FSL
Facilitating open-science with realistic fMRI simulation: validation and application
Background With advances in methods for collecting and analyzing fMRI data, there is a concurrent need to understand how to reliably evaluate and optimally use these methods. Simulations of fMRI data
Facilitating open-science with realistic fMRI simulation: validation and application.
TLDR
This work describes how to use fmrisim to extract noise properties from real fMRI data and then create a synthetic dataset with matched noise properties and a user-specified signal, and validate the noise generated by fm Crisim to show that it can approximate the noise properties of real data.
Fully Bayesian spatio-temporal modeling of FMRI data
TLDR
A fully Bayesian approach to modeling in functional magnetic resonance imaging (FMRI), incorporating spatio-temporal noise modeling and haemodynamic response function (HRF) modeling is presented, and a novel HRF model made up of half-cosines is proposed, which allows distinct combinations of parameters to represent characteristics of interest.
...
...