Multivariate Model Specification for fMRI Data

doi:10.1006/nimg.2002.1094

NeuroImage

Volume 16, Issue 4, August 2002, Pages 1068-1083

https://doi.org/10.1006/nimg.2002.1094 Get rights and content

Abstract

We present a general method—denoted MoDef—to help specify (or define) the model used to analyze brain imaging data. This method is based on the use of the multivariate linear model on a training data set. We show that when the a priori knowledge about the expected brain response is not too precise, the method allows for the specification of a model that yields a better sensitivity in the statistical results. This obviously relies on the validity of the a priori information, in our case the representativity of the training set, an issue addressed using a cross-validation technique. We propose a fast implementation that allows the use of the method on large data sets as found with functional Magnetic Resonance Images. An example of application is given on an experimental fMRI data set that includes nine subjects who performed a mental computation task. Results show that the method increases the statistical sensitivity of fMRI analyses.

References (37)

A.H. Andersen et al.
Principal component analysis of the dynamic response measured by fmri: A generalized linear systems framework
Magn. Reson. Imag.
(1999)
A. Andrade et al.
Ambiguous results in functional neuroimaging data analysis due to covariate correlation
Neuroimage
(1999)
R. Baumgartner et al.
Comparison of two exploratory data analysis methods for fmri: Fuzzy clustering vs principal component analysis
Magn. Reson. Imag.
(2000)
E.T. Bullmore et al.
Functional magnetic resonance image analysis of a large-scale neurocognitive network
Neuroimage
(1996)
K.J. Friston et al.
To smooth or not to smooth? Bias and efficiency in fmri time-series analysis
Neuroimage
(2000)
L.K. Hansen et al.
Generalizable patterns in neuroimaging: How many principal components?
Neuroimage
(1999)
A.R. McIntosh et al.
Spatial pattern analysis of functional brain images using partial least squares
Neuroimage
(1996)
M.J. McKeown
Detection of consistently task-related activations in fmri data with hybrid independent component analysis
Neuroimage
(2000)
O. Simon et al.
Topographical layout of hand, eye, calculation, and language-related areas in the human parietal lobe
Neuron
(2002)
K.J. Worsley et al.
Analysis of fmri time-series revisited-again
Neuroimage
(1995)

K.J. Worsley et al.

Characterizing the response of pet and fmri data using multivariate linear models

Neuroimage

(1997)

K.J. Worsley et al.

Tests for distributed, nonfocal brain activations

Neuroimage

(1995)

H. Akaike

A new look at the statistical model identification

IEEE Trans. Auto. Control

(1974)

E. Bullmore et al.

Statistical methods of estimation and inference for functional mr image analysis

Magn. Reson. Med.

(1996)

E. Bullmore et al.

Colored noise and computational inference in neurophysiological (fmri) time series analysis: Resampling methods in time and wavelet domains

Hum. Brain Mapp.

(2001)

M.A. Burock et al.

Estimation and detection of event-related fMRI signals with temporally correlated noise: A statistically efficient and unbiased approach

Hum. Brain Mapp.

(2000)

Caussinus

Models and Uses of Principal Components Analysis

(1985)

F. Chochon et al.

Differential contributions of the left and right inferior parietal lobules to number processing

J. Cogn. Neurosci.

(1999)

Cited by (59)

Temporal trajectory of brain tissue property changes induced by electroconvulsive therapy
2021, NeuroImage
Citation Excerpt :
This strategy is known to inflate the type I error rate and does not model the relationship between dependent variables Fox (2015). The use of multivariate statistics allows for assessing how a combination of dependent variables reflects an effect of interest, and thus provides more information than the univariate GLM approach (McFarquhar et al., 2016, Stoyanov et al., 2019, Zufferey et al., 2017, Kherif et al., 2002 Aug 1). The recently proposed implementation of multivariate GLM for neuroimaging data (McFarquhar et al., 2016), facilitates the modelling of either multi-contrast datasets or repeated measures datasets, but do not handle the case of datasets that have both characteristics.
After more than eight decades of electroconvulsive therapy (ECT) for pharmaco-resistant depression, the mechanisms governing its anti-depressant effects remain poorly understood. Computational anatomy studies using longitudinal T1-weighted magnetic resonance imaging (MRI) data have demonstrated ECT effects on hippocampus volume and cortical thickness, but they lack the interpretational specificity about underlying neurobiological processes.
We sought to fill in the gap of knowledge by acquiring quantitative MRI indicative for brain's myelin, iron and tissue water content at multiple time-points before, during and after ECT treatment. We adapted established tools for longitudinal spatial registration of MRI data to the relaxometry-based multi-parameter maps aiming to preserve the initial total signal amount and introduced a dedicated multivariate analytical framework.
The whole-brain voxel-based analysis based on a multivariate general linear model showed that there is no brain tissue oedema contributing to the predicted ECT-induced hippocampus volume increase neither in the short, nor in the long-term observations. Improvements in depression symptom severity over time were associated with changes in both volume estimates and brain tissue properties expanding beyond mesial temporal lobe structures to anterior cingulate cortex, precuneus and striatum.
The obtained results stemming from multi-contrast MRI quantitative data provided a fingerprint of ECT-induced brain tissue changes over time that are contrasted against the background of established morphometry findings. The introduced data processing and statistical testing algorithms provided a reliable analytical framework for longitudinal multi-parameter brain maps. The results, particularly the evidence of lack of ECT impact on brain tissue water, should be considered preliminary considering the small sample size of the study.
Multi-dimensional connectivity: a conceptual and mathematical review
2020, NeuroImage
The estimation of functional connectivity between regions of the brain, for example based on statistical dependencies between the time series of activity in each region, has become increasingly important in neuroimaging. Typically, multiple time series (e.g. from each voxel in fMRI data) are first reduced to a single time series that summarises the activity in a region of interest, e.g. by averaging across voxels or by taking the first principal component; an approach we call one-dimensional connectivity. However, this summary approach ignores potential multi-dimensional connectivity between two regions, and a number of recent methods have been proposed to capture such complex dependencies. Here we review the most common multi-dimensional connectivity methods, from an intuitive perspective, from a formal (mathematical) point of view, and through a number of simulated and real (fMRI and MEG) data examples that illustrate the strengths and weaknesses of each method. The paper is accompanied with both functions and scripts, which implement each method and reproduce all the examples.
Principal component analysis
2019, Machine Learning: Methods and Applications to Brain Disorders
This chapter discusses the use of principal component analysis (PCA) for analyzing high-dimensional data in the context of brain disorders. PCA belongs to the family of dimension reduction methods and is particularly useful when the data are large (i.e., multiple variables), big (i.e., multiple observations per variable), and highly correlated. The goal is to identify a reduced set of features that represent the original data in a lower-dimensional subspace with minimal loss of information. PCA and related methods provide means to summarize the data and extract information about individual differences. This makes these methods particularly useful in the era of Big Data and personalized medicine. In the first section, we explain the mathematical formula behind PCA. In the second section, we show how to implement the method using a toy example. Finally, in the last section, we discuss some exemplar applications of PCA from the existing literature.
Neuroticism, depression, and anxiety traits exacerbate the state of cognitive impairment and hippocampal vulnerability to Alzheimer's disease
2017, Alzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring
Certain personality traits are associated with higher risk of Alzheimer's disease, similar to cognitive impairment. The identification of biological markers associated with personality in mild cognitive impairment could advance the early detection of Alzheimer's disease.
We used hierarchical multivariate linear models to quantify the interaction between personality traits, state of cognitive impairment, and MRI biomarkers (gray matter brain volume, gray matter mean water diffusion) in the medial temporal lobe (MTL).
Over and above a main effect of cognitive state, the multivariate linear model showed significant interaction between cognitive state and personality traits predicting MTL abnormality. The interaction effect was mainly driven by neuroticism and its facets (anxiety, depression, and stress) and was associated with right-left asymmetry and an anterior to posterior gradient in the MTL.
Our results support the hypothesis that personality traits can alter the vulnerability and pathoplasticity of disease and therefore modulate related biomarker expression.
How to avoid mismodelling in GLM-based fMRI data analysis: cross-validated Bayesian model selection
2016, NeuroImage
Citation Excerpt :
Beyond this naïve approach, the problem of model misspecification in fMRI analysis has been recognized by researchers and a number of strategies have been developed to deal with potential mismodelling. Kherif and Loh have proposed algorithms for model optimization, but they only allow inference pertaining to nested model comparisons (Kherif et al., 2002) and condition regressor timing (Loh et al., 2008). Razavi et al. (2003) investigated model accuracy based on the goodness of fit, but do not consider model complexity.
Voxel-wise general linear models (GLMs) are a standard approach for analyzing functional magnetic resonance imaging (fMRI) data. An advantage of GLMs is that they are flexible and can be adapted to the requirements of many different data sets. However, the specification of first-level GLMs leaves the researcher with many degrees of freedom which is problematic given recent efforts to ensure robust and reproducible fMRI data analysis. Formal model comparisons that allow a systematic assessment of GLMs are only rarely performed. On the one hand, too simple models may underfit data and leave real effects undiscovered. On the other hand, too complex models might overfit data and also reduce statistical power. Here we present a systematic approach termed cross-validated Bayesian model selection (cvBMS) that allows to decide which GLM best describes a given fMRI data set. Importantly, our approach allows for non-nested model comparison, i.e. comparing more than two models that do not just differ by adding one or more regressors. It also allows for spatially heterogeneous modelling, i.e. using different models for different parts of the brain. We validate our method using simulated data and demonstrate potential applications to empirical data. The increased use of model comparison and model selection should increase the reliability of GLM results and reproducibility of fMRI studies.
Integrative Bayesian analysis of neuroimaging-genetic data with application to cocaine dependence
2016, NeuroImage
Neuroimaging and genetic studies provide distinct and complementary information about the structural and biological aspects of a disease. Integrating the two sources of data facilitates the investigation of the links between genetic variability and brain mechanisms among different individuals for various medical disorders. This article presents a general statistical framework for integrative Bayesian analysis of neuroimaging-genetic (iBANG) data, which is motivated by a neuroimaging-genetic study in cocaine dependence. Statistical inference necessitated the integration of spatially dependent voxel-level measurements with various patient-level genetic and demographic characteristics under an appropriate probability model to account for the multiple inherent sources of variation. Our framework uses Bayesian model averaging to integrate genetic information into the analysis of voxel-wise neuroimaging data, accounting for spatial correlations in the voxels. Using multiplicity controls based on the false discovery rate, we delineate voxels associated with genetic and demographic features that may impact diffusion as measured by fractional anisotropy (FA) obtained from DTI images. We demonstrate the benefits of accounting for model uncertainties in both model fit and prediction. Our results suggest that cocaine consumption is associated with FA reduction in most white matter regions of interest in the brain. Additionally, gene polymorphisms associated with GABAergic, serotonergic and dopaminergic neurotransmitters and receptors were associated with FA.

View all citing articles on Scopus

View full text

Regular ArticleMultivariate Model Specification for fMRI Data

Abstract

Magn. Reson. Imag.

Neuroimage

Magn. Reson. Imag.

Neuroimage

Neuroimage

Neuroimage

Neuroimage

Neuroimage

Neuron

Neuroimage

Neuroimage

Neuroimage

A new look at the statistical model identification

IEEE Trans. Auto. Control

Statistical methods of estimation and inference for functional mr image analysis

Magn. Reson. Med.

Colored noise and computational inference in neurophysiological (fmri) time series analysis: Resampling methods in time and wavelet domains

Hum. Brain Mapp.

Estimation and detection of event-related fMRI signals with temporally correlated noise: A statistically efficient and unbiased approach

Hum. Brain Mapp.

Models and Uses of Principal Components Analysis

Differential contributions of the left and right inferior parietal lobules to number processing

J. Cogn. Neurosci.

Regular Article
Multivariate Model Specification for fMRI Data