Brain covariance selection: better individual functional connectivity models using population prior

By Gaël Varoquaux, Alexandre Gramfort, Jean-Baptiste Poline, Bertrand Thirion. Neural Information Processing Systems, 2010

307 citations recorded by the source corpus.

Spontaneous brain activity, as observed in functional neuroimaging, has been shown to display reproducible structure that expresses brain architecture and carries markers of brain pathologies. An important view of modern neuroscience is that such large-scale structure of coherent activity reflects modularity properties of brain connectivity graphs. However, to date, there has been no demonstration that the limited and noisy data available in spontaneous activity observations could be used to learn full-brain probabilistic models that generalize to new data. Learning such models entails two main challenges: i) modeling full brain connectivity is a difficult estimation problem that faces the curse of dimensionality and ii) variability between subjects, coupled with the variability of functional signals between experimental runs, makes the use of multiple datasets challenging. We describe subject-level brain functional connectivity structure as a multivari-ate Gaussian process and introduce a new strategy to estimate it from group data, by imposing a common structure on the graphical model in the population. We show that individual models learned from functional Magnetic Resonance Imaging (fMRI) data using this population prior generalize better to unseen data than models based on alternative regularization schemes. To our knowledge, this is the first report of a cross-validated model of spontaneous brain activity. Finally, we use the estimated graphical model to explore the large-scale characteristics of functional architecture and show for the first time that known cognitive networks appear as the integrated communities of functional connectivity graph.

Subfields: Cognitive Neuroscience, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/4967cec6a71a9d3fce57c1c1e91f00db248ffec5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Clinical applications of the functional connectome (2013, unknown): “This can be addressed in part using regularization methods (Ryali et al., 2012; Smith et al., 2011; Varoquaux et al., 2010).”
Abnormal intrinsic brain functional network dynamics in Parkinson’s disease (2017, methodology): “Using the timeseries data of all possible 44 independent component pairs within each window, the resulting 44 44 pairwise covariance matrix was calculated using the regularized precision matrix (inverse covariance matrix) (Varoquaux et al., 2010).”
Tracking whole-brain connectivity dynamics in the resting state. (2014, unknown): “Because relatively short time segments may have insufficient information to characterize the full covariance matrix, we estimated covariance from the regularized precision matrix (inverse covariance matrix, ∑i−1(w)) (Varoquaux et al. 2010; Smith et al. 2011).”
Estimation of functional connectivity in fMRI data using stability selection-based sparse partial correlation with elastic net penalty (2011, unknown): “Only few studies to date have used regularization procedures for estimating functional networks in the context of brain imaging data (Huang et al., 2010; Lee et al., 2011; Smith et al., 2011; Varoquaux et al., 2010).”
Dynamic connectivity regression: Determining state-related changes in brain connectivity (2012, methodology): “Similar to Varoquaux et al. (2010) it is assumed that within each partition the graph structure is the same across subjects.”
The future of FMRI connectivity (2012, background): “For examples of nice initial work, see (Varoquaux et al., 2010; Ramsey et al., 2011).”
Benchmarking functional connectome‐based predictive models for resting‐state fMRI (2019, unknown): “…using Wards algorithm (Ward, 1963) with spatial connectivity constraints (Michel et al., 2012); and two linear decomposition methods: iii) Canonical Independent Component Analysis (GroupICA or CanICA) (Varoquaux et al., 2010c), iv) Dictionary Learning - ℓ 1 (DictLearn) (Mensch et al., 2016b).”
The structural-functional connectome and the default mode network of the human brain (2014, unknown): “Similar approaches have been used on fMRI-data (Huang et al., 2010; Ryali et al., 2010; Varoquaux and Craddock, 2013; Varoquaux et al., 2010; Wee et al., in press) and in other domains, e.g. to analyze genetic datasets (Stifanelli et al., 2011; Witten and Tibshirani, 2009).”
Dynamic functional connectivity analysis reveals transient states of dysconnectivity in schizophrenia (2014, methodology): “Subjects had their eyes closed during the resting state scan.”