DeepAI AI Chat
Log In Sign Up

A Hierarchical Graphical Model for Big Inverse Covariance Estimation with an Application to fMRI

by   Xi Luo, et al.

Brain networks has attracted the interests of many neuroscientists. From functional MRI (fMRI) data, statistical tools have been developed to recover brain networks. However, the dimensionality of whole-brain fMRI, usually in hundreds of thousands, challenges the applicability of these methods. We develop a hierarchical graphical model (HGM) to remediate this difficulty. This model introduces a hidden layer of networks based on sparse Gaussian graphical models, and the observed data are sampled from individual network nodes. In fMRI, the network layer models the underlying signals of different brain functional units, and how these units directly interact with each other. The introduction of this hierarchical structure not only provides a formal and interpretable approach, but also enables efficient computation for inferring big networks with hundreds of thousands of nodes. Based on the conditional convexity of our formulation, we develop an alternating update algorithm to compute the HGM model parameters simultaneously. The effectiveness of this approach is demonstrated on simulated data and a real dataset from a stop/go fMRI experiment.


page 10

page 12

page 14

page 15


Effective and Interpretable fMRI Analysis via Functional Brain Network Generation

Recent studies in neuroscience show great potential of functional brain ...

Incorporating structured assumptions with probabilistic graphical models in fMRI data analysis

With the wide adoption of functional magnetic resonance imaging (fMRI) b...

Fused graphical lasso for brain networks with symmetries

Neuroimaging is the growing area of neuroscience devoted to produce data...

Integrating Additional Knowledge Into Estimation of Graphical Models

In applications of graphical models, we typically have more information ...

Time-dependent spatially varying graphical models, with application to brain fMRI data analysis

In this work, we present an additive model for space-time data that spli...

Emotional Brain State Classification on fMRI Data Using Deep Residual and Convolutional Networks

The goal of emotional brain state classification on functional MRI (fMRI...

Communication-Avoiding Optimization Methods for Massive-Scale Graphical Model Structure Learning

Undirected graphical models compactly represent the structure of large, ...