Estimating Brain Effective Connectivity in fMRI data by Non-stationary Dynamic Bayesian Networks

Estimating brain effective connectivity (EC) from neuroimaging data has recently received wide interest and become a new topic in the neuroinformatics field. Currently, dynamic Bayesian networks (DBN) have been successfully applied to estimating EC from functional magnetic resonance imaging (fMRI) time-series data as they can capture the temporal characteristics of connectivity among brain regions. However, DBN methods assume that activations of brain regions are stationary and follow a Markovian condition, which are strong assumptions that may not be valid in many cases. In this paper, we introduce a novel method to estimate brain effective connectivity networks from fMRI data using non-stationary dynamic Bayesian networks, named as EC-nsDBN. EC-nsDBN can not only capture the non-stationary temporal information from fMRI time-series data but also estimate how interactions among brain regions change dynamically over the fMRI experiments. Systematic experiments on simulated data show that EC-nsDBN has better direction identification ability compared with other state-of-the-art algorithms, and can accurately capture the temporal characteristics of connectivity. Experiments on real-world data sets are also provided to support our analysis.

[1]  Sheng Zhang,et al.  Bayesian network models in brain functional connectivity analysis , 2014, Int. J. Approx. Reason..

[2]  Dinggang Shen,et al.  Learning Discriminative Bayesian Networks from High-Dimensional Continuous Neuroimaging Data , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Vince D. Calhoun,et al.  SimTB, a simulation toolbox for fMRI data under a model of spatiotemporal separability , 2012, NeuroImage.

[4]  Mahdi Jalili,et al.  Directed Functional Networks in Alzheimer's Disease: Disruption of Global and Local Connectivity Measures , 2017, IEEE Journal of Biomedical and Health Informatics.

[5]  Alexander J. Hartemink,et al.  Learning Non-Stationary Dynamic Bayesian Networks , 2010, J. Mach. Learn. Res..

[6]  Christopher Meek,et al.  Causal inference and causal explanation with background knowledge , 1995, UAI.

[7]  Jing Li,et al.  A Sparse Structure Learning Algorithm for Gaussian Bayesian Network Identification from High-Dimensional Data , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Fabio Stella,et al.  Learning Continuous Time Bayesian Networks in Non-stationary Domains , 2016, J. Artif. Intell. Res..

[9]  K. M. Deneen,et al.  Altered effective connectivity patterns of the default mode network in Alzheimer's disease: An fMRI study , 2014, Neuroscience Letters.

[10]  Alexander J. Hartemink,et al.  Non-stationary dynamic Bayesian networks , 2008, NIPS.

[11]  Aapo Hyvärinen,et al.  A Linear Non-Gaussian Acyclic Model for Causal Discovery , 2006, J. Mach. Learn. Res..

[12]  Karl J. Friston.  Functional and effective connectivity in neuroimaging: A synthesis , 1994 .

[13]  Jiji Zhang,et al.  On the completeness of orientation rules for causal discovery in the presence of latent confounders and selection bias , 2008, Artif. Intell..

[14]  Juan Zhou,et al.  Learning effective brain connectivity with dynamic Bayesian networks , 2007, NeuroImage.

[15]  Marina Vannucci,et al.  A Bayesian Approach for Estimating Dynamic Functional Network Connectivity in fMRI Data , 2018, Journal of the American Statistical Association.

[16]  Russell A. Poldrack,et al.  Six problems for causal inference from fMRI , 2010, NeuroImage.

[17]  Aidong Zhang,et al.  Learning Effective Connectivity Network Structure from fMRI Data Based on Artificial Immune Algorithm , 2016, PloS one.

[18]  Martin J. McKeown,et al.  Dynamic Bayesian network modeling of fMRI: A comparison of group-analysis methods , 2008, NeuroImage.

[19]  Michael L. Lipton,et al.  Hippocampal volume and cingulum bundle fractional anisotropy are independently associated with verbal memory in older adults , 2015, Brain Imaging and Behavior.

[20]  Mark W. Woolrich,et al.  Network modelling methods for FMRI , 2011, NeuroImage.

[21]  Karl J. Friston,et al.  Granger causality revisited , 2014, NeuroImage.

[22]  J. Rauschecker,et al.  Effective connectivity in the default mode network is distinctively disrupted in Alzheimer's disease—A simultaneous resting‐state FDG‐PET/fMRI study , 2019, Human brain mapping.

[23]  Joseph Ramsey,et al.  Bayesian networks for fMRI: A primer , 2014, NeuroImage.

[24]  Juan Li,et al.  A new dynamic Bayesian network approach for determining effective connectivity from fMRI data , 2013, Neural Computing and Applications.

[25]  Gloria Menegaz,et al.  Exploring the Epileptic Brain Network Using Time-Variant Effective Connectivity and Graph Theory , 2017, IEEE Journal of Biomedical and Health Informatics.

[26]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[27]  Aidong Zhang,et al.  An ant colony optimization algorithm for learning brain effective connectivity network from fMRI data , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).