nCREANN: Nonlinear Causal Relationship Estimation by Artificial Neural Network; Applied for Autism Connectivity Study

Quantifying causal (effective) interactions between different brain regions are very important in neuroscience research. Many conventional methods estimate effective connectivity based on linear models. However, using linear connectivity models may oversimplify the functions and dynamics of the brain. In this paper, we propose a causal relationship estimator called nonlinear Causal Relationship Estimation by Artificial Neural Network (nCREANN) that identifies both linear and nonlinear components of effective connectivity in the brain. Furthermore, it can distinguish between these two types of connectivity components by calculating the linear and nonlinear parts of the network input-output mapping. The nCREANN performance has been verified using synthesized data and then it has been applied on EEG data collected during rest in children with autism spectrum disorder (ASD) and typically developing (TD) children. The results show that overall linear connectivity in TD subjects is higher, while the nonlinear connectivity component is more dominant in ASDs. We suggest that our findings may represent different underlying neural activation dynamics in ASD and TD subjects. The results of nCREANN may provide new insight into the connectivity between the interactive brain regions.

[1]  Chris McNorgan,et al.  A Connectionist Approach to Mapping the Human Connectome Permits Simulations of Neural Activity Within an Artificial Brain , 2013, Brain Connect..

[2]  Mark W. Woolrich,et al.  A symmetric multivariate leakage correction for MEG connectomes , 2015, NeuroImage.

[3]  J. Fermaglich.  Electric Fields of the Brain: The Neurophysics of EEG , 1982 .

[4]  Kazuyuki Aihara,et al.  Detecting Causality from Nonlinear Dynamics with Short-term Time Series , 2014, Scientific Reports.

[5]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[6]  Daniele Marinazzo,et al.  Kernel method for nonlinear granger causality. , 2007, Physical review letters.

[7]  C. Stam,et al.  Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field , 2005, Clinical Neurophysiology.

[8]  L. Faes,et al.  Information-based detection of nonlinear Granger causality in multivariate processes via a nonuniform embedding technique. , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Gordon Pipa,et al.  Transfer entropy—a model-free measure of effective connectivity for the neurosciences , 2010, Journal of Computational Neuroscience.

[10]  M. Hallett,et al.  Linear and nonlinear information flow based on time-delayed mutual information method and its application to corticomuscular interaction , 2010, Clinical Neurophysiology.

[11]  Karl J. Friston,et al.  Multiple sparse priors for the M/EEG inverse problem , 2008, NeuroImage.

[12]  Ali Cheknane,et al.  Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models , 2013 .

[13]  Daniele Marinazzo,et al.  Kernel-Granger causality and the analysis of dynamical networks. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  J. F. Alonso,et al.  Stress assessment based on EEG univariate features and functional connectivity measures , 2015, Physiological measurement.

[15]  Iman Mohammad-Rezazadeh,et al.  Estimation of effective connectivity using multi-layer perceptron artificial neural network , 2017, Cognitive Neurodynamics.

[16]  S Makeig,et al.  Event-related brain response abnormalities in autism: evidence for impaired cerebello-frontal spatial attention networks. , 2001, Brain research. Cognitive brain research.

[17]  M Palus,et al.  Synchronization as adjustment of information rates: detection from bivariate time series. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[18]  A. Lindell,et al.  Atypicalities in Cortical Structure, Handedness, and Functional Lateralization for Language in Autism Spectrum Disorders , 2013, Neuropsychology Review.

[19]  Gholam-Ali Hossein-Zadeh,et al.  Nonlinear effective connectivity measure based on adaptive Neuro Fuzzy Inference System and Granger Causality , 2018, NeuroImage.

[20]  G. Dawson,et al.  Resting State Cortical Connectivity Reflected in EEG Coherence in Individuals With Autism , 2007, Biological Psychiatry.

[21]  Luiz A. Baccalá,et al.  Partial directed coherence: a new concept in neural structure determination , 2001, Biological Cybernetics.

[22]  Qionghai Dai,et al.  Causality Analysis of Neural Connectivity: Critical Examination of Existing Methods and Advances of New Methods , 2011, IEEE Transactions on Neural Networks.

[23]  Gang Pan,et al.  Estimating Brain Connectivity With Varying-Length Time Lags Using a Recurrent Neural Network , 2018, IEEE Transactions on Biomedical Engineering.

[24]  Nicole M. G. Salowitz,et al.  Electroencephalogram Coherence in Children With and Without Autism Spectrum Disorders: Decreased Interhemispheric Connectivity in Autism , 2014, Autism research : official journal of the International Society for Autism Research.

[25]  F. Babiloni,et al.  Estimation of the cortical functional connectivity with the multimodal integration of high-resolution EEG and fMRI data by directed transfer function , 2005, NeuroImage.

[26]  Fei He,et al.  A new NARX-based Granger linear and nonlinear casual influence detection method with applications to EEG data , 2013, Journal of Neuroscience Methods.

[27]  F. H. Lopes da Silva,et al.  Interdependence of EEG signals: Linear vs. nonlinear Associations and the significance of time delays and phase shifts , 2005, Brain Topography.

[28]  Gholam-Ali Hossein-Zadeh,et al.  Estimation of direct nonlinear effective connectivity using information theory and multilayer perceptron , 2014, Journal of Neuroscience Methods.

[29]  Christian O'Reilly,et al.  Is functional brain connectivity atypical in autism? A systematic review of EEG and MEG studies , 2017, PloS one.

[30]  Arnold Neumaier,et al.  Algorithm 808: ARfit—a matlab package for the estimation of parameters and eigenmodes of multivariate autoregressive models , 2001, TOMS.

[31]  Dirk Hoyer,et al.  Drug effect on EEG connectivity assessed by linear and nonlinear couplings , 2010, Human brain mapping.