Inter-region Synchronization Analysis Based on Heterogeneous Matrix Similarity Measurement

EEG synchronization is an essential tool to understand mechanisms of communication between brain regions. Despite numerous successes along this direction, grand challenges still remain: (1) to establish the relation between treatment outcome and the synchronization patterns amongst brain regions and (2) to correctly quantify the synchronization amongst brain regions with different electrode placement topologies. As for this problem, we propose an approach to inter-region synchronization analysis based on Heterogeneous Matrix Similarity Measurement to avoid information loss of the results on similarity. It is measured by deriving the bridge matrix that quantifies the distance from the source matrix to the target one both of arbitrary dimensions. The similarity measures are then used to examine the relation between brain region interactions (directional) and treatment outcome. Experiments have been performed on EEG collected from patients received anti-depression treatment with both non-effective and effective outcomes. Experimental results indicate that for the non-effective group, \(97\%\) (\(95\%\)) similarity values from right temporal to central (from left temporal to central) are greater than the average similarity value of all patients; The new correlation measures can quantify the directional synchronization between brain regions and form an indicator for anti-depression treatment outcome with a high-level confidence. The approach also holds potentials in sophisticated applications involving clustering and dimensionality reduction.

[1]  E. Kandel,et al.  Neuroscience thinks big (and collaboratively) , 2013, Nature Reviews Neuroscience.

[2]  P. Rapp,et al.  Time domain measures of inter-channel EEG correlations: a comparison of linear, nonparametric and nonlinear measures , 2013, Cognitive Neurodynamics.

[3]  Xiaoli Li,et al.  Estimating coupling direction between neuronal populations with permutation conditional mutual information , 2010, NeuroImage.

[4]  C. J. Stam,et al.  Functional connectivity patterns of human magnetoencephalographic recordings: a ‘small-world’ network? , 2004, Neuroscience Letters.

[5]  Andrew T. Drysdale,et al.  Resting-state connectivity biomarkers define neurophysiological subtypes of depression , 2016, Nature Medicine.

[6]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Michael Mitzenmacher,et al.  Detecting Novel Associations in Large Data Sets , 2011, Science.

[9]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[10]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[11]  Alex Martin,et al.  A wavelet-based method for measuring the oscillatory dynamics of resting-state functional connectivity in MEG , 2011, NeuroImage.

[12]  Olaf Sporns,et al.  Disturbed resting state EEG synchronization in bipolar disorder: A graph-theoretic analysis☆ , 2013, NeuroImage: Clinical.

[13]  Aamir Saeed Malik,et al.  A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD) , 2018, Medical & Biological Engineering & Computing.

[14]  Cheuk Y. Tang,et al.  Ketamine Treatment and Global Brain Connectivity in Major Depression , 2017, Neuropsychopharmacology.

[15]  Olaf Sporns,et al.  Complex network measures of brain connectivity: Uses and interpretations , 2010, NeuroImage.

[16]  Andrew W. Moore,et al.  Gradient Descent for General Reinforcement Learning , 1998, NIPS.

[17]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[18]  Thomas Brox,et al.  Generating Images with Perceptual Similarity Metrics based on Deep Networks , 2016, NIPS.

[19]  Rajiv Ranjan,et al.  Towards Brain Big Data Classification: Epileptic EEG Identification With a Lightweight VGGNet on Global MIC , 2018, IEEE Access.

[20]  S. Knuutila,et al.  True 3q Chromosomal Amplification in Squamous Cell Lung Carcinoma by FISH and aCGH Molecular Analysis: Impact on Targeted Drugs , 2012, PloS one.

[21]  Dirk Westhoff,et al.  A ROM-friendly secure code update mechanism for WSNs using a stateful-verifier τ-time signature scheme , 2009, WiSec '09.

[22]  Steve Horvath,et al.  Resting-State Quantitative Electroencephalography Reveals Increased Neurophysiologic Connectivity in Depression , 2012, PloS one.

[23]  Lizhe Wang,et al.  Global Synchronization Measurement of Multivariate Neural Signals with Massively Parallel Nonlinear Interdependence Analysis , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.