How to Build a Functional Connectomic Biomarker for Mild Cognitive Impairment From Source Reconstructed MEG Resting-State Activity: The Combination of ROI Representation and Connectivity Estimator Matters

Our work aimed to demonstrate the combination of machine learning and graph theory for the designing of a connectomic biomarker for mild cognitive impairment (MCI) subjects using eyes-closed neuromagnetic recordings. The whole analysis based on source-reconstructed neuromagnetic activity. As ROI representation, we employed the principal component analysis (PCA) and centroid approaches. As representative bi-variate connectivity estimators for the estimation of intra and cross-frequency interactions, we adopted the phase locking value (PLV), the imaginary part (iPLV) and the correlation of the envelope (CorrEnv). Both intra and cross-frequency interactions (CFC) have been estimated with the three connectivity estimators within the seven frequency bands (intra-frequency) and in pairs (CFC), correspondingly. We demonstrated how different versions of functional connectivity graphs single-layer (SL-FCG) and multi-layer (ML-FCG) can give us a different view of the functional interactions across the brain areas. Finally, we applied machine learning techniques with main scope to build a reliable connectomic biomarker by analyzing both SL-FCG and ML-FCG in two different options: as a whole unit using a tensorial extraction algorithm and as single pair-wise coupling estimations. We concluded that edge-weighed feature selection strategy outperformed the tensorial treatment of SL-FCG and ML-FCG. The highest classification performance was obtained with the centroid ROI representation and edge-weighted analysis of the SL-FCG reaching the 98% for the CorrEnv in α1:α2 and 94% for the iPLV in α2. Classification performance based on the multi-layer participation coefficient, a multiplexity index reached 52% for iPLV and 52% for CorrEnv. Selected functional connections that build the multivariate connectomic biomarker in the edge-weighted scenario are located in default-mode, fronto-parietal, and cingulo-opercular network. Our analysis supports the notion of analyzing FCG simultaneously in intra and cross-frequency whole brain interactions with various connectivity estimators in beamformed recordings.

[1]  F De Vico Fallani,et al.  Loss of brain inter-frequency hubs in Alzheimer's disease , 2016, Scientific Reports.

[2]  Fernando Maestú,et al.  Network Disruption and Cerebrospinal Fluid Amyloid-Beta and Phospho-Tau Levels in Mild Cognitive Impairment , 2015, Journal of Neuroscience.

[3]  Cornelis J. Stam,et al.  Selective impairment of hippocampus and posterior hub areas in Alzheimer’s disease: an MEG-based multiplex network study , 2017, Brain : a journal of neurology.

[4]  Umberto Castellani,et al.  Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[5]  P. Campo,et al.  Medial temporal lobe neuromagnetic hypoactivation and risk for developing cognitive decline in elderly population: A 2-year follow-up study , 2006, Neurobiology of Aging.

[6]  Karl J. Friston,et al.  Why Voxel-Based Morphometry Should Be Used , 2001, NeuroImage.

[7]  Michael Vourkas,et al.  Tracking brain dynamics via time-dependent network analysis , 2010, Journal of Neuroscience Methods.

[8]  George Zouridakis,et al.  Reconfiguration of dominant coupling modes in mild traumatic brain injury mediated by δ-band activity: A resting state MEG study , 2017, Neuroscience.

[9]  Yu Sun,et al.  A tensorial approach to access cognitive workload related to mental arithmetic from EEG functional connectivity estimates , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[10]  Thomas Arendt,et al.  Synaptic degeneration in Alzheimer’s disease , 2009, Acta Neuropathologica.

[11]  R. C. Oldfield.  The assessment and analysis of handedness: the Edinburgh inventory. , 1971, Neuropsychologia.

[12]  Vito Latora,et al.  Structural measures for multiplex networks. , 2013, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  R. Knight,et al.  The functional role of cross-frequency coupling , 2010, Trends in Cognitive Sciences.

[14]  George Zouridakis,et al.  Functional connectivity changes detected with magnetoencephalography after mild traumatic brain injury , 2015, NeuroImage: Clinical.

[15]  H. Braak,et al.  Neuropathological stageing of Alzheimer-related changes , 2004, Acta Neuropathologica.

[16]  Jaeseung Jeong.  EEG dynamics in patients with Alzheimer's disease , 2004, Clinical Neurophysiology.

[17]  Viktor K. Jirsa,et al.  Cross-frequency coupling in real and virtual brain networks , 2013, Front. Comput. Neurosci..

[18]  M. Wibral,et al.  Untangling cross-frequency coupling in neuroscience , 2014, Current Opinion in Neurobiology.

[19]  Jakob Heinzle,et al.  Multivariate information-theoretic measures reveal directed information structure and task relevant changes in fMRI connectivity , 2010, Journal of Computational Neuroscience.

[20]  Nitish V. Thakor,et al.  Causal Interactions between Frontalθ – Parieto-Occipitalα2 Predict Performance on a Mental Arithmetic Task , 2016, Front. Hum. Neurosci..

[21]  Edwin van Dellen,et al.  The minimum spanning tree: An unbiased method for brain network analysis , 2015, NeuroImage.

[22]  Paolo Maria Rossini,et al.  Cerebrovascular disease and hippocampal atrophy are differently linked to functional coupling of brain areas: an EEG coherence study in MCI subjects. , 2008, Journal of Alzheimer's disease : JAD.

[23]  Hans-Jochen Heinze,et al.  Phase-amplitude cross-frequency coupling in the human nucleus accumbens tracks action monitoring during cognitive control , 2013, Front. Hum. Neurosci..

[24]  K. Miller,et al.  Exaggerated phase–amplitude coupling in the primary motor cortex in Parkinson disease , 2013, Proceedings of the National Academy of Sciences.

[25]  Nick C Fox,et al.  The Diagnosis of Mild Cognitive Impairment due to Alzheimer’s Disease: Recommendations from the National Institute on Aging-Alzheimer’s Association Workgroups on Diagnostic Guidelines for Alzheimer’s Disease , 2011 .

[26]  A. Barabash,et al.  Searching for Primary Predictors of Conversion from Mild Cognitive Impairment to Alzheimer's Disease: A Multivariate Follow-Up Study. , 2016, Journal of Alzheimer's disease : JAD.

[27]  S. Fields,et al.  Urinary incontinence. A primary care guide to managing acute and chronic symptoms in older adults. , 2000, Geriatrics.

[28]  Ricardo Bruña,et al.  Phase locking value revisited: teaching new tricks to an old dog , 2017, Journal of neural engineering.

[29]  Darren Price,et al.  Investigating the electrophysiological basis of resting state networks using magnetoencephalography , 2011, Proceedings of the National Academy of Sciences.

[30]  Bharat B. Biswal,et al.  Competition between functional brain networks mediates behavioral variability , 2008, NeuroImage.

[31]  Xenophon Papademetris,et al.  Graph-theory based parcellation of functional subunits in the brain from resting-state fMRI data , 2010, NeuroImage.

[32]  Angus W. MacDonald,et al.  Fronto-parietal and cingulo-opercular network integrity and cognition in health and schizophrenia , 2015, Neuropsychologia.

[33]  George Zouridakis,et al.  Functional connectivity networks in the autistic and healthy brain assessed using Granger causality , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[34]  Sonja Grün,et al.  Cross-frequency interaction of the eye-movement related LFP signals in V1 of freely viewing monkeys , 2012, Front. Syst. Neurosci..

[35]  Michael X. Cohen,et al.  Oscillatory Activity and Phase–Amplitude Coupling in the Human Medial Frontal Cortex during Decision Making , 2009, Journal of Cognitive Neuroscience.

[36]  Ricardo Bruña,et al.  Alpha-Band Hypersynchronization in Progressive Mild Cognitive Impairment: A Magnetoencephalography Study , 2014, The Journal of Neuroscience.

[37]  George Zouridakis,et al.  Altered Rich-Club and Frequency-Dependent Subnetwork Organization in Mild Traumatic Brain Injury: A MEG Resting-State Study , 2017, Front. Hum. Neurosci..

[38]  Fernando Maestú,et al.  The Default Mode Network is functionally and structurally disrupted in amnestic mild cognitive impairment — A bimodal MEG–DTI study , 2014, NeuroImage: Clinical.

[39]  Stavros I. Dimitriadis.  Over a unified connectivity estimator for intra and inter-frequency couplings through symbolic transfer entropy: A MEG resting-state analysis , 2016 .

[40]  Ioannis Tarnanas,et al.  Topological Filtering of Dynamic Functional Brain Networks Unfolds Informative Chronnectomics: A Novel Data-Driven Thresholding Scheme Based on Orthogonal Minimal Spanning Trees (OMSTs) , 2017, Front. Neuroinform..

[41]  W. Niessen,et al.  The effect of hippocampal function, volume and connectivity on posterior cingulate cortex functioning during episodic memory fMRI in mild cognitive impairment , 2017, European Radiology.

[42]  Matthew J. Brookes,et al.  Alzheimer's disease disrupts alpha and beta-band resting-state oscillatory network connectivity , 2017, Clinical Neurophysiology.

[43]  S. Lawrie,et al.  Medial temporal lobe function during emotional memory in early Alzheimer’s disease, mild cognitive impairment and healthy ageing: an fMRI study , 2013, BMC Psychiatry.

[44]  Cornelis J. Stam,et al.  Magnetoencephalographic evaluation of resting-state functional connectivity in Alzheimer's disease , 2006, NeuroImage.

[45]  Nitish Thakor,et al.  Revealing Cross-Frequency Causal Interactions During a Mental Arithmetic Task Through Symbolic Transfer Entropy: A Novel Vector-Quantization Approach , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[46]  Ioannis Tarnanas,et al.  A novel biomarker of amnestic MCI based on dynamic cross-frequency coupling patterns during cognitive brain responses , 2015, Front. Neurosci..

[47]  C. Stam,et al.  Synchronization likelihood: an unbiased measure of generalized synchronization in multivariate data sets , 2002 .

[48]  Mark P. Richardson,et al.  Cross-frequency coupling within and between the human thalamus and neocortex , 2013, Front. Hum. Neurosci..

[49]  Elgar Fleisch,et al.  Mnemonic strategy training of the elderly at risk for dementia enhances integration of information processing via cross-frequency coupling , 2016, Alzheimer's & dementia.

[50]  J. A. Almendral,et al.  Reorganization of Functional Networks in Mild Cognitive Impairment , 2011, PloS one.

[51]  Esther Florin,et al.  The brain's resting-state activity is shaped by synchronized cross-frequency coupling of neural oscillations , 2015, NeuroImage.

[52]  James T. Becker,et al.  White Matter Damage Disorganizes Brain Functional Networks in Amnestic Mild Cognitive Impairment , 2014 .

[53]  Amir Shmuel,et al.  Laminar Distribution of Phase-Amplitude Coupling of Spontaneous Current Sources and Sinks , 2015, Front. Neurosci..

[54]  Matthew J. Brookes,et al.  Ghost interactions in MEG/EEG source space: A note of caution on inter-areal coupling measures , 2017, NeuroImage.

[55]  Stavros I. Dimitriadis,et al.  Mining Time-Resolved Functional Brain Graphs to an EEG-Based Chronnectomic Brain Aged Index (CBAI) , 2017, Front. Hum. Neurosci..

[56]  Haiping Lu,et al.  MPCA: Multilinear Principal Component Analysis of Tensor Objects , 2008, IEEE Transactions on Neural Networks.

[57]  Karl J. Friston.  Functional and Effective Connectivity: A Review , 2011, Brain Connect..

[58]  Zhongxiang Ding,et al.  Directed Functional Connectivity of Posterior Cingulate Cortex and Whole Brain in Alzheimer's Disease and Mild Cognitive Impairment. , 2017, Current Alzheimer research.

[59]  Panagiotis G. Simos,et al.  Data-Driven Topological Filtering Based on Orthogonal Minimal Spanning Trees: Application to Multigroup Magnetoencephalography Resting-State Connectivity , 2017, Brain Connect..

[60]  Roberto C. Sotero,et al.  Topology, Cross-Frequency, and Same-Frequency Band Interactions Shape the Generation of Phase-Amplitude Coupling in a Neural Mass Model of a Cortical Column , 2016, bioRxiv.

[61]  M. Corbetta,et al.  Large-scale cortical correlation structure of spontaneous oscillatory activity , 2012, Nature Neuroscience.

[62]  George Loizou,et al.  Computer vision and pattern recognition , 2007, Int. J. Comput. Math..

[63]  M. Hallett,et al.  Identifying true brain interaction from EEG data using the imaginary part of coherency , 2004, Clinical Neurophysiology.

[64]  Roberto Hornero,et al.  MEG Connectivity Analysis in Patients with Alzheimer’s Disease Using Cross Mutual Information and Spectral Coherence , 2010, Annals of Biomedical Engineering.

[65]  Dimitri Van De Ville,et al.  Decoding brain states from fMRI connectivity graphs , 2011, NeuroImage.

[66]  G. Nolte.  The magnetic lead field theorem in the quasi-static approximation and its use for magnetoencephalography forward calculation in realistic volume conductors. , 2003, Physics in medicine and biology.

[67]  Cees van Leeuwen,et al.  Efficiency of Conscious Access Improves with Coupling of Slow and Fast Neural Oscillations , 2014, Journal of Cognitive Neuroscience.

[68]  E. John,et al.  Decreased EEG synchronization in Alzheimer’s disease and mild cognitive impairment , 2005, Neurobiology of Aging.

[69]  D. Leopold,et al.  Layer-Specific Entrainment of Gamma-Band Neural Activity by the Alpha Rhythm in Monkey Visual Cortex , 2012, Current Biology.

[70]  F. Varela,et al.  Measuring phase synchrony in brain signals , 1999, Human brain mapping.

[71]  Takashi Asada,et al.  [Diagnosis of mild cognitive impairment]. , 2004, Seishin shinkeigaku zasshi = Psychiatria et neurologia Japonica.

[72]  Mark W. Woolrich,et al.  Measuring functional connectivity in MEG: A multivariate approach insensitive to linear source leakage , 2012, NeuroImage.

[73]  S. Micheloyannis,et al.  Altered cross-frequency coupling in resting-state MEG after mild traumatic brain injury. , 2016, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[74]  Jack M. Fletcher,et al.  Data-driven Topological Filtering based on Orthogonal Minimal Spanning Trees: Application to Multi-Group MEG Resting-State Connectivity , 2017, bioRxiv.

[75]  F. Collette,et al.  Alzheimer' Disease as a Disconnection Syndrome? , 2003, Neuropsychology Review.

[76]  E G Tangalos,et al.  Mild cognitive impairment. When is it a precursor to Alzheimer's disease? , 2000, Geriatrics.

[77]  S. Taulu,et al.  Suppression of Interference and Artifacts by the Signal Space Separation Method , 2003, Brain Topography.

[78]  Matthew J. Brookes,et al.  Measuring functional connectivity using MEG: Methodology and comparison with fcMRI , 2011, NeuroImage.

[79]  J. Matias Palva,et al.  Hyperedge bundling: A practical solution to spurious interactions in MEG/EEG source connectivity analyses , 2017, NeuroImage.

[80]  N. Castellanos,et al.  Synchronization during an internally directed cognitive state in healthy aging and mild cognitive impairment: a MEG study , 2014, AGE.

[81]  Josef Parvizi,et al.  Dynamic Changes in Phase-Amplitude Coupling Facilitate Spatial Attention Control in Fronto-Parietal Cortex , 2014, PLoS biology.

[82]  Yong He,et al.  Disrupted Functional Brain Connectome in Individuals at Risk for Alzheimer's Disease , 2013, Biological Psychiatry.

[83]  Satu Palva,et al.  Roles of multiscale brain activity fluctuations in shaping the variability and dynamics of psychophysical performance. , 2011, Progress in brain research.

[84]  Derek K. Jones,et al.  Improving the Reliability of Network Metrics in Structural Brain Networks by Integrating Different Network Weighting Strategies into a Single Graph , 2017, Front. Neurosci..

[85]  F. Mormann,et al.  Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients , 2000 .

[86]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[87]  Brendon O. Watson,et al.  Brain rhythms and neural syntax: implications for efficient coding of cognitive content and neuropsychiatric disease. , 2012, Dialogues in clinical neuroscience.

[88]  N. Tzourio-Mazoyer,et al.  Automated Anatomical Labeling of Activations in SPM Using a Macroscopic Anatomical Parcellation of the MNI MRI Single-Subject Brain , 2002, NeuroImage.

[89]  R. Wise,et al.  Frontoparietal cognitive control of verbal memory recall in Alzheimer's disease , 2014, Annals of neurology.

[90]  W. Drongelen,et al.  Localization of brain electrical activity via linearly constrained minimum variance spatial filtering , 1997, IEEE Transactions on Biomedical Engineering.

[91]  Cornelis J. Stam,et al.  Disturbed Beta Band Functional Connectivity in Patients With Mild Cognitive Impairment: An MEG Study , 2009, IEEE Transactions on Biomedical Engineering.

[92]  Ankoor S. Shah,et al.  An oscillatory hierarchy controlling neuronal excitability and stimulus processing in the auditory cortex. , 2005, Journal of neurophysiology.

[93]  Matthew J. Brookes,et al.  A multi-layer network approach to MEG connectivity analysis , 2016, NeuroImage.

[94]  Deng Cai,et al.  Tensor Subspace Analysis , 2005, NIPS.

[95]  J. Morris,et al.  The diagnosis of dementia due to Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer’s Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[96]  Panagiotis G. Simos,et al.  Greater Repertoire and Temporal Variability of Cross-Frequency Coupling (CFC) Modes in Resting-State Neuromagnetic Recordings among Children with Reading Difficulties , 2016, Front. Hum. Neurosci..

[97]  S. Aurtenetxe,et al.  White Matter Damage Disorganizes Brain Functional Networks in Amnestic Mild Cognitive Impairment , 2014, Brain Connect..

[98]  Jun Li,et al.  Brain spontaneous functional connectivity and intelligence , 2008, NeuroImage.

[99]  E. Tangalos,et al.  Mild Cognitive Impairment Clinical Characterization and Outcome , 1999 .

[100]  James T. Becker,et al.  A multicenter study of the early detection of synaptic dysfunction in Mild Cognitive Impairment using Magnetoencephalography-derived functional connectivity , 2015, NeuroImage: Clinical.

[101]  Giorgio Roffo,et al.  Feature Selection Library (MATLAB Toolbox) , 2016 .

[102]  Ricardo Bruña,et al.  Influence of the APOE ε4 allele and mild cognitive impairment diagnosis in the disruption of the MEG resting state functional connectivity in sources space. , 2015, Journal of Alzheimer's disease : JAD.

[103]  W. Jagust,et al.  Degree of discrepancy between self and other‐reported everyday functioning by cognitive status: dementia, mild cognitive impairment, and healthy elders , 2005, International journal of geriatric psychiatry.

[104]  Kristina M. Visscher,et al.  A Core System for the Implementation of Task Sets , 2006, Neuron.

[105]  C. J. Stam,et al.  EEG synchronization likelihood in mild cognitive impairment and Alzheimer's disease during a working memory task , 2004, Clinical Neurophysiology.

[106]  Michael T. Lin,et al.  Co-occurrence of Alzheimer's disease β-amyloid and tau pathologies at synapses , 2010, Neurobiology of Aging.

[107]  Nitish Thakor,et al.  Cognitive Workload Assessment Based on the Tensorial Treatment of EEG Estimates of Cross-Frequency Phase Interactions , 2014, Annals of Biomedical Engineering.