EEG Connectivity Analysis Using Denoising Autoencoders for the Detection of Dyslexia

The Temporal Sampling Framework (TSF) theorizes that the characteristic phonological difficulties of dyslexia are caused by an atypical oscillatory sampling at one or more temporal rates. The LEEDUCA study conducted a series of Electroencephalography (EEG) experiments on children listening to amplitude modulated (AM) noise with slow-rythmic prosodic (0.5-1[Formula: see text]Hz), syllabic (4-8[Formula: see text]Hz) or the phoneme (12-40[Formula: see text]Hz) rates, aimed at detecting differences in perception of oscillatory sampling that could be associated with dyslexia. The purpose of this work is to check whether these differences exist and how they are related to children's performance in different language and cognitive tasks commonly used to detect dyslexia. To this purpose, temporal and spectral inter-channel EEG connectivity was estimated, and a denoising autoencoder (DAE) was trained to learn a low-dimensional representation of the connectivity matrices. This representation was studied via correlation and classification analysis, which revealed ability in detecting dyslexic subjects with an accuracy higher than 0.8, and balanced accuracy around 0.7. Some features of the DAE representation were significantly correlated ([Formula: see text]) with children's performance in language and cognitive tasks of the phonological hypothesis category such as phonological awareness and rapid symbolic naming, as well as reading efficiency and reading comprehension. Finally, a deeper analysis of the adjacency matrix revealed a reduced bilateral connection between electrodes of the temporal lobe (roughly the primary auditory cortex) in DD subjects, as well as an increased connectivity of the F7 electrode, placed roughly on Broca's area. These results pave the way for a complementary assessment of dyslexia using more objective methodologies such as EEG.

[1]  Weidong Zhou,et al.  Using Dictionary Pair Learning for Seizure Detection , 2019, Int. J. Neural Syst..

[2]  Kevin Kok Wai Wong,et al.  A Review of Electroencephalogram-Based Analysis and Classification Frameworks for Dyslexia , 2016, ICONIP.

[3]  Weidong Zhou,et al.  Epileptic Seizure Detection with EEG Textural Features and Imbalanced Classification Based on EasyEnsemble Learning , 2019, Int. J. Neural Syst..

[4]  Dimitris Kugiumtzis,et al.  Identification of Hidden Sources by Estimating Instantaneous Causality in High-Dimensional Biomedical Time Series , 2019, Int. J. Neural Syst..

[5]  B. Pennington,et al.  Developmental dyslexia , 2012, The Lancet.

[6]  Usha Goswami,et al.  The Journal of the Acoustical Society of America The role of phase synchronisation between low frequency amplitude modulations in child phonology and morphology speech tasks , 2018 .

[7]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[8]  Vangelis Sakkalis,et al.  Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG , 2011, Comput. Biol. Medicine.

[9]  John Boddy,et al.  Evoked potentials and the dynamics of language processing , 1981, Biological Psychology.

[10]  Hojjat Adeli,et al.  Complexity of weighted graph: A new technique to investigate structural complexity of brain activities with applications to aging and autism , 2017, Neuroscience Letters.

[11]  James F. Peters,et al.  Multi-manifold LLE learning in pattern recognition , 2015, Pattern Recognit..

[12]  G. Egan,et al.  Reduced connectivity of the auditory cortex in patients with auditory hallucinations: a resting state functional magnetic resonance imaging study , 2009, Psychological Medicine.

[13]  C. J. Álvarez,et al.  Syllabic parsing in children: a developmental study using visual word-spotting in Spanish* , 2016, Journal of Child Language.

[14]  L. Lagae,et al.  Altered functional connectivity of the language network in ASD: Role of classical language areas and cerebellum☆ , 2014, NeuroImage: Clinical.

[15]  Danielle S. Bassett,et al.  Integrating EEG and MEG Signals to Improve Motor Imagery Classification in Brain-Computer Interface , 2017, Int. J. Neural Syst..

[16]  R. Tibshirani,et al.  Sparse inverse covariance estimation with the graphical lasso. , 2008, Biostatistics.

[17]  Yang Yang,et al.  Principal States of Dynamic Functional Connectivity Reveal the Link Between Resting-State and Task-State Brain: An fMRI Study , 2018, Int. J. Neural Syst..

[18]  Hojjat Adeli,et al.  Fuzzy Synchronization Likelihood-wavelet methodology for diagnosis of autism spectrum disorder , 2012, Journal of Neuroscience Methods.

[19]  J. Schoffelen,et al.  Source connectivity analysis with MEG and EEG , 2009, Human brain mapping.

[20]  Antonio Fernández-Caballero,et al.  Multiscale Entropy Analysis for Recognition of Visually Elicited Negative Stress From EEG Recordings , 2019, Int. J. Neural Syst..

[21]  Francisco Jesús Martínez-Murcia,et al.  Learning Longitudinal MRI Patterns by SICE and Deep Learning: Assessing the Alzheimer's Disease Progression , 2017, MIUA.

[22]  Jared A. Nielsen,et al.  Abnormal lateralization of functional connectivity between language and default mode regions in autism , 2014, Molecular Autism.

[23]  Sampsa Vanhatalo,et al.  Time-Varying EEG Correlations Improve Automated Neonatal Seizure Detection , 2019, Int. J. Neural Syst..

[24]  H. Adeli,et al.  Brain functional connectivity patterns for emotional state classification in Parkinson’s disease patients without dementia , 2016, Behavioural Brain Research.

[25]  P. Welch.  The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms , 1967 .

[26]  Denis Burnham,et al.  Atypical cortical entrainment to speech in the right hemisphere underpins phonemic deficits in dyslexia , 2018, NeuroImage.

[27]  C. Adler,et al.  Quantitative EEG as a predictive biomarker for Parkinson disease dementia , 2011, Neurology.

[28]  Fei Wang,et al.  The Dynamic Brain Networks of Motor Imagery: Time-Varying Causality Analysis of Scalp EEG , 2019, Int. J. Neural Syst..

[29]  E Donchin,et al.  A new method for off-line removal of ocular artifact. , 1983, Electroencephalography and clinical neurophysiology.

[30]  Klaus-Robert Müller,et al.  The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials , 2004, IEEE Transactions on Biomedical Engineering.

[31]  Antonio José Ibañez-Molina,et al.  Differential Effects of Simulated Cortical Network Lesions on Synchrony and EEG Complexity , 2019, Int. J. Neural Syst..

[32]  Usha Goswami,et al.  A neural oscillations perspective on phonological development and phonological processing in developmental dyslexia , 2019, Lang. Linguistics Compass.

[33]  Robert P. W. Duin,et al.  Classifiers in almost empty spaces , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[34]  Sabine Van Huffel,et al.  Neonatal Seizure Detection Using Deep Convolutional Neural Networks , 2019, Int. J. Neural Syst..

[35]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[36]  Debbie Gooch,et al.  Developmental dyslexia: predicting individual risk , 2015, Journal of child psychology and psychiatry, and allied disciplines.

[37]  Lawrence K. Saul,et al.  Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifold , 2003, J. Mach. Learn. Res..

[38]  Juan Manuel Górriz,et al.  Periodogram Connectivity of EEG Signals for the Detection of Dyslexia , 2019, IWINAC.

[39]  Fabio Babiloni,et al.  Human Brain Distinctiveness Based on EEG Spectral Coherence Connectivity , 2014, IEEE Transactions on Biomedical Engineering.

[40]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[41]  Usha Goswami,et al.  Speech rhythm and language acquisition: an amplitude modulation phase hierarchy perspective , 2019, Annals of the New York Academy of Sciences.

[42]  F. Deligianni,et al.  Relating resting-state fMRI and EEG whole-brain connectomes across frequency bands , 2014, Front. Neurosci..

[43]  Diego Castillo-Barnes,et al.  Studying the Manifold Structure of Alzheimer's Disease: A Deep Learning Approach Using Convolutional Autoencoders , 2020, IEEE Journal of Biomedical and Health Informatics.

[44]  Fatma Latifoglu,et al.  Analysis of the Complexity Measures in the EEG of Schizophrenia Patients , 2016, Int. J. Neural Syst..

[45]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[46]  Hojjat Adeli,et al.  Functional community analysis of brain: A new approach for EEG-based investigation of the brain pathology , 2011, NeuroImage.

[47]  Chang-Hwan Im,et al.  Performance Prediction for a Near-Infrared Spectroscopy-Brain-Computer Interface Using Resting-State Functional Connectivity of the Prefrontal Cortex , 2018, Int. J. Neural Syst..

[48]  Gonzalo Alarcón,et al.  Characterizing EEG Cortical Dynamics and Connectivity with Responses to Single Pulse Electrical Stimulation (SPES) , 2017, Int. J. Neural Syst..

[49]  Julio Ortega,et al.  An Anomaly Detection Approach for Dyslexia Diagnosis Using EEG Signals , 2019, IWINAC.

[50]  Manuel Recuero,et al.  Short-Term Effects of Binaural Beats on EEG Power, Functional Connectivity, Cognition, Gait and Anxiety in Parkinson's Disease , 2017, Int. J. Neural Syst..

[51]  Juan Manuel Górriz,et al.  P300 brainwave extraction from EEG signals: An unsupervised approach , 2017, Expert Syst. Appl..

[52]  Yan Zhao,et al.  Single-Cell Recordings to Target the Anterior Nucleus of the Thalamus in Deep Brain Stimulation for Patients with Refractory Epilepsy , 2019, Int. J. Neural Syst..

[53]  Olivier Ledoit,et al.  A well-conditioned estimator for large-dimensional covariance matrices , 2004 .

[54]  H. Adeli,et al.  of Depressive Women and Men Spatiotemporal Analysis of Relative Convergence of EEGs Reveals Differences Between Brain Dynamics , 2013 .

[55]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[56]  H. Adeli,et al.  Complexity of functional connectivity networks in mild cognitive impairment subjects during a working memory task , 2014, Clinical Neurophysiology.

[57]  John Suckling,et al.  Brain anatomy and its relationship to behavior in adults with autism spectrum disorder: a multicenter magnetic resonance imaging study. , 2012, Archives of general psychiatry.

[58]  H. Adeli,et al.  Visibility graph similarity: A new measure of generalized synchronization in coupled dynamic systems , 2012 .

[59]  Jan Wouters,et al.  A longitudinal study investigating neural processing of speech envelope modulation rates in children with (a family risk for) dyslexia , 2017, Cortex.

[60]  Christoph Schmidt,et al.  Tracking the Reorganization of Module Structure in Time-Varying Weighted Brain Functional Connectivity Networks , 2017, Int. J. Neural Syst..

[61]  A. Toga,et al.  Neuroanatomical precursors of dyslexia identified from pre-reading through to age 11. , 2014, Brain : a journal of neurology.

[62]  D Liberati,et al.  EEG coherence in Alzheimer's disease. , 1998, Electroencephalography and clinical neurophysiology.

[63]  Yury Shtyrov,et al.  Impaired neural mechanism for online novel word acquisition in dyslexic children , 2018, Scientific Reports.

[64]  Joel Nothman,et al.  SciPy 1.0-Fundamental Algorithms for Scientific Computing in Python , 2019, ArXiv.