Autoencoding of long-term scalp electroencephalogram to detect epileptic seizure for diagnosis support system

INTRODUCTION Epileptologists could benefit from a diagnosis support system that automatically detects seizures because visual inspection of long-term electroencephalograms (EEGs) is extremely time-consuming. However, the diversity of seizures among patients makes it difficult to develop universal features that are applicable for automatic seizure detection in all cases, and the rarity of seizures results in a lack of sufficient training data for classifiers. METHODS To overcome these problems, we utilized an autoencoder (AE), which is often used for anomaly detection in the field of machine learning, to perform seizure detection. We hypothesized that multichannel EEG signals are compressible by AE owing to their spatio-temporal coupling and that the AE should be able to detect seizures as anomalous events from an interictal EEG. RESULTS Through experiments, we found that the AE error was able to classify seizure and nonseizure states with a sensitivity of 100% in 22 out of 24 available test subjects and that the AE was better than the commercially available software BESA and Persyst for half of the test subjects. CONCLUSIONS These results suggest that the AE error is a feasible candidate for a universal seizure detection feature.

[1]  Chen Zhang,et al.  A 16-Channel Patient-Specific Seizure Onset and Termination Detection SoC With Impedance-Adaptive Transcranial Electrical Stimulator , 2015, IEEE Journal of Solid-State Circuits.

[2]  Ali H. Shoeb,et al.  Patient-specific seizure onset detection , 2004, Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

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

[4]  Guo-Qiang Zhang,et al.  EpiDEA: Extracting Structured Epilepsy and Seizure Information from Patient Discharge Summaries for Cohort Identification , 2012, AMIA.

[5]  B. W. van Dijk,et al.  Opportunities and methodological challenges in EEG and MEG resting state functional brain network research , 2015, Clinical Neurophysiology.

[6]  Takehisa Yairi,et al.  Anomaly Detection Using Autoencoders with Nonlinear Dimensionality Reduction , 2014, MLSDA'14.

[7]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[8]  J. Gotman,et al.  A system to detect the onset of epileptic seizures in scalp EEG , 2005, Clinical Neurophysiology.

[9]  Joseph Picone,et al.  Deep Architectures for Automated Seizure Detection in Scalp EEGs , 2017, ArXiv.

[10]  Jasmin Kevric,et al.  Epileptic seizure detection using hybrid machine learning methods , 2017, Neural Computing and Applications.

[11]  Hojjat Adeli,et al.  Mixed-Band Wavelet-Chaos-Neural Network Methodology for Epilepsy and Epileptic Seizure Detection , 2007, IEEE Transactions on Biomedical Engineering.

[12]  Hasan Ocak,et al.  Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy , 2009, Expert Syst. Appl..

[13]  Brian Litt,et al.  Collaborating and sharing data in epilepsy research. , 2015, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[14]  Kensuke Kawai,et al.  Seizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images , 2019, NeuroImage: Clinical.

[15]  Cornelis J Stam,et al.  Seizure detection in the neonatal EEG with synchronization likelihood , 2003, Clinical Neurophysiology.

[16]  Yasuo Horiuchi,et al.  Reverberant speech recognition based on denoising autoencoder , 2013, INTERSPEECH.

[17]  Tamer Demiralp,et al.  Classification of electroencephalogram signals with combined time and frequency features , 2011, Expert Syst. Appl..

[18]  Chen Zhang,et al.  Design and Implementation of an On-Chip Patient-Specific Closed-Loop Seizure Onset and Termination Detection System , 2016, IEEE Journal of Biomedical and Health Informatics.

[19]  C. M. Lim,et al.  Characterization of EEG - A comparative study , 2005, Comput. Methods Programs Biomed..

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Abdulhamit Subasi,et al.  Automatic identification of epileptic seizures from EEG signals using linear programming boosting , 2016, Comput. Methods Programs Biomed..

[22]  J Gotman,et al.  Automatic detection of seizures and spikes. , 1999, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[23]  Tong Zhang,et al.  A multistage, multimethod approach for automatic detection and classification of epileptiform EEG , 2002, IEEE Transactions on Biomedical Engineering.

[24]  Kemal Polat,et al.  Artificial immune recognition system with fuzzy resource allocation mechanism classifier, principal component analysis and FFT method based new hybrid automated identification system for classification of EEG signals , 2008, Expert Syst. Appl..

[25]  Stephanie Gollwitzer,et al.  Automatic seizure detection in long-term scalp EEG using an adaptive thresholding technique: A validation study for clinical routine , 2014, Clinical Neurophysiology.

[26]  M. Botvinick,et al.  Neural representations of events arise from temporal community structure , 2013, Nature Neuroscience.

[27]  Michael J. A. M. Van Putten,et al.  Nearest neighbor phase synchronization as a measure to detect seizure activity from scalp EEG recordings. , 2003 .

[28]  Elif Derya íbeyli.  Lyapunov exponents/probabilistic neural networks for analysis of EEG signals , 2010 .

[29]  Yusuf Uzzaman Khan,et al.  AUTOMATIC DETECTION OF SEIZURE ONSET IN PEDIATRIC EEG , 2012 .

[30]  Scott B. Wilson,et al.  Seizure detection: evaluation of the Reveal algorithm , 2004, Clinical Neurophysiology.

[31]  Sebastian Stober,et al.  Deep Feature Learning for EEG Recordings , 2015, ArXiv.

[32]  G M Manzano,et al.  Anterior zygomatic electrodes: a special electrode for the study of temporal lobe epilepsy. , 1986, Applied neurophysiology.

[33]  Tingxi Wen,et al.  Deep Convolution Neural Network and Autoencoders-Based Unsupervised Feature Learning of EEG Signals , 2018, IEEE Access.

[34]  Kensuke Kawai,et al.  State-dependent precursors of seizures in correlation-based functional networks of electrocorticograms of patients with temporal lobe epilepsy , 2012, Neurological Sciences.

[35]  A. Tzallas,et al.  Automated Epileptic Seizure Detection Methods: A Review Study , 2012 .

[36]  Ilker Yaylali,et al.  Detection of Interictal Spikes and Artifactual Data Through Orthogonal Transformations , 2005, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[37]  Jeffrey Pennington,et al.  Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection , 2011, NIPS.

[38]  Ankit N Khambhati,et al.  Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings , 2017, Brain : a journal of neurology.

[39]  M. Scheuer,et al.  Seizure detection with automated EEG analysis: A validation study focusing on periodic patterns , 2014, Clinical Neurophysiology.

[40]  Jasmin Kevric,et al.  Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction , 2018, Biomed. Signal Process. Control..

[41]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[42]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[43]  W. Hauser,et al.  Comment on Epileptic Seizures and Epilepsy: Definitions Proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE) , 2005, Epilepsia.

[44]  Hojjat Adeli,et al.  A Wavelet-Chaos Methodology for Analysis of EEGs and EEG Subbands to Detect Seizure and Epilepsy , 2007, IEEE Transactions on Biomedical Engineering.