The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.

Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Prague Prague Czech Republic

Department of Neurology St Anne's University Hospital Brno Czech Republic

Department of Physiology and Biomedical Engineering Mayo Clinic Rochester MN 55905 USA

International Clinical Research Center St Anne's University Hospital Brno Brno Czech Republic

Mayo Systems Electrophysiology Laboratory Department of Neurology Mayo Clinic Rochester MN 55905 USA

The Czech Academy of Sciences Institute of Scientific Instruments Brno Czech Republic

Zobrazit více v PubMed

Brazier, M. A. B. Computer techniques in EEG analysis. (Elsevier, 1961).

Buzsaki, G. Rhythms of the Brain. (Oxford University Press, 2011).

Berger, H. Hans Berger on the electroencephalogram of man: the fourteen original reports on the human electroencephalogram. (Elsevier Pub. Co., 1969).

Schomer, D. L. Niedermeyer’s Electroencephalography: Basic Principles, Clinical Applications, and Related Fields. (Oxford University Press, 2018).

Houfek EE, Ellingson RJ. On the reliability of clinical EEG interpretation. J. Nerv. Ment. Dis. 1959;128:425–437. doi: 10.1097/00005053-195905000-00006. PubMed DOI

Piccinelli P, et al. Inter-rater reliability of the EEG reading in patients with childhood idiopathic epilepsy. Epilepsy Res. 2005;66:195–198. doi: 10.1016/j.eplepsyres.2005.07.004. PubMed DOI

Gardner AB, Worrell GA, Marsh E, Dlugos D, Litt B. Human and automated detection of high-frequency oscillations in clinical intracranial EEG recordings. Clin. Neurophysiol. Off. J. Int. Fed. Clin. Neurophysiol. 2007;118:1134–1143. doi: 10.1016/j.clinph.2006.12.019. PubMed DOI PMC

Gerber PA, et al. Interobserver agreement in the interpretation of EEG patterns in critically ill adults. J. Clin. Neurophysiol. Off. Publ. Am. Electroencephalogr. Soc. 2008;25:241–249. PubMed

Abend NS, et al. Interobserver reproducibility of electroencephalogram interpretation in critically ill children. J. Clin. Neurophysiol. Off. Publ. Am. Electroencephalogr. Soc. 2011;28:15–19. PubMed PMC

Grant AC, et al. EEG interpretation reliability and interpreter confidence: a large single-center study. Epilepsy Behav. EB. 2014;32:102–107. doi: 10.1016/j.yebeh.2014.01.011. PubMed DOI PMC

Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun. ACM. 2017;60:84–90. doi: 10.1145/3065386. DOI

New Era for Robust Speech Recognition: Exploiting Deep Learning. (Springer International Publishing, 2017).

Kubat Miroslav. An Introduction to Machine Learning. Cham: Springer International Publishing; 2015. Reinforcement Learning; pp. 277–286.

Clifford, G. et al. AF Classification from a Short Single Lead ECG Recording: the Physionet Computing in Cardiology Challenge 2017. in, 10.22489/CinC.2017.065-469 (2017). PubMed PMC

Plesinger F, Nejedly P, Viscor I, Halamek J, Jurak P. Parallel use of a convolutional neural network and bagged tree ensemble for the classification of Holter ECG. Physiol. Meas. 2018;39:094002. doi: 10.1088/1361-6579/aad9ee. PubMed DOI

Roy, Y. et al. Deep learning-based electroencephalography analysis: a systematic review. ArXiv190105498 Cs Eess Stat (2019). PubMed

Nejedly P, et al. Intracerebral EEG Artifact Identification Using Convolutional Neural Networks. Neuroinformatics. 2018 doi: 10.1007/s12021-018-9397-6. PubMed DOI PMC

Acharya UR, Oh SL, Hagiwara Y, Tan JH, Adeli H. Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals. Comput. Biol. Med. 2018;100:270–278. doi: 10.1016/j.compbiomed.2017.09.017. PubMed DOI

Kiral-Kornek I, et al. Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System. EBioMedicine. 2017;27:103–111. doi: 10.1016/j.ebiom.2017.11.032. PubMed DOI PMC

Jasper’s Basic Mechanisms of the Epilepsies. (National Center for Biotechnology Information (US), 2012). PubMed

Manaswi Navin Kumar. Deep Learning with Applications Using Python. Berkeley, CA: Apress; 2018. RNN and LSTM; pp. 115–126.

Pascanu, R., Mikolov, T. & Bengio, Y. On the difficulty of training Recurrent Neural Networks. ArXiv12115063 Cs (2012).

Brázdil M, et al. Very high-frequency oscillations: Novel biomarkers of the epileptogenic zone. Ann. Neurol. 2017;82:299–310. doi: 10.1002/ana.25006. PubMed DOI

Plesinger F, Jurco J, Halamek J, Jurak P. SignalPlant: an open signal processing software platform. Physiol. Meas. 2016;37:N38–48. doi: 10.1088/0967-3334/37/7/N38. PubMed DOI

Nejedly P, Plesinger F, Halamek J, Jurak P. CudaFilters: A SignalPlant library for GPU-accelerated FFT and FIR filtering. Softw. Pract. Exp. 2018;48:3–9. doi: 10.1002/spe.2507. DOI

LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539. PubMed DOI

Ben-Nun, T. & Hoefler, T. Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis. ArXiv180209941 Cs (2018).

Kingma, D. P. & Ba, J. Adam: A Method for Stochastic Optimization. (2014).

PyTorch. Available at: https://www.pytorch.org. (Accessed: 1st February 2019).

Zimmermann Hans-Georg, Tietz Christoph, Grothmann Ralph. Lecture Notes in Computer Science. Berlin, Heidelberg: Springer Berlin Heidelberg; 2012. Forecasting with Recurrent Neural Networks: 12 Tricks; pp. 687–707.

Utilization of temporal autoencoder for semi-supervised intracranial EEG clustering and classification

Distributed brain co-processor for tracking spikes, seizures and behaviour during electrical brain stimulation

Seizure likelihood varies with day-to-day variations in sleep duration in patients with refractory focal epilepsy: A longitudinal electroencephalography investigation

Identifying seizure risk factors: A comparison of sleep, weather, and temporal features using a Bayesian forecast

Multicenter intracranial EEG dataset for classification of graphoelements and artifactual signals