Automated detection of abnormalities from an EEG recording of epilepsy patients with a compact convolutional neural network

Electroencephalography (EEG) is essential for the diagnosis of epilepsy, but it requires expertise and experience to identify abnormalities. It is thus crucial to develop automated models for the detection of abnormalities in EEGs related to epilepsy. This paper describes the development of a novel class of compact convolutional neural networks (CNNs) for detecting abnormal patterns and electrodes in EEGs for epilepsy. The designed model is inspired by a CNN developed for brain-computer interfacing called multichannel EEGNet (mEEGNet). Unlike the EEGNet, the proposed model, mEEGNet, has the same number of electrode inputs and outputs to detect abnormal patterns. The mEEGNet was evaluated with a clinical dataset consisting of 29 cases of juvenile and childhood absence epilepsy labeled by a clinical expert. The labels were given to paroxysmal discharges visually observed in both ictal (seizure) and interictal (nonseizure) durations. Results showed that the mEEGNet detected abnormalities with the area under the curve, F1-values, and sensitivity equivalent to or higher than those of existing CNNs. Moreover, the number of parameters is much smaller than other CNN models. To our knowledge, the dataset of absence epilepsy validated with machine learning through this research is the largest in the literature. ?Fully documented templates are available in the elsarticle package on CTAN. ∗Corresponding author Email address: tanakat@cc.tuat.ac.jp (Toshihisa Tanaka) Preprint submitted to Journal of LATEX Templates June 29, 2021 ar X iv :2 10 5. 10 35 8v 2 [ ee ss .S P] 2 6 Ju n 20 21

[1]  Yuichi Tanaka,et al.  Scalpnet: Detection of Spatiotemporal Abnormal Intervals in Epileptic EEG Using Convolutional Neural Networks , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  Toshihisa Tanaka,et al.  Fully Data-driven Convolutional Filters with Deep Learning Models for Epileptic Spike Detection , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Stephen M. Gordon,et al.  EEGNet: A Compact Convolutional Neural Network for EEG-based Brain-Computer Interfaces , 2021 .

[4]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Rubén San-Segundo-Hernández,et al.  Classification of epileptic EEG recordings using signal transforms and convolutional neural networks , 2019, Comput. Biol. Medicine.

[6]  Pradip Sircar,et al.  Seizures classification based on higher order statistics and deep neural network , 2020, Biomed. Signal Process. Control..

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

[8]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Andreas Christmann,et al.  Support vector machines , 2008, Data Mining and Knowledge Discovery Handbook.

[10]  L. Rossi,et al.  Interictal paroxysmal EEG abnormalities in childhood absence epilepsy , 2011, Seizure.

[11]  M. Putten,et al.  Detecting abnormal electroencephalograms using deep convolutional networks , 2019, Clinical Neurophysiology.

[12]  C P Panayiotopoulos,et al.  Typical absence seizures and their treatment , 1999, Archives of disease in childhood.

[13]  Maurice Abou Jaoude,et al.  Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning , 2019, Clinical Neurophysiology.

[14]  Yongtian He,et al.  Deep learning for electroencephalogram (EEG) classification tasks: a review , 2019, Journal of neural engineering.

[15]  Joelle Pineau,et al.  Learning Robust Features using Deep Learning for Automatic Seizure Detection , 2016, MLHC.

[16]  S. Kessler,et al.  A Practical Guide to Treatment of Childhood Absence Epilepsy , 2019, Pediatric Drugs.

[17]  Saeid Nahavandi,et al.  A comprehensive comparison of handcrafted features and convolutional autoencoders for epileptic seizures detection in EEG signals , 2021, Expert Syst. Appl..

[18]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.

[19]  M. Shamim Hossain,et al.  Applying Deep Learning for Epilepsy Seizure Detection and Brain Mapping Visualization , 2019, ACM Trans. Multim. Comput. Commun. Appl..

[20]  Saleh A. Alshebeili,et al.  A Review of EEG and MEG Epileptic Spike Detection Algorithms , 2018, IEEE Access.

[21]  Rui Cao,et al.  Epileptic Seizure Detection Based on EEG Signals and CNN , 2018, Front. Neuroinform..

[22]  U. Rajendra Acharya,et al.  A deep convolutional neural network model for automated identification of abnormal EEG signals , 2018, Neural Computing and Applications.

[23]  Ruben Morales-Menendez,et al.  A review of epileptic seizure detection using machine learning classifiers , 2020, Brain Informatics.

[24]  Josef Parvizi,et al.  Promises and limitations of human intracranial electroencephalography , 2018, Nature Neuroscience.

[25]  M. Friedman.  The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance , 1937 .

[26]  Yang Song,et al.  Class-Balanced Loss Based on Effective Number of Samples , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Sebastian Raschka,et al.  Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence , 2020, Inf..

[28]  U. Rajendra Acharya,et al.  Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals , 2017, Comput. Biol. Medicine.

[29]  Justin Dauwels,et al.  Epileptiform spike detection via convolutional neural networks , 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).