Abstract
The benign epilepsy with spinous waves in the central temporal region (BECT) is the one of the most common epileptic syndromes in children, that seriously threaten the nervous system development of children. The most obvious feature of BECT is the existence of a large number of electroencephalogram (EEG) spikes in the Rolandic area during the interictal period, that is an important basis to assist neurologists in BECT diagnosis. With this regard, the paper proposes a novel BECT spike detection algorithm based on time domain EEG sequence features and the long short-term memory (LSTM) neural network. Three time domain sequence features, that can obviously characterize the spikes of BECT, are extracted for EEG representation. The synthetic minority oversampling technique (SMOTE) is applied to address the spike imbalance issue in EEGs, and the bi-directional LSTM (BiLSTM) is trained for spike detection. The algorithm is evaluated using the EEG data of 15 BECT patients recorded from the Children's Hospital, Zhejiang University School of Medicine (CHZU). The experiment shows that the proposed algorithm can obtained an average of 88.54% F1 score, 92.04% sensitivity, and 85.75% precision, that generally outperforms several state-of-the-art spike detection methods.
Highlights
To have a better diagnosis of BECT patients, 56 neurologists have to analyze the EEG data to find the epilep- 57As a common neurological disease, the incidence of epilep- tiform discharges in the millisecond level, which is extremely 58 sy in children is 10∼15 times as high as that of adults. tedious and time-consuming
We develop a Benign childhood epilepsy with centro-temporal spikes
The fully connected (FC) neural network is designed with a the EEGs of 15 children (8 males and 7 females) suffered three-layer structure, the number of neurons are 500, 250, and from the BECT syndrome, with the age ranging from 3 to
Summary
To have a better diagnosis of BECT patients, 56 neurologists have to analyze the EEG data to find the epilep- 57. Most spike detection has high-frequency spike-like characteristics, but its amplitude 138 algorithms tend to use time domain features. Compared with the long-term EEG recordings, the duration segment to ensure that they can be applied for the subsequent ;W of the EEG in the non-spike state is usually much longer model learning. The mor- Fig. 5 plots the typical BECT spike and non-spike EEG phological opening-closing operation (OC), closing-opening samples, and their corresponding SNE and MC features. Conventional RNN gener- from the original EEG, the characteristic sequence containing ally uses simple repeating module containing only one tanh only the waveform of the type structure unit is layer for time series learning.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Transactions on Neural Systems and Rehabilitation Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
