QuPWM: Feature Extraction Method for Epileptic Spike Classification

Magnetoencephalography-based approaches to epilepsy classification

Epilepsy is a chronic central nervous system disorder characterized by recurrent seizures. Not only does epilepsy severely affect the daily life of the patient, but the risk of premature death in patients with epilepsy is three times higher than that of the normal population. Magnetoencephalography (MEG) is a non-invasive, high temporal and spatial resolution electrophysiological data that provides a valid basis for epilepsy diagnosis, and used in clinical practice to locate epileptic foci in patients with epilepsy. It has been shown that MEG helps to identify MRI-negative epilepsy, contributes to clinical decision-making in recurrent seizures after previous epilepsy surgery, that interictal MEG can provide additional localization information than scalp EEG, and complete excision of the stimulation area defined by the MEG has prognostic significance for postoperative seizure control. However, due to the complexity of the MEG signal, it is often difficult to identify subtle but critical changes in MEG through visual inspection, opening up an important area of research for biomedical engineers to investigate and implement intelligent algorithms for epilepsy recognition. At the same time, the use of manual markers requires significant time and labor costs, necessitating the development and use of computer-aided diagnosis (CAD) systems that use classifiers to automatically identify abnormal activity. In this review, we discuss in detail the results of applying various different feature extraction methods on MEG signals with different classifiers for epilepsy detection, subtype determination, and laterality classification. Finally, we also briefly look at the prospects of using MEG for epilepsy-assisted localization (spike detection, high-frequency oscillation detection) due to the unique advantages of MEG for functional area localization in epilepsy, and discuss the limitation of current research status and suggestions for future research. Overall, it is hoped that our review will facilitate the reader to quickly gain a general understanding of the problem of MEG-based epilepsy classification and provide ideas and directions for subsequent research.

An improved BECT spike detection method with functional brain network features based on PLV

Background

Children with benign childhood epilepsy with centro-temporal spikes (BECT) have spikes, sharps, and composite waves on their electroencephalogram (EEG). It is necessary to detect spikes to diagnose BECT clinically. The template matching method can identify spikes effectively. However, due to the individual specificity, finding representative templates to detect spikes in actual applications is often challenging.

Purpose

This paper proposes a spike detection method using functional brain networks based on phase locking value (FBN-PLV) and deep learning.

Methods

To obtain high detection effect, this method uses a specific template matching method and the ‘peak-to-peak' phenomenon of montages to obtain a set of candidate spikes. With the set of candidate spikes, functional brain networks (FBN) are constructed based on phase locking value (PLV) to extract the features of the network structure during spike discharge with phase synchronization. Finally, the time domain features of the candidate spikes and the structural features of the FBN-PLV are input into the artificial neural network (ANN) to identify the spikes.

Results

Based on FBN-PLV and ANN, the EEG data sets of four BECT cases from the Children's Hospital, Zhejiang University School of Medicine are tested with the AC of 97.6%, SE of 98.3%, and SP 96.8%.

Fully-Automated Spike Detection and Dipole Analysis of Epileptic MEG Using Deep Learning

Magnetoencephalography (MEG) is a useful tool for clinically evaluating the localization of interictal spikes. Neurophysiologists visually identify spikes from the MEG waveforms and estimate the equivalent current dipoles (ECD). However, presently, these analyses are manually performed by neurophysiologists and are time-consuming. Another problem is that spike identification from MEG waveforms largely depends on neurophysiologists' skills and experiences. These problems cause poor cost-effectiveness in clinical MEG examination. To overcome these problems, we fully automated spike identification and ECD estimation using a deep learning approach fully automated AI-based MEG interictal epileptiform discharge identification and ECD estimation (FAMED). We applied a semantic segmentation method, which is an image processing technique, to identify the appropriate times between spike onset and peak and to select appropriate sensors for ECD estimation. FAMED was trained and evaluated using clinical MEG data acquired from 375 patients. FAMED training was performed in two stages: in the first stage, a classification network was learned, and in the second stage, a segmentation network that extended the classification network was learned. The classification network had a mean AUC of 0.9868 (10-fold patient-wise cross-validation); the sensitivity and specificity were 0.7952 and 0.9971, respectively. The median distance between the ECDs estimated by the neurophysiologists and those using FAMED was 0.63 cm. Thus, the performance of FAMED is comparable to that of neurophysiologists, and it can contribute to the efficiency and consistency of MEG ECD analysis.

SQNN: A Spike-wave index Quantification Neural Network with a pre-labeling algorithm for epileptiform activity identification and quantification in children

OBJECTIVE

Electrical status epilepticus during slow sleep (ESES) is a phenomenon identified by strong activation of epileptiform activity in the electroencephalogram (EEG) during sleep. For children disturbed by ESES, spike-wave index (SWI) is defined to quantify the epileptiform activity in the EEG during sleep. Accurate SWI quantification is important for clinical diagnosis and prognosis. To quantify SWI automatically, a deep learning method is proposed in this paper.

APPROACH

Firstly, a pre-labeling algorithm (PreLA) composed of the adaptive wavelet enhanced decomposition and a slow-wave discrimination rule is designed to efficiently label the EEG signal. It enables the collection of large-scale EEG dataset with fine-grained labels. Then, an SWI Quantification Neural Network (SQNN) is constructed to accurately classify each sample point as normal or abnormal and to identify the abnormal events. SWI can be calculated automatically based on the total duration of abnormalities and the length of the signal.

MAIN RESULTS

Experiments on two datasets demonstrate that the PreLA is effective and robust for labeling the EEG data and the SQNN accurately and reliably quantifies SWI without using any thresholds. The average estimation error of SWI is 3.12%, indicating that our method is more accurate and robust than experts and previous related works. The processing speed of SQNN is 100 times faster than that of experts.

SIGNIFICANCE

Deep learning provides a novel approach to automatic SWI quantification and PreLA provides an easy way to label the EEG data with ESES syndromes. The results of the experiments indicate that the proposed method has a high potential for clinical diagnosis and prognosis of epilepsy in children.

BECT Spike Detection Based on Novel EEG Sequence Features and LSTM Algorithms

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.

A Position Weight Matrix Feature Extraction Algorithm Improves Hand Gesture Recognition

Recent advances in the biomedical field have generated a massive amount of data and records (signals) that are collected for diagnosis purposes. The correct interpretation and understanding of these signals present a big challenge for digital health vision. In this work, Quantization-based position Weight Matrix (QuPWM) feature extraction method for multiclass classification is proposed to improve the interpretation of biomedical signals. This method is validated on surface Electromyogram (sEMG) signals recognition for eight different hand gestures. The used CapgMyo dataset consists of high-density sEMG signals across 128 channels acquired from 9 intact subjects. Our pilot results show that an accuracy of up to 83% can be achieved for some subjects using a support vector machine classifier, and an average accuracy of 75% has been reached for all studied subjects using the CapgMyo dataset. The proposed method shows a good potential in extracting relevant features from different biomedical signals such as Electroencephalogram (EEG) and Magnetoencephalogram (MEG) signals.