Adversarial Representation Learning for Robust Patient-Independent Epileptic Seizure Detection

Application of deconvolutional networks for feature interpretability in epilepsy detection

Introduction

Scalp electroencephalography (EEG) is commonly used to assist in epilepsy detection. Even automated detection algorithms are already available to assist clinicians in reviewing EEG data, many algorithms used for seizure detection in epilepsy fail to account for the contributions of different channels. The Fully Convolutional Network (FCN) can provide the model's interpretability but has not been applied in seizure detection.

Methods

To address these challenges, a novel convolutional neural network (CNN) model, combining SE (Squeeze-and-Excitation) modules, was proposed on top of the FCN. The epilepsy detection performance for patient-independent was evaluated on the CHB-MIT dataset. Then, the SE module was removed from the model and integrated the model with Inception, ResNet, and CBAM modules separately.

Results

The method showed superior advancement, stability, and reliability compared to the other three methods. The method demonstrated a G-Mean of 82.7% for sensitivity (SEN) and specificity (SPE) on the CHB-MIT dataset. In addition, The contributions of each channel to the seizure detection task have also been quantified, which led us to find that the FZ, CZ, PZ, FT9, FT10, and T8 brain regions have a more pronounced impact on epileptic seizures.

Discussion

This article presents a novel algorithm for epilepsy detection that accurately identifies seizures in different patients and enhances the model's interpretability.

An epilepsy detection method based on multi-dimensional feature extraction and dual-branch hypergraph convolutional network

Epilepsy is a disease caused by abnormal neural discharge, which severely harms the health of patients. Its pathogenesis is complex and variable with various forms of seizures, leading to significant differences in epilepsy manifestations among different patients. The changes of brain network are strongly correlated with related pathologies. Therefore, it is crucial to effectively and deeply explore the intrinsic features of epilepsy signals to reveal the rules of epilepsy occurrence and achieve accurate detection. Existing methods have faced the following issues: 1) single approach for feature extraction, resulting in insufficient classification information due to the lack of rich dimensions in captured features; 2) inability to deeply analyze the essential commonality of epilepsy signal after feature extraction, making the model susceptible to data distribution and noise interference. Thus, we proposed a high-precision and robust model for epileptic seizure detection, which, for the first time, applies hypergraph convolution to the field of epilepsy detection. Through a hypergraph network structure constructed based on relationships between channels in electroencephalogram (EEG) signals, the model explores higher-order characteristics of epilepsy EEG data. Specifically, we use the Conv-LSTM module and Power spectral density (PSD), a two-branch parallel method, to extract channel features from space-time and frequency domains to solve the problem of insufficient feature extraction, and can adequately describe the data structure and distribution from multiple perspectives through double-branch parallel feature extraction. In addition, we construct a hypergraph on the captured features to explore the intrinsic features in the high-dimensional space in an attempt to reveal the essential commonality of epileptic signal feature extraction. Finally, using the ensemble learning concept, we accomplished epilepsy detection on the dual-branch hypergraph convolution. The model underwent leave-one-out cross-validation on the TUH dataset, achieving an average accuracy of 96.9%, F1 score of 97.3%, Pre of 98.2% and Re of 96.7%. In addition, the model was generalized performance tested on CHB-MIT scalp EEG dataset with leave-one-out cross-validation, and the average ACC, F1 score, Pre and Re were 94.4%, 95.1%, 95.8%, and 93.9% respectively. Experimental results indicate that the model outperforms related literature, providing valuable reference for the clinical application of epilepsy detection.

Evaluation of the Relation between Ictal EEG Features and XAI Explanations

Epilepsy is a neurological disease with one of the highest rates of incidence worldwide. Although EEG is a crucial tool for its diagnosis, the manual detection of epileptic seizures is time consuming. Automated methods are needed to streamline this process; although there are already several works that have achieved this, the process by which it is executed remains a black box that prevents understanding of the ways in which machine learning algorithms make their decisions. A state-of-the-art deep learning model for seizure detection and three EEG databases were chosen for this study. The developed models were trained and evaluated under different conditions (i.e., three distinct levels of overlap among the chosen EEG data windows). The classifiers with the best performance were selected, then Shapley Additive Explanations (SHAPs) and Local Interpretable Model-Agnostic Explanations (LIMEs) were employed to estimate the importance value of each EEG channel and the Spearman's rank correlation coefficient was computed between the EEG features of epileptic signals and the importance values. The results show that the database and training conditions may affect a classifier's performance. The most significant accuracy rates were 0.84, 0.73, and 0.64 for the CHB-MIT, Siena, and TUSZ EEG datasets, respectively. In addition, most EEG features displayed negligible or low correlation with the importance values. Finally, it was concluded that a correlation between the EEG features and the importance values (generated by SHAP and LIME) may have been absent even for the high-performance models.

Identification of autism spectrum disorder based on electroencephalography: A systematic review

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by difficulties in social communication and repetitive and stereotyped behaviors. According to the World Health Organization, about 1 in 100 children worldwide has autism. With the global prevalence of ASD, timely and accurate diagnosis has been essential in enhancing the intervention effectiveness for ASD children. Traditional ASD diagnostic methods rely on clinical observations and behavioral assessment, with the disadvantages of time-consuming and lack of objective biological indicators. Therefore, automated diagnostic methods based on machine learning and deep learning technologies have emerged and become significant since they can achieve more objective, efficient, and accurate ASD diagnosis. Electroencephalography (EEG) is an electrophysiological monitoring method that records changes in brain spontaneous potential activity, which is of great significance for identifying ASD children. By analyzing EEG data, it is possible to detect abnormal synchronous neuronal activity of ASD children. This paper gives a comprehensive review of the EEG-based ASD identification using traditional machine learning methods and deep learning approaches, including their merits and potential pitfalls. Additionally, it highlights the challenges and the opportunities ahead in search of more effective and efficient methods to automatically diagnose autism based on EEG signals, which aims to facilitate automated ASD identification.

RIHANet: A Residual-based Inception with Hybrid-Attention Network for Seizure Detection using EEG signals

Increasing attention is being given to machine learning methods designed to aid clinicians in treatment selection. Therefore, this has aroused a heightened focus on the auto-detect system of epilepsy utilizing electroencephalogram(EEG) data. However, in order for the recognition model to accurately capture a wide range of features related to channel, frequency, and temporal information, it is necessary to have EEG data that is correctly represented. To tackle this challenge, we propose a Residual-based Inception with Hybrid-Attention Network(RIHANet) to achieve automatic seizure detection. Initially, by employing Empirical Mode Decomposition and Short-time Fourier Transform(EMD-STFT) for data processing, it can improve the quality of time-frequency representation of EEG. Additionally, by applying a novel Residual-based Inception to the network architecture, the detection model can learn local and global multiscale spatial-temporal features. Furthermore, the Hybrid Attention model designed is used to obtain relationships between EEG signals from multiple perspectives, including channels, sub-spaces, and global. Using four public datasets, the suggested approach outperforms the results in the most recent scholarly publications.

Efficient and generalizable cross-patient epileptic seizure detection through a spiking neural network

Introduction

Epilepsy is a global chronic disease that brings pain and inconvenience to patients, and an electroencephalogram (EEG) is the main analytical tool. For clinical aid that can be applied to any patient, an automatic cross-patient epilepsy seizure detection algorithm is of great significance. Spiking neural networks (SNNs) are modeled on biological neurons and are energy-efficient on neuromorphic hardware, which can be expected to better handle brain signals and benefit real-world, low-power applications. However, automatic epilepsy seizure detection rarely considers SNNs.

Methods

In this article, we have explored SNNs for cross-patient seizure detection and discovered that SNNs can achieve comparable state-of-the-art performance or a performance that is even better than artificial neural networks (ANNs). We propose an EEG-based spiking neural network (EESNN) with a recurrent spiking convolution structure, which may better take advantage of temporal and biological characteristics in EEG signals.

Results

We extensively evaluate the performance of different SNN structures, training methods, and time settings, which builds a solid basis for understanding and evaluation of SNNs in seizure detection. Moreover, we show that our EESNN model can achieve energy reduction by several orders of magnitude compared with ANNs according to the theoretical estimation.

Discussion

These results show the potential for building high-performance, low-power neuromorphic systems for seizure detection and also broaden real-world application scenarios of SNNs.

An improved GBSO-TAENN-based EEG signal classification model for epileptic seizure detection

Detection and classification of epileptic seizures from the EEG signals have gained significant attention in recent decades. Among other signals, EEG signals are extensively used by medical experts for diagnosing purposes. So, most of the existing research works developed automated mechanisms for designing an EEG-based epileptic seizure detection system. Machine learning techniques are highly used for reduced time consumption, high accuracy, and optimal performance. Still, it limits by the issues of high complexity in algorithm design, increased error value, and reduced detection efficacy. Thus, the proposed work intends to develop an automated epileptic seizure detection system with an improved performance rate. Here, the Finite Linear Haar wavelet-based Filtering (FLHF) technique is used to filter the input signals and the relevant set of features are extracted from the normalized output with the help of Fractal Dimension (FD) analysis. Then, the Grasshopper Bio-Inspired Swarm Optimization (GBSO) technique is employed to select the optimal features by computing the best fitness value and the Temporal Activation Expansive Neural Network (TAENN) mechanism is used for classifying the EEG signals to determine whether normal or seizure affected. Numerous intelligence algorithms, such as preprocessing, optimization, and classification, are used in the literature to identify epileptic seizures based on EEG signals. The primary issues facing the majority of optimization approaches are reduced convergence rates and higher computational complexity. Furthermore, the problems with machine learning approaches include a significant method complexity, intricate mathematical calculations, and a decreased training speed. Therefore, the goal of the proposed work is to put into practice efficient algorithms for the recognition and categorization of epileptic seizures based on EEG signals. The combined effect of the proposed FLHF, FD, GBSO, and TAENN models might dramatically improve disease detection accuracy while decreasing complexity of system along with time consumption as compared to the prior techniques. By using the proposed methodology, the overall average epileptic seizure detection performance is increased to 99.6% with f-measure of 99% and G-mean of 98.9% values.

An empirical comparison of deep learning explainability approaches for EEG using simulated ground truth

Recent advancements in machine learning and deep learning (DL) based neural decoders have significantly improved decoding capabilities using scalp electroencephalography (EEG). However, the interpretability of DL models remains an under-explored area. In this study, we compared multiple model explanation methods to identify the most suitable method for EEG and understand when some of these approaches might fail. A simulation framework was developed to evaluate the robustness and sensitivity of twelve back-propagation-based visualization methods by comparing to ground truth features. Multiple methods tested here showed reliability issues after randomizing either model weights or labels: e.g., the saliency approach, which is the most used visualization technique in EEG, was not class or model-specific. We found that DeepLift was consistently accurate as well as robust to detect the three key attributes tested here (temporal, spatial, and spectral precision). Overall, this study provides a review of model explanation methods for DL-based neural decoders and recommendations to understand when some of these methods fail and what they can capture in EEG.

Feature separation and adversarial training for the patient-independent detection of epileptic seizures

An epileptic seizure is the external manifestation of abnormal neuronal discharges, which seriously affecting physical health. The pathogenesis of epilepsy is complex, and the types of epileptic seizures are diverse, resulting in significant variation in epileptic seizure data between subjects. If we feed epilepsy data from multiple patients directly into the model for training, it will lead to underfitting of the model. To overcome this problem, we propose a robust epileptic seizure detection model that effectively learns from multiple patients while eliminating the negative impact of the data distribution shift between patients. The model adopts a multi-level temporal-spectral feature extraction network to achieve feature extraction, a feature separation network to separate features into category-related and patient-related components, and an invariant feature extraction network to extract essential feature information related to categories. The proposed model is evaluated on the TUH dataset using leave-one-out cross-validation and achieves an average accuracy of 85.7%. The experimental results show that the proposed model is superior to the related literature and provides a valuable reference for the clinical application of epilepsy detection.

Patient Independent Interictal Epileptiform Discharge Detection

Epilepsy is a highly prevalent brain condition with many serious complications arising from it. The majority of patients which present to a clinic and undergo electroencephalogram (EEG) monitoring would be unlikely to experience seizures during the examination period, thus the presence of interictal epileptiform discharges (IEDs) become effective markers for the diagnosis of epilepsy. Furthermore, IED shapes and patterns are highly variable across individuals, yet trained experts are still able to identify them through EEG recordings - meaning that commonalities exist across IEDs that an algorithm can be trained on to detect and generalise to the larger population. This research proposes an IED detection system for the binary classification of epilepsy using scalp EEG recordings. The proposed system features an ensemble based deep learning method to boost the performance of a residual convolutional neural network, and a bidirectional long short-term memory network. This is implemented using raw EEG data, sourced from Temple University Hospital's EEG Epilepsy Corpus, and is found to outperform the current state of the art model for IED detection across the same dataset. The achieved accuracy and Area Under Curve (AUC) of 94.92% and 97.45% demonstrates the effectiveness of an ensemble method, and that IED detection can be achieved with high performance using raw scalp EEG data, thus showing promise for the proposed approach in clinical settings.

Patient-independent seizure detection based on long-term iEEG and a novel lightweight CNN

Objective.Patient-dependent seizure detection based on intracranial electroencephalography (iEEG) has made significant progress. However, due to the difference in the locations and number of iEEG electrodes used for each patient, patient-independent seizure detection based on iEEG has not been carried out. Additionally, current seizure detection algorithms based on deep learning have outperformed traditional machine learning algorithms in many performance metrics. However, they still have shortcomings of large memory footprints and slow inference speed.Approach.To solve the above problems of the current study, we propose a novel lightweight convolutional neural network model combining the Convolutional Block Attention Module (CBAM). Its performance for patient-independent seizure detection is evaluated on two long-term continuous iEEG datasets: SWEC-ETHZ and TJU-HH. Finally, we reproduce four other patient-independent methods to compare with our method and calculate the memory footprints and inference speed for all methods.Main results.Our method achieves 83.81% sensitivity (SEN) and 85.4% specificity (SPE) on the SWEC-ETHZ dataset and 86.63% SEN and 92.21% SPE on the TJU-HH dataset. In particular, it takes only 11 ms to infer 10 min iEEG (128 channels), and its memory footprint is only 22 kB. Compared to baseline methods, our method not only achieves better patient-independent seizure detection performance but also has a smaller memory footprint and faster inference speed.Significance.To our knowledge, this is the first iEEG-based patient-independent seizure detection study. This facilitates the application of seizure detection algorithms to the future clinic.

Cluster Embedding Joint-Probability-Discrepancy Transfer for Cross-Subject Seizure Detection

Transfer learning (TL) has been applied in seizure detection to deal with differences between different subjects or tasks. In this paper, we consider cross-subject seizure detection that does not rely on patient history records, that is, acquiring knowledge from other subjects through TL to improve seizure detection performance. We propose a novel domain adaptation method, named the Cluster Embedding Joint-Probability-Discrepancy Transfer (CEJT), for data distribution structure learning. Specifically, 1) The joint probability distribution discrepancy is minimized to reduce the distribution shift in the source and target domains, and strengthen the discriminative knowledge of classes. 2) A clustering is performed on the target domain, and the class centroids of sources is used as the clustering prototype of the target domain to enhance data structure. It is worth noting that the manifold regularization is used to improve the quality of clustering prototypes. In addition, a correlation-alignment-based source selection metric (SSC) is designed for most favorable subject selection, reducing the computational cost as well as avoiding some negative transfer. Experiments on 15 patients with focal epilepsy from the Children's Hospital, Zhejiang University School of Medicine (CHZU) database shown that CEJT outperforms several state-of-the-art approaches, and can promote the application of seizure detection.

Supervised Machine Learning and Deep Learning Techniques for Epileptic Seizure Recognition Using EEG Signals-A Systematic Literature Review

Electroencephalography (EEG) is a complicated, non-stationary signal that requires extensive preprocessing and feature extraction approaches to be accurately analyzed. In recent times, Deep learning (DL) has shown great promise in exploiting the characteristics of EEG signals as it can learn relevant features from raw data autonomously. Although studies involving DL have become more common in the last two years, the topic of whether DL truly delivers advantages over conventional Machine learning (ML) methodologies remains unsettled. This study aims to present a detailed overview of the main challenges in the field of seizure detection, prediction, and classification utilizing EEG data, and the approaches taken to solve them using ML and DL methods. A systematic review was conducted surveying peer-reviewed publications published between 2017 and 16 July 2022 using two scientific databases (Web of Science and Scopus) totaling 6822 references after discarding duplicate publications. Whereas 2262 articles were screened based on the title, abstract, and keywords, only 214 were eligible for full-text assessment. A total of 91 papers have been included in this survey after meeting the eligible inclusion and exclusion criteria. The most significant findings from the review are summarized, and several important concepts involving ML and DL for seizure detection, prediction, and classification are discussed in further depth. This review aims to learn more about the different approaches for identifying different types and stages of epileptic seizures, which may then be employed to enhance the lives of epileptic patients in the future, as well as aid experts in the field.

Explainable AI for clinical and remote health applications: a survey on tabular and time series data

Nowadays Artificial Intelligence (AI) has become a fundamental component of healthcare applications, both clinical and remote, but the best performing AI systems are often too complex to be self-explaining. Explainable AI (XAI) techniques are defined to unveil the reasoning behind the system’s predictions and decisions, and they become even more critical when dealing with sensitive and personal health data. It is worth noting that XAI has not gathered the same attention across different research areas and data types, especially in healthcare. In particular, many clinical and remote health applications are based on tabular and time series data, respectively, and XAI is not commonly analysed on these data types, while computer vision and Natural Language Processing (NLP) are the reference applications. To provide an overview of XAI methods that are most suitable for tabular and time series data in the healthcare domain, this paper provides a review of the literature in the last 5 years, illustrating the type of generated explanations and the efforts provided to evaluate their relevance and quality. Specifically, we identify clinical validation, consistency assessment, objective and standardised quality evaluation, and human-centered quality assessment as key features to ensure effective explanations for the end users. Finally, we highlight the main research challenges in the field as well as the limitations of existing XAI methods.

XAI4EEG: spectral and spatio-temporal explanation of deep learning-based seizure detection in EEG time series

In clinical practice, algorithmic predictions may seriously jeopardise patients’ health and thus are required to be validated by medical experts before a final clinical decision is met. Towards that aim, there is need to incorporate explainable artificial intelligence techniques into medical research. In the specific field of epileptic seizure detection there are several machine learning algorithms but less methods on explaining them in an interpretable way. Therefore, we introduce XAI4EEG: an application-aware approach for an explainable and hybrid deep learning-based detection of seizures in multivariate EEG time series. In XAI4EEG, we combine deep learning models and domain knowledge on seizure detection, namely (a) frequency bands, (b) location of EEG leads and (c) temporal characteristics. XAI4EEG encompasses EEG data preparation, two deep learning models and our proposed explanation module visualizing feature contributions that are obtained by two SHAP explainers, each explaining the predictions of one of the two models. The resulting visual explanations provide an intuitive identification of decision-relevant regions in the spectral, spatial and temporal EEG dimensions. To evaluate XAI4EEG, we conducted a user study, where users were asked to assess the outputs of XAI4EEG, while working under time constraints, in order to emulate the fact that clinical diagnosis is done - more often than not - under time pressure. We found that the visualizations of our explanation module (1) lead to a substantially lower time for validating the predictions and (2) leverage an increase in interpretability, trust and confidence compared to selected SHAP feature contribution plots.

Multi-view cross-subject seizure detection with information bottleneck attribution

OBJECTIVE

Significant progress has been witnessed in within-subject seizure detection from Electroencephalography (EEG) signals. Consequently, more and more works have been shifted from within-subject seizure detection to cross-subject scenarios. However, the progress is hindered by inter-patient variations caused by gender, seizure type, etc. Approach: To tackle this problem, we propose a multi-view cross-object seizure detection model with information bottleneck attribution. Feature representations specific to seizures are learned from raw EEG data by adversarial deep learning. Combined with the manually designed discriminative features, the model can detect seizures across different subjects. In addition, we introduce information bottleneck attribution to provide insights into the decision-making of the adversarial learning process, thus enhancing the interpretability of the model.

MAIN RESULTS

Extensive experiments are conducted on two benchmark datasets. The experimental results verify the efficacy of the model.

Patient-Independent Seizure Detection Based on Channel-Perturbation Convolutional Neural Network and Bidirectional Long Short-Term Memory

Automatic seizure detection is of great significance for epilepsy diagnosis and alleviating the massive burden caused by manual inspection of long-term EEG. At present, most seizure detection methods are highly patient-dependent and have poor generalization performance. In this study, a novel patient-independent approach is proposed to effectively detect seizure onsets. First, the multi-channel EEG recordings are preprocessed by wavelet decomposition. Then, the Convolutional Neural Network (CNN) with proper depth works as an EEG feature extractor. Next, the obtained features are fed into a Bidirectional Long Short-Term Memory (BiLSTM) network to further capture the temporal variation characteristics. Finally, aiming to reduce the false detection rate (FDR) and improve the sensitivity, the postprocessing, including smoothing and collar, is performed on the outputs of the model. During the training stage, a novel channel perturbation technique is introduced to enhance the model generalization ability. The proposed approach is comprehensively evaluated on the CHB-MIT public scalp EEG database as well as a more challenging SH-SDU scalp EEG database we collected. Segment-based average accuracies of 97.51% and 93.70%, event-based average sensitivities of 86.51% and 89.89%, and average AUC-ROC of 90.82% and 90.75% are yielded on the CHB-MIT database and SH-SDU database, respectively.

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

Deep neural networks (DNN) have shown unprecedented success in various brain-machine interface (BMI) applications such as epileptic seizure prediction. However, existing approaches typically train models in a patient-specific fashion due to the highly personalized characteristics of epileptic signals. Therefore, only a limited number of labeled recordings from each subject can be used for training. As a consequence, current DNN based methods demonstrate poor generalization ability to some extent due to the insufficiency of training data. On the other hand, patient-independent models attempt to utilize more patient data to train a universal model for all patients by pooling patient data together. Despite different techniques applied, results show that patient-independent models perform worse than patient-specific models due to high individual variation across patients. A substantial gap thus exists between patient-specific and patient-independent models. In this paper, we propose a novel training scheme based on knowledge distillation which makes use of a large amount of data from multiple subjects. It first distills informative features from signals of all available subjects with a pre-trained general model. A patient-specific model can then be obtained with the help of distilled knowledge and additional personalized data. The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors. Five state-of-the-art seizure prediction methods are trained on the CHB-MIT sEEG database with our proposed scheme. The resulting accuracy, sensitivity, and false prediction rate show that our proposed training scheme consistently improves the prediction performance of state-of-the-art methods by a large margin.

Deep Convolutional Gated Recurrent Unit Combined with Attention Mechanism to Classify Pre-Ictal from Interictal EEG with Minimized Number of Channels

The early prediction of epileptic seizures is important to provide appropriate treatment because it can notify clinicians in advance. Various EEG-based machine learning techniques have been used for automatic seizure classification based on subject-specific paradigms. However, because subject-specific models tend to perform poorly on new patient data, a generalized model with a cross-patient paradigm is necessary for building a robust seizure diagnosis system. In this study, we proposed a generalized model that combines one-dimensional convolutional layers (1D CNN), gated recurrent unit (GRU) layers, and attention mechanisms to classify preictal and interictal phases. When we trained this model with ten minutes of preictal data, the average accuracy over eight patients was 82.86%, with 80% sensitivity and 85.5% precision, outperforming other state-of-the-art models. In addition, we proposed a novel application of attention mechanisms for channel selection. The personalized model using three channels with the highest attention score from the generalized model performed better than when using the smallest attention score. Based on these results, we proposed a model for generalized seizure predictors and a seizure-monitoring system with a minimized number of EEG channels.

A deep neural network for the classification of epileptic seizures using hierarchical attention mechanism

Electroencephalogram (EEG) is a common diagnostic tool for measuring the seizure activity of the brain. There are many deep learning techniques introduced to analyze EEG. These methods show phenomenal results, although they are limited to computational complexity. Our objective was to develop a novel algorithm that gives maximum classification accuracy with a minor computational complexity. In this view, we have introduced a novel convolutional architecture with an integration of a hierarchical attention mechanism. The model comprises three parts: Feature extraction layer, which uses to extract the convoluted feature map; hierarchical attention layer, which is used to obtain weighted hierarchical feature map; classification layer, which uses weighted features for classification of healthy and seizure subjects. The proposed model can extract significant information from the EEG signal to classify seizure subjects, and it is compared with a few existing deep convolutional algorithms through experimentation. The experimental outcomes show that the proposed model has higher accuracy with less computational time.

Unsupervised seizure identification on EEG

BACKGROUND AND OBJECTIVE

Epilepsy is one of the most common neurological disorders, whose development is typically detected via early seizures. Electroencephalogram (EEG) is prevalently employed for seizure identification due to its routine and low expense collection. The stochastic nature of EEG makes manual seizure inspections laborsome, motivating automated seizure identification. The relevant literature focuses mostly on supervised machine learning. Despite their success, supervised methods require expert labels indicating seizure segments, which are difficult to obtain on clinically-acquired EEG. Thus, we aim to devise an unsupervised method for seizure identification on EEG.

METHODS

We propose the first fully-unsupervised deep learning method for seizure identification on raw EEG, using a variational autoencoder (VAE). In doing so, we train the VAE on recordings without seizures. As training captures non-seizure activity, we identify seizures with respect to the reconstruction errors at inference time. Moreover, we extend the traditional VAE training loss to suppress EEG artifacts. Our method does not require ground-truth expert labels indicating seizure segments or manual feature extraction.

RESULTS

We implement our method using the PyTorch library and execute experiments on an NVIDIA V100 GPU. We evaluate our method on three benchmark EEG datasets: (i) intracranial recordings from the University of Pennsylvania and the Mayo Clinic, (ii) scalp recordings from the Temple University Hospital of Philadelphia, and (iii) scalp recordings from the Massachusetts Institute of Technology and the Boston Children's Hospital. To assess performance, we report accuracy, precision, recall, Area under the Receiver Operating Characteristics Curve (AUC), and p-value under the Welch t-test for distinguishing seizure vs. non-seizure EEG windows. Our approach can successfully distinguish seizures from non-seizure activity, with up to 0.83 AUC on intracranial recordings. Moreover, our algorithm has the potential for real-time inference, by processing at least 10 s of EEG in a second.

CONCLUSION

We take the first successful steps in deep learning-based unsupervised seizure identification on raw EEG. Our approach has the potential of alleviating the burden on clinical experts regarding laborsome EEG inspections for seizures. Furthermore, aiding the identification of early seizures via our method could facilitate successful detection of epilepsy development and initiate antiepileptogenic therapies.

An Automatic Method for Epileptic Seizure Detection Based on Deep Metric Learning

Electroencephalography (EEG) is a commonly used clinical approach for the diagnosis of epilepsy which is a life-threatening neurological disorder. Many algorithms have been proposed for the automatic detection of epileptic seizures using traditional machine learning and deep learning. Although deep learning methods have achieved great success in many fields, their performance in EEG analysis and classification is still limited mainly due to the relatively small sizes of available datasets. In this paper, we propose an automatic method for the detection of epileptic seizures based on deep metric learning which is a novel strategy tackling the few-shot problem by mitigating the demand for massive data. First, two one-dimensional convolutional embedding modules are proposed as a deep feature extractor, for single-channel and multichannel EEG signals respectively. Then, a deep metric learning model is detailed along with a stage-wise training strategy. Experiments are conducted on the publicly-available Bonn University dataset which is a benchmark dataset, and the CHB-MIT dataset which is larger and more realistic. Impressive averaged accuracy of 98.60% and specificity of 100% are achieved on the most difficult classification of interictal (subset D) vs ictal (subset E) of the Bonn dataset. On the CHB-MIT dataset, an averaged accuracy of 86.68% and specificity of 93.71% are reached. With the proposed method, automatic and accurate detection of seizures can be performed in real time, and the heavy burden of neurologists can be effectively reduced.

Multi-View Multi-Scale Optimization of Feature Representation for EEG Classification Improvement

Effectively extracting common space pattern (CSP) features from motor imagery (MI) EEG signals is often highly dependent on the filter band selection. At the same time, optimizing the EEG channel combinations is another key issue that substantially affects the SMR feature representations. Although numerous algorithms have been developed to find channels that record important characteristics of MI, most of them select channels in a cumbersome way with low computational efficiency, thereby limiting the practicality of MI-based BCI systems. In this study, we propose the multi-scale optimization (MSO) of spatial patterns, optimizing filter bands over multiple channel sets within CSPs to further improve the performance of MI-based BCI. Specifically, several channel subsets are first heuristically predefined, and then raw EEG data specific to each of these subsets bandpass-filtered at the overlap between a set of filter bands. Further, instead of solving learning problems for each channel subset independently, we propose a multi-view learning based sparse optimization to jointly extract robust CSP features with L_2,1 -norm regularization, aiming to capture the shared salient information across multiple related spatial patterns for enhanced classification performance. A support vector machine (SVM) classifier is then trained on these optimized EEG features for accurate recognition of MI tasks. Experimental results on three public EEG datasets validate the effectiveness of MSO compared to several other competing methods and their variants. These superior experimental results demonstrate that the proposed MSO method has promising potential in MI-based BCIs.

Reinforcement Learning Based Fast Self-Recalibrating Decoder for Intracortical Brain-Machine Interface

BACKGROUND

For the nonstationarity of neural recordings in intracortical brain-machine interfaces, daily retraining in a supervised manner is always required to maintain the performance of the decoder. This problem can be improved by using a reinforcement learning (RL) based self-recalibrating decoder. However, quickly exploring new knowledge while maintaining a good performance remains a challenge in RL-based decoders.

METHODS

To solve this problem, we proposed an attention-gated RL-based algorithm combining transfer learning, mini-batch, and weight updating schemes to accelerate the weight updating and avoid over-fitting. The proposed algorithm was tested on intracortical neural data recorded from two monkeys to decode their reaching positions and grasping gestures.

RESULTS

The decoding results showed that our proposed algorithm achieved an approximate 20% increase in classification accuracy compared to that obtained by the non-retrained classifier and even achieved better classification accuracy than the daily retraining classifier. Moreover, compared with a conventional RL method, our algorithm improved the accuracy by approximately 10% and the online weight updating speed by approximately 70 times.

CONCLUSIONS

This paper proposed a self-recalibrating decoder which achieved a good and robust decoding performance with fast weight updating and might facilitate its application in wearable device and clinical practice.

Cross-Subject Seizure Detection in EEGs Using Deep Transfer Learning

Electroencephalography (EEG) plays an import role in monitoring the brain activities of patients with epilepsy and has been extensively used to diagnose epilepsy. Clinically reading tens or even hundreds of hours of EEG recordings is very time consuming. Therefore, automatic detection of seizure is of great importance. But the huge diversity of EEG signals belonging to different patients makes the task of seizure detection much challenging, for both human experts and automation methods. We propose three deep transfer convolutional neural networks (CNN) for automatic cross-subject seizure detection, based on VGG16, VGG19, and ResNet50, respectively. The original dataset is the CHB-MIT scalp EEG dataset. We use short time Fourier transform to generate time-frequency spectrum images as the input dataset, while positive samples are augmented due to the infrequent nature of seizure. The model parameters pretrained on ImageNet are transferred to our models. And the fine-tuned top layers, with an output layer of two neurons for binary classification (seizure or nonseizure), are trained from scratch. Then, the input dataset are randomly shuffled and divided into three partitions for training, validating, and testing the deep transfer CNNs, respectively. The average accuracies achieved by the deep transfer CNNs based on VGG16, VGG19, and ResNet50 are 97.75%, 98.26%, and 96.17% correspondingly. On those results of experiments, our method could prove to be an effective method for cross-subject seizure detection.