Automatic Epileptic Seizure Detection Research Articles

Multi-branch fusion graph neural network based on multi-head attention for childhood seizure detection.

The most common manifestation of neurological disorders in children is the occurrence of epileptic seizures. In this study, we propose a multi-branch graph convolutional network (MGCNA) framework with a multi-head attention mechanism for detecting seizures in children. The MGCNA framework extracts effective and reliable features from high-dimensional data, particularly by exploring the relationships between EEG features and electrodes and considering the spatial and temporal dependencies in epileptic brains. This method incorporates three graph learning approaches to systematically assess the connectivity and synchronization of multi-channel EEG signals. The multi-branch graph convolutional network is employed to dynamically learn temporal correlations and spatial topological structures. Utilizing the multi-head attention mechanism to process multi-branch graph features further enhances the capability to handle local features. Experimental results demonstrate that the MGCNA exhibits superior performance on patient-specific and patient-independent experiments. Our end-to-end model for automatic detection of epileptic seizures could be employed to assist in clinical decision-making.

Generative AI with WGAN-GP for boosting seizure detection accuracy.

Imbalanced datasets pose challenges for developing accurate seizure detection systems based on electroencephalogram (EEG) data. Generative AI techniques may help augment minority class data to facilitate automatic epileptic seizure detection. This study investigates the impact of various data augmentation (DA) approaches, including Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), Vanilla GAN, Conditional GAN (CGAN), and Cramer GAN, on classification performance with Random Forest models. The best-performing GAN variant, WGAN-GP, was then integrated with a bidirectional Long Short-Term Memory (LSTM) architecture and compared against traditional and synthetic oversampling methods. The evaluation of different GAN variants for data augmentation with Random Forest classifiers identified WGAN-GP as the most effective approach. The integration of WGAN-GP with bidirectional LSTM yielded substantial performance improvements, outperforming traditional oversampling methods and achieving an accuracy of 91.73% on the augmented data, compared to 86% accuracy on real data without augmentation. The proposed generative AI approach combining WGAN-GP and recurrent neural network models outperforms comparative synthetic oversampling methods on metrics relevant for reliable seizure detection from imbalanced EEG datasets. Incorporating the WGAN-GP generative AI technique for data augmentation and integrating it with bidirectional LSTM elevates seizure detection accuracy for imbalanced EEG datasets, surpassing the performance of traditional oversampling and class weight adjustment methods. This approach shows promise for improving epilepsy monitoring and management through enhanced automated detection system effectiveness.

Automatic detection of epileptic seizure based on one dimensional cascaded convolutional autoencoder with adaptive window-thresholding

Objective. Identifying the seizure occurrence period (SOP) in extended EEG recordings is crucial for neurologists to diagnose seizures effectively. However, many existing computer-aided diagnosis systems for epileptic seizure detection (ESD) primarily focus on distinguishing between ictal and interictal states in EEG recordings. This focus has limited their application in clinical settings, as these systems typically rely on supervised learning approaches that require labeled data.Approach. To address this, our study introduces an unsupervised learning framework for ESD using a 1D- cascaded convolutional autoencoder (1D-CasCAE). In this approach, EEG recordings from selected patients in the CHB-MIT datasets are first segmented into 5 s epochs. Eight informative channels are chosen based on the correlation coefficient and Shannon entropy. The 1D-CasCAE is designed to autonomously learn the characteristic patterns of interictal (non-seizure) segments through downsampling and upsampling processes. The integration of adaptive thresholding and a moving window significantly enhances the model's robustness, enabling it to accurately identify ictal segments in long EEG recordings.Main results. Experimental results demonstrate that the proposed 1D-CasCAE effectively learns normal EEG signal patterns and efficiently detects anomalies (ictal segments) using reconstruction errors. When compared with other leading methods in anomaly detection, our model exhibits superior performance, as evidenced by its average Gmean, sensitivity, specificity, precision, and false positive rate scores of 98.00% ± 3.51%, 94.94% ± 6.92%, 99.60% ± 0.30%, 79.92% ± 13.56% and 0.0044 ± 0.0030 h-1respectively for a typical patient in CHB-MIT datasets.Significance. The developed model framework can be employed in clinical settings, replacing the manual inspection process of EEG signals by neurologists. Furthermore, the proposed automated system can adapt to each patient's SOP through the use of variable time windows for seizure detection.

Automatic Detection of Epileptic Seizures from EEG Signals Using Artificial Intelligence Methods

Epilepsy is a neurological disorder in which involuntary contractions, sensory abnormalities, and changes occur as a result of abrupt and uncontrolled discharges in the neurons in the brain, which disrupt the systems regulated by the brain. In epilepsy, abnormal electrical impulses from cells in various brain areas are noticed. The accurate interpretation of these electrical impulses is critical in the illness diagnosis. This study aims to use different machine-learning algorithms to diagnose epileptic seizures. The frequency components of EEG data were extracted using parametric approaches. This feature extraction approach was fed into machine learning classification algorithms, including Artificial Neural Network (ANN), Gradient Boosting, and Random Forest. The ANN classifier was shown to have the most significant test performance in this investigation, with roughly 97% accuracy and a 91% F1 score in recognizing epileptic episodes. The Gradient Boosting classifier, on the other hand, performed similarly to the ANN, with 96% accuracy and a 93% F1 score.

Automatic detection of epileptic seizure using machine learning-based IANFIS-LightGBM system

A sudden increase in electrical activity in the brain is a defining feature of one of the severe neurological diseases known as epilepsy. This abnormality appears as a seizure, and identifying seizures is an important field of research. An essential technique for examining the features of neurological issues brain activities, and epileptic seizures is electroencephalography (EEG). In EEG data, analyzing epileptic irregularities visually requires a lot of time from neurologists. For accurate detection of epileptic seizures, numerous scientific techniques have been used with EEG data, and most of these techniques have produced promising results. For EEG signal classification with a high classification accuracy rate, the present research proposes an enhanced machine learning-based epileptic seizure detection model. The present research provides a hybrid Improved Adaptive Neuro-Fuzzy Inference System (IANFIS)-Light Gradient Boosting Machine (LightGBM) technique for automatically detecting and diagnosing epilepsy from EEG data. The experimental findings were supported by EEG records made available by the German University of Bonn and scalp EEG data acquired at Children’s Hospital Boston. The suggested IANFIS-LightGBM, according to the results, offers the most significant classification accuracy ratings in both situations.

SaE-GBLS: an effective self-adaptive evolutionary optimized graph-broad model for EEG-based automatic epileptic seizure detection.

Epilepsy is a common neurological condition that affects a large number of individuals worldwide. One of the primary challenges in epilepsy is the accurate and timely detection of seizure. Recently, the graph regularized broad learning system (GBLS) has achieved superior performance improvement with its flat structure and less time-consuming training process compared to deep neural networks. Nevertheless, the number of feature and enhancement nodes in GBLS is predetermined. These node settings are also randomly selected and remain unchanged throughout the training process. The characteristic of randomness is thus more easier to make non-optimal nodes generate, which cannot contribute significantly to solving the optimization problem. To obtain more optimal nodes for optimization and achieve superior automatic detection performance, we propose a novel broad neural network named self-adaptive evolutionary graph regularized broad learning system (SaE-GBLS). Self-adaptive evolutionary algorithm, which can construct mutation strategies in the strategy pool based on the experience of producing solutions for selecting network parameters, is incorporated into SaE-GBLS model for optimizing the node parameters. The epilepsy seizure is automatic detected by our proposed SaE-GBLS model based on three publicly available EEG datasets and one private clinical EEG dataset. The experimental results indicate that our suggested strategy has the potential to perform as well as current machine learning approaches.

Two-Stage Approach With Combination of Outlier Detection Method and Deep Learning Enhances Automatic Epileptic Seizure Detection

Two-Stage Approach With Combination of Outlier Detection Method and Deep Learning Enhances Automatic Epileptic Seizure Detection

Automatic epileptic seizure detection based on EEG using a moth-flame optimization of one-dimensional convolutional neural networks.

Frequent epileptic seizures can cause irreversible damage to the brains of patients. A potential therapeutic approach is to detect epileptic seizures early and provide artificial intervention to the patient. Currently, extracting electroencephalogram (EEG) features to detect epileptic seizures often requires tedious methods or the repeated adjustment of neural network hyperparameters, which can be time- consuming and demanding for researchers. This study proposes an automatic detection model for an EEG based on moth-flame optimization (MFO) optimized one-dimensional convolutional neural networks (1D-CNN). First, according to the characteristics and need for early epileptic seizure detection, a data augmentation method for dividing an EEG into small samples is proposed. Second, the hyperparameters are tuned based on MFO and trained for an EEG. Finally, the softmax classifier is used to output EEG classification from a small-sample and single channel. The proposed model is evaluated with the Bonn EEG dataset, which verifies the feasibility of EEG classification problems that involve up to five classes, including healthy, preictal, and ictal EEG from various brain regions and individuals. Compared with existing advanced optimization algorithms, such as particle swarm optimization, genetic algorithm, and grey wolf optimizer, the superiority of the proposed model is further verified. The proposed model can be implemented into an automatic epileptic seizure detection system to detect seizures in clinical applications.

Automatic epileptic seizure detection based on persistent homology.

Epilepsy is a prevalent brain disease, which is quite difficult-to-treat or cure. This study developed a novel automatic seizure detection method based on the persistent homology method. In this study, a Vietoris-Rips (VR) complex filtration model was constructed based on the EEG data. And the persistent homology method was applied to calculate the VR complex filtration barcodes to describe the topological changes of EEG recordings. Afterward, the barcodes as the topological characteristics of EEG signals were fed into the GoogLeNet for classification. The persistent homology is applicable for multi-channel EEG data analysis, where the global topological information is calculated and the features are extracted by considering the multi-channel EEG data as a whole, without the multiple calculations or the post-stitching. Three databases were used to evaluate the proposed approach and the results showed that the approach had high performances in the epilepsy detection. The results obtained from the CHB-MIT Database recordings revealed that the proposed approach can achieve a segment-based averaged accuracy, sensitivity and specificity values of 97.05%, 96.71% and 97.38%, and achieve an event-based averaged sensitivity value of 100% with 1.22s average detection latency. In addition, on the Siena Scalp Database, the proposed method yields averaged accuracy, sensitivity and specificity values of 96.42%, 95.23% and 97.6%. Multiple tasks of the Bonn Database also showed achieved accuracy of 99.55%, 98.63%, 98.28% and 97.68%, respectively. The experimental results on these three EEG databases illustrate the efficiency and robustness of our approach for automatic detection of epileptic seizure.

Retracted: Automatic Detection and Classification of Epileptic Seizures in Patients with Liver Cirrhosis and Overlapping Hev Infection Based on Deep Multimodal Fusion Technology

Retracted: Automatic Detection and Classification of Epileptic Seizures in Patients with Liver Cirrhosis and Overlapping Hev Infection Based on Deep Multimodal Fusion Technology

Power and Area Optimized Deep Learning Framework for Accurate Automatic Epileptic Seizure Detection

Power and Area Optimized Deep Learning Framework for Accurate Automatic Epileptic Seizure Detection

Cross-patient automatic epileptic seizure detection using patient-adversarial neural networks with spatio-temporal EEG augmentation

Cross-patient automatic epileptic seizure detection through electroencephalogram (EEG) is significant for clinical application and research. However, most automatic seizure detection methods are patient-specific and have poor generalization ability to unseen patients. In this paper, we consider two aspects for solving the cross-patient generalization problem in deep learning approaches. Firstly, we propose a new data augmentation method to largely improve generalization. We analyze the statistical distribution of seizure EEG signals and propose spatio-temporal EEG augmentation (STEA) to generate synthetic training seizure data with spatio-temporal dependencies in EEG. Secondly, we propose patient-adversarial neural network (PANN) to learn a patient-invariant representation for better generalization. We add a discriminator to distinguish the identity of patients and perform adversarial optimization between the feature extractor and identity discriminator, so that only shared seizure features are maintained. We conduct experiments on both public and clinical EEG datasets with various settings of different window lengths and divisions of training and testing sets. Our model significantly improves the performance of cross-patient detection compared with other methods and achieves state-of-the-art performance. Particularly, our proposed method achieves up to 95% sensitivity on CHB-MIT under 5 s window length segments, and achieves about 85% AUC and sensitivity even on the clinical dataset. Our designed methods can enable detection models extended to unseen patients, with performance achieving the clinical application standards.

Automatic epileptic seizure detection using MSA-DCNN and LSTM techniques with EEG signals

To identify epilepsy, Electroencephalography (EEG) is an important and common tool used to study the electrical activity of the human brain. The machine learning-based classifier is utilized to detect the seizure by manually extracting the features from the EEG signals in previous works. Though, these effective benefits have been proved already with automatic feature extraction, they are unable to achieve the classification of multiple classes. Meanwhile, real-time epileptic seizure detection is unable to keep the capacity because the identifiable EGG is too long. Hence, this paper is decided to develop an enhanced deep learning architecture with EEG signal for performing automatic epileptic seizure detection. The EEG signal is collected from the standard datasets. The Fourier-Bessel Series Expansion-Based Empirical Wavelet Transform (FBSE-EWT) method is used to decompose the signal from the gathered data. In feature extraction, the decomposed signals are used and while extracting the signal features, the autoencoder is involved in that process. To reduce the computational overload, the relief-F feature ranking method is used for choosing the important signal features. The Long Short Term Memory (LSTM) and Multi-Scale Atrous-based Deep Convolutional Neural Networks (MSA-DCNN) are used that is named as Hybrid Deep Scheme (HDS) to detect epileptic seizures with the top-ranked features for epileptic seizure classification. The Black Widow Optimization (BWO) and the Spider Monkey Optimization (SMO) are combined to generate Adaptive Spider Monkey Black Widow Optimization (ASMBWO) that is employed to perform the parameter tuning into a classification technique. Using different measures, the experimental analysis is done between the conventional epileptic seizure detection and the proposed model to establish an enhanced performance of the proposed model.

Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach.

Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the non-overlapping window technique, which we tested on the TUSZ dataset. The system accurately detects seizure episodes (87.7% Sn, 91.16% Sp) and carefully distinguishes eight seizure types (95-100% Acc). An increase in EEG sampling rate from 50 to 250 Hz boosted model performance: the precision of seizure detection rose by 5%, and seizure differentiation by 7%. A low sampling rate is a reasonable solution for training reliable models with EEG data. Decreasing the number of EEG electrodes from 21 to 8 did not affect seizure detection but worsened seizure differentiation significantly: 98.24 ± 0.17 vs. 85.14 ± 3.14% recall. In detecting epileptic episodes, all electrodes provided equally informative input, but in seizure differentiation, their informative value varied. We improved model explainability with interpretable ML. Activation maximization highlighted the presence of EEG patterns specific to eight seizure types. Cortical projection of epileptic sources depicted differences between generalized and focal seizures. Interpretable ML techniques confirmed that our system recognizes biologically meaningful features as indicators of epileptic activity in EEG.

Epileptic seizure detection from electroencephalogram (EEG) signals using linear graph convolutional network and DenseNet based hybrid framework

A clinical condition known as epilepsy occurs when the brain's regular electrical activity is disturbed, resulting in a rapid, aberrant, and excessive discharge of brain neurons. The electroencephalogram (EEG) signal is the measurement of electrical activity received from the nerve cells of the cerebral cortex to make precise diagnoses of disorders, which is made crucial attention for treating epilepsy patients in recent years. The concentration on grid-like data has been a significant drawback of existing deep learning-based automatic epileptic seizure detection algorithms from raw EEG signals; nevertheless, physiological recordings frequently have irregular and unordered structures, making it challenging to think of them as a matrix. In order to take advantage of the implicit information that exists in seizure detection, graph neural networks have received a lot of attention. These networks feature interacting nodes connected by edges whose weights can be either dictated by temporal correlations or anatomical junctions. To address this limitation, a novel hybrid framework is proposed for epileptic seizure detection by using linear graph convolution neural network (LGCN) and DenseNet. When compared to previous deep learning networks, DenseNet achieves the model's higher computational accuracy and memory efficiency by reducing the vanishing gradient problem and enhancing feature propagation in each of its layers. The Stockwell transform (S-transform) is used to preprocess from the raw EEG signal and then group the resulting matrix into time-frequency blocks as inputs for the LGCN to use for feature selection and after the Densenet uses for classification. The proposed hybrid framework outperforms the state-of-the-art in seizure detection tasks, achieving 98% accuracy and 98.60% specificity in extensive experiments on the publicly available CHB-MIT EEG dataset.

Barnes–Hut approximation based accelerating t-SNE for seizure detection

Background:Automatic detection of epileptic seizures is critical in the paradigm of epilepsy diagnosis and in relieving the cumbersome visual inspection of electroencephalogram (EEG) recordings. A speedy algorithm could help in more reliable monitoring and detection of seizures. Methods and materials:In this study, we aim to provide an EEG-based seizure detection system with computational efficiency and improved performance. In the proposed work, many features including temporal, spectral, and non-linear features from each intrinsic mode function (IMF) of empirical mode decomposition (EMD) have been used. Barnes–Hut approximation-based t-stochastic neighborhood embedding (bh t-SNE) was explored for the first time to observe the reduction in computational time (CT) period in the automatic seizure detection system. Three classes of widely-used EEG Bonn datasets were used to assess the performance of the proposed method. Results:The proposed Barnes–Hut-based accelerating t-SNE along with SVM and KNN reduced more than half of the classification time with the same accuracy. The classifier takes 2.147±0.1 s for SVM and 1.216±0.1 s for KNN without the proposed t-SNE and 1.31±0.1 s for SVM and 0.736±0.1 s for KNN (at the trade-off parameter θ=0.5) with the proposed Barnes–hut based t-SNE (bh t-SNE) at an accuracy of 100%. Conclusions: The findings of the experimental work indicate that the proposed method is effective in reducing the computational time while maintaining the required efficacy. As a result, the inclusion of these algorithms in hardware might prove to be effective in assisting neurologists in detecting seizures.

An automated epileptic seizure detection using optimized neural network from EEG signals

AbstractAmong the central nervous system (neurological) disorders, epilepsy is considered to be a dangerous and chronic disorder that causes recurring seizures, showing unusual behaviour for some period of time, shaking of hands and legs, loss of sensation and awareness. It occurs when electrical activities in the brain become abnormal. The test performed in order to detect epileptic seizures is known as electroencephalograph (EEG) signal test which is conducted by analysing the electrical impulses in the brain. The manual identification process of EEG brain signals is time consuming and a laborious task. So the neurologists may sometimes give a varying result which may affect the performance of detecting epileptic seizures. The combination of manual identification of the signal and machine learning technique will be able to provide a correct result in a confusion situation reducing analytic and therapeutic errors that are unavoidable in human clinical practice. The existing approaches of detection of epileptic seizures cannot correctly train their network if the size of the dataset is very large thus obtaining lower classification accuracy. An optimized neural network technique is proposed in this work for automatic detection of Epileptic seizure using EEG signals of the brain. The EEG signals are used for feature extraction by applying Discrete Wavelet Transform (DWT). Using the extracted features, input samples are created and then fed to a hybrid model which is a combination of self‐organizing neural network (SONN) and multilayer perceptron (MLP) trained with a genetic algorithm (GA). This model acts as a classifier for detecting Epileptic seizures by classifying the samples into two classes namely Non‐Epileptic and Epileptic class. Clustering is performed first for the large dataset samples using SONN and for each cluster, an MLP‐GA network is used to train the samples belonging to the same cluster. Performing clustering helps to correctly train the MLP networks for obtaining high classification accuracy. GA has been specifically chosen as a learning algorithm instead of Backpropagation (BP) algorithm for MLP because GA can find the global minima thus solving the local minima problem faced by BP algorithm. The performance measures are evaluated thereby achieving precision value of 98%, recall value of 100%, F1 score value of 98.99% and an overall accuracy of 99.2%. The proposed hybrid method using SONN and MLP‐GA has more potential to classify the EEG signals.

Fed-ESD: Federated learning for efficient epileptic seizure detection in the fog-assisted internet of medical things

Epilepsy is a predominant paroxysmal neurological disturbance that is usually recognized as the incidence of impulsive seizures rarely seen in medicine. Automatic detection of epileptic seizures from electroencephalogram (EEG) signals is viewed as an effective diagnosis of patients on the Internet of Medical Things (IoMT). To design a robust detection service in an IoMT environment, the EEG signals of different patients are collected from geographically distributed patients to a centralized server. However, this makes the patient’s privacy prone to exposure and adds to the energy and communication costs. Also, the central server can be subject to malevolent attacks, resulting in non-efficient solutions. In this regard, for the first time, this paper presents a privacy-preserving federated learning framework for epileptic seizure detection (called Fed-ESD) from EEG signals in the fog-computing-based IoMT. A lightweight and efficient spatiotemporal transformer network is introduced to collaboratively learn spatial and temporal representations from the local data of each participant. The proposed Fed-ESD employs geographically situated fog nodes as local aggregators to enable sharing of location-based EEG signals for comparable IoMT applications. Moreover, a greedy method is introduced for deciding on the ideal fog node to be the coordinator node responsible for global aggregation during the training, thereby decreasing the reliance on the central server in the IoMT. Experimental evaluations demonstrate the efficiency of the proposed Fed-ESD in terms of detection performance, resource-efficiency, stability, and scalability for deployment in the IoMT.

EpilepIndex: A novel feature engineering tool to detect epilepsy using EEG signals.

Epilepsy is a common neurological disease characterized by seizures. A person with a seizure onset can lose consciousness which in turn can lead to fatal accidents. Electroencephalogram (EEG) is a recording of the electrical signals from the brain which is used to analyse the epileptic seizures. Physical visual examination of the EEG by trained neurologists is subjective and highly difficult due to the non-linear complex nature of the EEG. This opens a window for automatic detection of epileptic seizures using machine learning methods. In this work, we have used a standard database that consists of five different sets of EEG data including the epileptic EEG. Using this data, we have devised a novel 22 possible clinically significant cases with the combination of binary and multi class type of classification problem to automatically classify epileptic EEG. As the EEG is non-linear, we have devised 11 statistically significant non-linear entropy features to extract from this database. These features are fed to 10 different classifiers of various types for each of the 22 clinically significant cases and their classification accuracy is reported for 10-fold cross validation. Random Forest and Optimized Forest classifiers reported accuracies above 90% for all 22 cases considered in this study. Such vast possible clinically significant 22 cases from the combination of the data from the database considered has not been in the literature with the best of the knowledge of the authors. Comparing with the literature, several studies have presented one or few combinations of these 22 cases in this work. In comparison to similar works, the accuracies obtained by the classifiers were highly competitive. In addition, a novel integrated epilepsy detection index named EpilepIndex (IED) is able to differentiate between epileptic EEG and a normal EEG with 100% accuracy.

Automatic detection method of epileptic seizures based on IRCMDE and PSO-SVM.

Multi-scale dispersion entropy (MDE) has been widely used to extract nonlinear features of electroencephalography (EEG) signals and realize automatic detection of epileptic seizures. However, information loss and poor robustness will exist when MDE is used to measure the nonlinear complexity of the time sequence. To solve the above problems, an automatic detection method for epilepsy was proposed, based on improved refined composite multi-scale dispersion entropy (IRCMDE) and particle swarm algorithm optimization support vector machine (PSO-SVM). First, the refined composite multi-scale dispersion entropy (RCMDE) is introduced, and then the segmented average calculation of coarse-grained sequence is replaced by local maximum calculation to solve the problem of information loss. Finally, the entropy value is normalized to improve the robustness of characteristic parameters, and IRCMDE is formed. The simulated results show that when examining the complexity of the simulated signal, IRCMDE can eliminate the issue of information loss compared with MDE and RCMDE and weaken the entropy change caused by different parameter selections. In addition, IRCMDE is used as the feature parameter of the epileptic EEG signal, and PSO-SVM is used to identify the feature parameters. Compared with MDE-PSO-SVM, and RCMDE-PSO-SVM methods, IRCMDE-PSO-SVM can obtain more accurate recognition results.