Seizure Detection System Research Articles

Epileptic Seizure Detection Using Brain-Rhythmic Recurrence Biomarkers and ONASNet-Based Transfer Learning.

The electroencephalogram (EEG) tool has great potential for real-time monitoring of abnormal brain activities, such as preictal and ictal seizures. Developing an EEG-based detection system for patients with epilepsy is vital for clinical management and targeted therapy. This paper proposes a single-channel seizure detection system using brain-rhythmic recurrence biomarkers (BRRM) and an optimized model (ONASNet). BRRM is a direct mapping of the recurrence morphology of brain rhythms in phase space; it reflects the nonlinear dynamics of original EEG signals. The architecture of ONASNet is determined through a modified neural network searching strategy. Then, we exploited transfer learning to apply ONASNet to our EEG data. The combination of BRRM and ONASNet leverages the multiple channels of a neural network to extract features from different brain rhythms simultaneously. We evaluated the efficiency of BRRM-ONASNet on the real EEG recordings derived from Bonn University. In the experiments, different transfer-learning models (TLMs) are respectively constructed using ONASNet and seven well-known neural network structures (VGG16/VGG19/ResNet50/InceptionV3/DenseNet121/Xception/NASNet). Moreover, we compared those TLMs by model size, computing complexity, learning capability, and prediction latency. ONASNet outperforms other structures by strong learning capability, high stability, small model size, short latency, and less requirement of computing resources. Comparing BRRM-ONASNet with other existing methods, our work performs better than others with 100% accuracy under the identical dataset and same detection task. Contributions: The proposed method in this study, analyzing nonlinear features from phase-space representations using a deep neural network, provides new insights for EEG decoding. The successful application of this method in epileptic-seizure detection contributes to computationally medical assistance for epilepsy.

Peri‐ictal and non‐seizure EEG event detection using generated metadata

AbstractLack of open access, seizure specific database has hindered the development of Automated Seizure Detection System (ASDS) along with state‐of‐the‐art feature selection and classification methods. Available databases contain noise, artefacts, different length & time EEG segments, associated comorbidities, clinical settings, and epilepsy/seizure types etc. Pre‐processing of such continuous EEG segments requires significant amount of time and may feed redundant information (with reference to a seizure event) to the classification model leading to inaccurate, real‐time seizure event detection systems. Hence, this paper proposes a metadata generation of large EEG databases (here, CHB‐MIT EEG scalp database v.1.0.0) for ASDS. We elucidate the need to generate seizure sensitive data through peri‐ictal and non‐seizure EEG segments. This paper performs multi‐variate analysis and two class (non‐seizure and seizure event) classification between these fixed length and time EEG segments from support vector machine (SVM) and k‐NN classifier. We thoroughly analysed the variation and dependence of different kernels, cost function, gamma, and degree for SVM based pipeline. The proposed pipeline has been compared with state‐of‐the‐art pipelines and has achieved good classification score. Such methods will help in development of generalised approach toward handling large EEG databases and machine learning applications for seizure detection and prediction.

An Approach to Understand Epilepsy and The Role of EEG in Its Diagnosis

Epilepsy is one of the most prevalent and debilitating neurological diseases yet there is a limited understanding of its psychophysiology and because of which its detection as well as treatment is delayed. The present article reviews the neurology and psychophysiology behind epilepsy and epileptic seizure and the role of electroencephalography (EEG) in the diagnosis of the same. The advantages and disadvantages of electroencephalography (EEG) in the diagnosis are discussed in length in this paper. The major drawback in the treatment or field of epilepsy is the criticality of the early detection of epilepsy and epileptic seizure. The article highlights the need of developing automated diagnostic system for epilepsy and seizure detection for patients as well as clinicians.

Multi-Level Optimization of an Ultra-Low Power BrainWave System for Non-Convulsive Seizure Detection.

We present a systematic evaluation and optimization of a complex bio-medical signal processing application on the BrainWave prototype system, targeted towards ambulatory EEG monitoring within a tiny power budget of 1 mW. The considered BrainWave processor is completely programmable, while maintaining energy-efficiency by means of a Coarse-Grained Reconfigurable Array (CGRA). This is demonstrated through the mapping and evaluation of a state-of-the-art non-convulsive epileptic seizure detection algorithm, while ensuring real-time operation and seizure detection accuracy. Exploiting the CGRA leads to an energy reduction of 73.1%, compared to a highly tuned software implementation (SW-only). A total of 9 complex kernels were benchmarked on the CGRA, resulting in an average 4.7 × speedup and average 4.4 × energy savings over highly tuned SW-only implementations. The BrainWave processor is implemented in 28-nm FDSOI technology with 80 kB of Foundry-provided SRAM. By exploiting near-threshold computing for the logic and voltage-stacking to minimize on-chip voltage-conversion overhead, additional 15.2% and 19.5% energy savings are obtained, respectively. At the Minimum-Energy-Point (MEP) (223 μW, 8 MHz) we report a measured state-of-the-art 90.6% system conversion efficiency, while executing the epileptic seizure detection in real-time.

Automatic detection of epileptiform potentials and seizures in the EEG

Automatic computer-based algorithms for the detection of epileptiform potentials and seizure patterns on EEG facilitate a time-saving, objective method of quantitative EEG interpretation which is available 7/24. For the automatic detection of interictal epileptiform potentials sensitivities range from 65 to 99% with false positive detections of 0,09 to 13,4 per minute. Recent studies documented equal or even better performance of automatic spike detection programs compared with experienced human EEG readers. The seizure detection problem-one of the major problems in clinical epileptology-consists of the fact that the majority of focal onset seizures with impaired awareness and of seizures arising out of sleep occur unnoticed by patients and their caregivers. Automatic seizure detection systems could facilitate objective seizure documentation and thus help to solve the seizure detection problem. Furthermore, seizure detection systems may help to prevent seizure-related injuries and sudden unexpected death in epilepsy (SUDEP), and could be an integral part of novel, seizure-triggered on-demand therapies in epilepsy. During long-term video-EEG monitoring seizure detection systems could improve patient safety, provide a time-saving objective and reproducible analysis of seizure patterns and facilitate automatic computer-based patient testing during seizures. Sensitivities of seizure detection systems range from 75 to 90% with extratemporal seizures being more difficult to detect than temporal seizures. The false positive alarm rate ranges from 0,1 to 5 per 24 hours. Finally, machine learning algorithms, especially deep learning approaches, open a new highly promising era in automatic spike and seizure detection.

Hybrid Fluoroscopic and Neurophysiological Targeting of Responsive Neurostimulation of the Rolandic Cortex.

Precise targeting of cortical surface electrodes to epileptogenic regions defined by anatomic and electrophysiological guideposts remains a surgical challenge during implantation of responsive neurostimulation (RNS) devices. To describe a hybrid fluoroscopic and neurophysiological technique for targeting of subdural cortical surface electrodes to anatomic regions with limited direct visualization, such as the interhemispheric fissure. Intraoperative two-dimensional (2D) fluoroscopy was used to colocalize and align an electrode for permanent device implantation with a temporary in Situ electrode placed for extraoperative seizure mapping. Intraoperative phase reversal mapping technique was performed to distinguish primary somatosensory and motor cortex. We applied these techniques to optimize placement of an interhemispheric strip electrode connected to a responsive neurostimulator system for detection and treatment of seizures arising from a large perirolandic cortical malformation. Intraoperative neuromonitoring (IONM) phase reversal technique facilitated neuroanatomic mapping and electrode placement. In challenging-to-access anatomic regions, fluoroscopy and intraoperative neurophysiology can be employed to augment targeting of neuromodulation electrodes to the site of seizure onset zone or specific neurophysiological biomarkers of clinical interest while minimizing brain retraction.

Automatic epileptic seizure detection approach based on multi-stage Quantized Kernel Least Mean Square filters

Epilepsy is one of the most common neurological disorders of the brain all over the world. For its detection, Electroencephalogram (EEG) is an important noninvasive diagnostic approach. This paper proposes a new automated real-time approach for EEG epileptic seizure detection based on serial concatenation of Quantized Kernel Least Mean Square (QKLMS) adaptive filters. The QKLMS filter is employed in the proposed system to achieve accurate real-time diagnosis with low hardware complexity. In the proposed serial concatenation filter design, the energy of prediction signal is investigated to detect the seizure interval on the EEG records and to classify healthy, epileptic inter-ictal, and epileptic ictal cases. The Grey Wolf Optimizer (GWO) algorithm is employed to find the optimum values of the energy threshold and the parameters of the QKLMS algorithm. The performance of the proposed QKLMS technique is compared with other adaptive filters, and the results reveal the superior performance of the QKLMS algorithm. The proposed system is examined with real EEG records taken from the Bonn University database, and the experimental results show that the proposed epileptic seizure detection system outperforms other state-of-the-art systems with an accuracy of 97.88 %, sensitivity of 98.80 %, specificity of 97.65 %, and computational time of 0.58 sec. This demonstrates that the proposed approach can be used to assist neurologists in enhancing the accuracy of epileptic seizure detection and speeding-up the diagnosis process without the need for visual inspection or analysis of a large volume of EEG data.

A channel independent generalized seizure detection method for pediatric epileptic seizures

Background and objectiveEpilepsy the disorder of the central nervous system has its worldwide presence in roughly 50 million people as estimated by the World Health Organization. Electroencephalogram (EEG) is one of the most common and non-invasive ways of analyzing and studying the subtle changes in neuronal activity of the brain during an epileptic seizure attack. These changes can be analyzed for developing an automated system that would assert the chances of an impending seizure. As changeable nature of seizure affects the patients from having a normal life, hence progress in developing new methods will improve the quality of life and also provide assistance in the medical sector. Objective of the proposed method is to avoid EEG channel selection and use all input EEG channel features to design a generalized epileptic seizure detection framework. MethodIn this work, a long short-term memory network has been proposed that is not complex and has the capability of effectively detecting epileptic seizures from both non-invasive and invasive electroencephalogram recordings. The proposed framework is simple and effective and designed in such capacity that raw electroencephalogram signals can be used to detect seizures. Also, a generalized approach has been followed that is channel independent such that EEG signals belonging to any hemisphere of the brain can be detected effectively by the proposed architecture. ResultsThe automated seizure detection system achieved high seizure detection sensitivity of 99.9%, and a low false-positive rate of 0.003 per hour for the Children's Hospital Boston-Massachusetts Institute of Technology dataset. While for the Sleep-Wake-Epilepsy-Center of the University Department of Neurology at the Inselspital Bern dataset, the sensitivity is 99.4% and false-positive rate of 0.006 per hour. Convergence analysis of the proposed model provides a significant amount of reliability and correctness in the efficient detection of epileptic seizures. ConclusionAssessment of the proposed framework on non-invasive as well as invasive EEG signals showed that the framework worked well for different type of EEG recordings as different metrics gave satisfactory results. As the framework is simple and did not require any additional parameter optimization techniques, it reduced the processing overheads without affecting the accuracy. Hence, it can be used as an efficient method for monitoring epileptic seizures.

A computationally efficient automated seizure detection method based on the novel idea of multiscale spectral features

In this work, we propose a novel feature extraction scheme called multiscale spectral features (MSSFs) for the design of an automated seizure detection system. The MSSFs are derived from multiscale power spectral density (MSPSD) of electroencephalogram (EEG) signals that characterize seizure activities. Firstly, three MSSFs are computed from MSPSD of EEG segments. Subsequently, Kruskal-Wallis test is conducted to verify the class discrimination abilities of the proposed MSSFs, and then extracted features are given to Random Forest (RF) classifier for the categorization of EEG segments. The performance of RF classifier is assessed on three benchmark EEG databases. We also evaluate the computational time required for MSSFs extraction from an EEG segment and compare it with the computational time required by the existing methodologies based on spectral features. We achieved promising classification performances in comparison with state-of-the-art seizure detection models. Besides, our proposed seizure detection system required only 0.01965 s to extract features from an EEG segment and to identify its class. The reduced computational time in comparison with related works manifest the supremacy of our proposed methodology. Furthermore, the MSSFs are implemented on Zynq UltraScale + MPSoC ZCU102 to exhibit the real-time seizure detection capabilities of the proposed method. The implementation results manifest that the proposed methodology can be incorporated as a portable seizure control device. Hence, this work may pave the way for the development of seizure detection algorithms that have high detection rates, reduced computational complexity and are hardware-friendly as well.

Artificial Intelligence in Epilepsy.

The study of seizure patterns in electroencephalography (EEG) requires several years of intensive training. In addition, inadequate training and human error may lead to misinterpretation and incorrect diagnosis. Artificial intelligence (AI)-based automated seizure detection systems hold an exciting potential to create paradigms for proper diagnosis and interpretation. AI holds the promise to transform healthcare into a system where machines and humans can work together to provide an accurate, timely diagnosis, and treatment to the patients. This article presents a brief overview of research on the use of AI systems for pattern recognition in EEG for clinical diagnosis. The article begins with the need for understanding nonstationary signals such as EEG and simplifying their complexity for accurate pattern recognition in medical diagnosis. It also explains the core concepts of AI, machine learning (ML), and deep learning (DL) methods. In this present context of epilepsy diagnosis, AI may work in two ways; first by creating visual representations (e.g., color-coded paradigms), which allow persons with limited training to make a diagnosis. The second is by directly explaining a complete automated analysis, which of course requires more complex paradigms than the previous one. We also clarify that AI is not about replacing doctors and strongly emphasize the need for domain knowledge in building robust AI models that can work in real-time scenarios rendering good detection accuracy in a minimum amount of time.

Very large scale integration implementation of seizure detection system with on‐chip support vector machine classifier

Very large scale integration implementation of seizure detection system with on‐chip support vector machine classifier

Seizure Detection Based on EEG Signals Using Asymmetrical Back Propagation Neural Network Method

Abnormal activity in the human brain is a symptom of epilepsy. Electroencephalogram (EEG) is a standard tool that has been widely used to detect seizures. A number of automated seizure detection systems based on EEG signal classification have been employed in present days, which includes a mixture of approaches but most of them rely on time signal features, time intervals or time frequency domains. Therefore, in this research, deep learning-based automated mechanism is introduced to improve the seizure detection accuracy from EEG signal using the Asymmetrical Back Propagation Neural Network (ABPN) method. The ABPN system includes four levels of repetitive training with weight adjustment, feed forward initialization, error and update weight and bias back-propagation. The proposed ABPN-based seizure detection system is validated using Physionet EEG dataset with matlab simulation, and the effectiveness of proposed seizure system is confirmed through simulation results. As compared with Deep Convolutional Neural Network (CNN) and Support Vector Machine–Particle Swarm Optimization (SVM-PSO)-based seizure detection system, the proposed ABPN system gives the best performance against various parameters. The sensitivity, specificity and accuracy are 96.32%, 95.12% and 98.36%, respectively.

Evaluation of artificial intelligence systems for assisting neurologists with fast and accurate annotations of scalp electroencephalography data

BackgroundAssistive automatic seizure detection can empower human annotators to shorten patient monitoring data review times. We present a proof-of-concept for a seizure detection system that is sensitive, automated, patient-specific, and tunable to maximise sensitivity while minimizing human annotation times. The system uses custom data preparation methods, deep learning analytics and electroencephalography (EEG) data. MethodsScalp EEG data of 365 patients containing 171,745 s ictal and 2,185,864 s interictal samples obtained from clinical monitoring systems were analysed as part of a crowdsourced artificial intelligence (AI) challenge. Participants were tasked to develop an ictal/interictal classifier with high sensitivity and low false alarm rates. We built a challenge platform that prevented participants from downloading or directly accessing the data while allowing crowdsourced model development. FindingsThe automatic detection system achieved tunable sensitivities between 75.00% and 91.60% allowing a reduction in the amount of raw EEG data to be reviewed by a human annotator by factors between 142x, and 22x respectively. The algorithm enables instantaneous reviewer-managed optimization of the balance between sensitivity and the amount of raw EEG data to be reviewed. InterpretationThis study demonstrates the utility of deep learning for patient-specific seizure detection in EEG data. Furthermore, deep learning in combination with a human reviewer can provide the basis for an assistive data labelling system lowering the time of manual review while maintaining human expert annotation performance. FundingIBM employed all IBM Research authors. Temple University employed all Temple University authors. The Icahn School of Medicine at Mount Sinai employed Eren Ahsen. The corresponding authors Stefan Harrer and Gustavo Stolovitzky declare that they had full access to all the data in the study and that they had final responsibility for the decision to submit for publication.

A novel automated seizure detection system from EMD-MSPCA denoised EEG: Refined composite multiscale sample, fuzzy and permutation entropies based scheme

This paper investigates three complexity measures namely, refined composite multiscale sample entropy (RCMSE), refined composite multiscale fuzzy entropy (RCMFE), and refined composite multiscale permutation entropy (RCMPE) as features for the automated detection of epileptic seizures from electroencephalograms (EEGs). Generally, the EEG signals contain unwanted frequency components and superimposed trends that may influence their complexity evaluation. Therefore, we propose a denoising technique based on empirical mode decomposition (EMD) and multiscale principal component analysis (MSPCA) called EMD-MSPCA, and explore its impact on the performance of RCMSE, RCMFE, and RCMPE features for seizure diagnosis. Additionally, we put forward a novel automated seizure detection methodology based on EMD-MSPCA denoised EEG and combined RCMSE, RCMFE, and RCMPE features to characterize healthy, seizure-free, and seizure EEG signals. The experimental results demonstrate that all the three entropy features can successfully characterize the abnormal dynamics related to epileptic EEG signals with RCMPE being the best feature; applying the proposed EMD-MSPCA denoising technique prior to feature extraction using RCMSE, RCMFE and, RCMPE not only improved the performances of various classifiers but also reduced the computational time of these three entropy features significantly; and the proposed seizure detection scheme yielded good classification accuracies on two widely used EEG databases as compared to state-of-the-art works, hence emerges as a robust model for automated detection of epileptic seizures.

Signal Dynamics Analysis for Epileptic Seizure Classification on EEG Signals

Epilepsy is the most common form of neurological disease. Patients with epilepsy may experience seizures of a certain duration with or without provocation. Epilepsy analysis can be done with an electroencephalogram (EEG) examination. Observation of qualitative EEG signals generates high cost and often confuses due to the nature of the non-linear EEG signal and noise. In this study, we proposed an EEG signal processing system for EEG seizure detection. The signal dynamics approach to normal and seizure signals' characterization became the main focus of this study. Spectral Entropy (SpecEn) and fractal analysis are used to estimate the EEG signal dynamics and used as feature sets. The proposed method is validated using a public EEG dataset, which included preictal, ictal, and interictal stages using the Naïve Bayes classifier. The test results showed that the proposed method is able to generate an ictal detection accuracy of up to 100%. It is hoped that the proposed method can be considered in the detection of seizure signals on the long-term EEG recording. Thus it can simplify the diagnosis of epilepsy.

A patient-independent classification system for onset detection of seizures.

Seizures are the most common brain dysfunction. Electroencephalography (EEG) is required for their detection and treatment initially. Studies show that if seizures are detected at their early stage, instant and effective treatment can be given to the patients. In this paper, an automated system for seizure onset detection is proposed. As the power spectrum of normal person's EEG and EEG of someone with epilepsy is plotted, powers present at different frequencies are found to be different for both. The proposed algorithm utilizes this frequency discrimination property of EEG with some statistical features to detect the seizure onset using simple linear classifier. The tests conducted on EEG data of 30 patients, obtained from the two different datasets, show the presence of all 183 seizures with mean latency of 0.9s and 1.02 false detections per hour. The main contribution of this study is the use of simple features and classifier in the field of seizures onset detection that reduces the computational complexity of the algorithm. Also, the classifier used is patient independent. This patient independency in the classification system would be helpful in the implementation of the proposed algorithm to develop an online detection system.

Video-Based Detection of Generalized Tonic-Clonic Seizures Using Deep Learning

Timely detection of seizures is crucial to implement optimal interventions, and may help reduce the risk of sudden unexpected death in epilepsy (SUDEP) in patients with generalized tonic-clonic seizures (GTCSs). While video-based automated seizure detection systems may be able to provide seizure alarms in both in-hospital and at-home settings, earlier studies have primarily employed hand-designed features for such a task. In contrast, deep learning-based approaches do not rely on prior feature selection and have demonstrated outstanding performance in many data classification tasks. Despite these advantages, neural network-based video classification has rarely been attempted for seizure detection. We here assessed the feasibility and efficacy of automated GTCSs detection from videos using deep learning. We retrospectively identified 76 GTCS videos from 37 participants who underwent long-term video-EEG monitoring (LTM) along with interictal video data from the same patients, and 10 full-night seizure-free recordings from additional patients. Using a leave-one-subject-out cross-validation approach (LOSO-CV), we evaluated the performance to detect seizures based on individual video frames (convolutional neural networks, CNNs) or video sequences [CNN+long short-term memory (LSTM) networks]. CNN+LSTM networks based on video sequences outperformed GTCS detection based on individual frames yielding a mean sensitivity of 88% and mean specificity of 92% across patients. The average detection latency after presumed clinical seizure onset was 22 seconds. Detection performance increased as a function of training dataset size. Collectively, we demonstrated that automated video-based GTCS detection with deep learning is feasible and efficacious. Deep learning-based methods may be able to overcome some limitations associated with traditional approaches using hand-crafted features, serve as a benchmark for future methods and analyses, and improve further with larger datasets.

A new design of real-time monitoring and spectral analysis of EEG and ECG signals for epileptic seizure detection

The evolution of telecommunications technology has made significant contributions and advances in medical technology. Most of the time, monitoring and evaluation require the use of more than two signals simultaneously recorded. Simultaneous monitoring of the electrocardiogram (ECG) and the electroencephalogram (EEG) is very useful to have information about general state of health of the patient. In this paper, a novel mono-channel wireless ECG and EEG system for epileptic seizure detection is presented. The system employs analogue circuits to acquisition, processing and spectral analysis of ECG and EEG signals simultaneously. Arduino platform is used to digitise and spectral analysis of signals. A 128×64 graphic LCD display module and a Bluetooth module are also used for plotting and transmission of signals. We also propose the magnitude squared coherence (MSC) as an important parameter to calculate in frequency domain the relationship between ECG and EEG signals and use it as a relevant discriminator in seizures and the epilepsies classification.

Automatic Detection of Epileptic Seizures in Neonatal Intensive Care Units Through EEG, ECG and Video Recordings: A Survey

In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is of utmost importance for a timely, effective and efficient clinical intervention. The continuous video electroencephalogram (v-EEG) is the gold standard for monitoring neonatal seizures, but it requires specialized equipment and expert staff available 24/24h. The purpose of this study is to present an overview of the main Neonatal Seizure Detection (NSD) systems developed during the last ten years that implement Artificial Intelligence techniques to detect and report the temporal occurrence of neonatal seizures. Expert systems based on the analysis of EEG, ECG and video recordings are investigated, and their usefulness as support tools for the medical staff in detecting and diagnosing neonatal seizures in NICUs is evaluated. EEG-based NSD systems show better performance than systems based on other signals. Recently ECG analysis, particularly the related HRV analysis, seems to be a promising marker of brain damage. Moreover, video analysis could be helpful to identify inconspicuous but pathological movements. This study highlights possible future developments of the NSD systems: a multimodal approach that exploits and combines the results of the EEG, ECG and video approaches and a system able to automatically characterize etiologies might provide additional support to clinicians in seizures diagnosis.

Hardware Acceleration of High Sensitivity Power-Aware Epileptic Seizure Detection System Using Dynamic Partial Reconfiguration

In this paper, a high-sensitivity low-cost power-aware Support Vector Machine (SVM) training and classification based system, is hardware implemented for a neural seizure detection application. The training accelerator algorithm, adopted in this work, is the sequential minimal optimization (SMO). System blocks are implemented to achieve the best trade-off between sensitivity and the consumption of area and power. The proposed seizure detection system achieves 98.38% sensitivity when tested with the implemented linear kernel classifier. The system is implemented on different platforms: such as Field Programmable Gate Array (FPGA) Xilinx Virtex-7 board and Application Specific Integrated Circuit (ASIC) using hardware-calibrated UMC 65nm CMOS technology. A power consumption evaluation is performed on both the ASIC and FPGA platforms showing that the ASIC power consumption is lower by at least 65% when compared with the FPGA counterpart. A power-aware system is implemented with FPGAs by the adoption of the Dynamic Partial Reconfiguration (DPR) technique that allows the dynamic operation of the system based on power level available to the system at the expense of degradation of the system accuracy. The proposed system exploits the advantages of DPR technology in FPGAs to switch between two proposed designs providing a decrease of 64% in power consumption.