A review of signal processing and machine learning techniques for interictal epileptiform discharge detection

Brain interictal epileptiform discharges (IEDs), as one of the hallmarks of epileptic brain, are transient events captured by electroencephalogram (EEG). IEDs are generated by seizure networks, and they occur between seizures (interictal periods). The development of a robust method for IED detection could be highly informative for clinical treatment procedures and epileptic patient management. Since 1972, different machine learning techniques, from template matching to deep learning, have been developed to automatically detect IEDs from scalp EEG (scEEG) and intracranial EEG (iEEG). While the scEEG signals suffer from low information details and high attenuation of IEDs due to the high skull electrical impedance, the iEEG signals recorded using implanted electrodes enjoy higher details and are more suitable for identifying the IEDs. In this review paper, we group IED detection techniques into six categories: (1) template matching, (2) feature representation (mimetic, time-frequency, and nonlinear features), (3) matrix decomposition, (4) tensor factorization, (5) neural networks, and (6) estimation of the iEEG from the concurrent scEEG followed by detection and classification. The methods are compared quantitatively (e.g., in terms of accuracy, sensitivity, and specificity), and their general advantages and limitations are described. Finally, current limitations and possible future research paths related to this field are mentioned.

Automated detection of absence seizures using a wearable electroencephalographic device: a phase 3 validation study and feasibility of automated behavioral testing

OBJECTIVE

Our primary goal was to measure the accuracy of fully automated absence seizure detection, using a wearable electroencephalographic (EEG) device. As a secondary goal, we also tested the feasibility of automated behavioral testing triggered by the automated detection.

METHODS

We conducted a phase 3 clinical trial (NCT04615442), with a prospective, multicenter, blinded study design. The input was the one-channel EEG recorded with dry electrodes embedded into a wearable headband device connected to a smartphone. The seizure detection algorithm was developed using artificial intelligence (convolutional neural networks). During the study, the predefined algorithm, with predefined cutoff value, analyzed the EEG in real time. The gold standard was derived from expert evaluation of simultaneously recorded full-array video-EEGs. In addition, we evaluated the patients' responsiveness to the automated alarms on the smartphone, and we compared it with the behavioral changes observed in the clinical video-EEGs.

RESULTS

We recorded 102 consecutive patients (57 female, median age = 10 years) on suspicion of absence seizures. We recorded 364 absence seizures in 39 patients. Device deficiency was 4.67%, with a total recording time of 309 h. Average sensitivity per patient was 78.83% (95% confidence interval [CI] = 69.56%-88.11%), and median sensitivity was 92.90% (interquartile range [IQR] = 66.7%-100%). The average false detection rate was .53/h (95% CI = .32-.74). Most patients (n = 66, 64.71%) did not have any false alarms. The median F1 score per patient was .823 (IQR = .57-1). For the total recording duration, F1 score was .74. We assessed the feasibility of automated behavioral testing in 36 seizures; it correctly documented nonresponsiveness in 30 absence seizures, and responsiveness in six electrographic seizures.

SIGNIFICANCE

Automated detection of absence seizures with a wearable device will improve seizure quantification and will promote assessment of patients in their home environment. Linking automated seizure detection to automated behavioral testing will provide valuable information from wearable devices.

Deep learning-based automated detection and multiclass classification of focal interictal epileptiform discharges in scalp electroencephalograms

Detection and spatial distribution analyses of interictal epileptiform discharges (IEDs) are important for diagnosing, classifying, and treating focal epilepsy. This study proposes deep learning-based models to detect focal IEDs in electroencephalography (EEG) recordings of the frontal, temporal, and occipital scalp regions. This study included 38 patients with frontal (n = 15), temporal (n = 13), and occipital (n = 10) IEDs and 232 controls without IEDs from a single tertiary center. All the EEG recordings were segmented into 1.5-s epochs and fed into 1- or 2-dimensional convolutional neural networks to construct binary classification models to detect IEDs in each focal region and multiclass classification models to categorize IEDs into frontal, temporal, and occipital regions. The binary classification models exhibited accuracies of 79.3-86.4%, 93.3-94.2%, and 95.5-97.2% for frontal, temporal, and occipital IEDs, respectively. The three- and four-class models exhibited accuracies of 87.0-88.7% and 74.6-74.9%, respectively, with temporal, occipital, and non-IEDs F1-scores of 89.9-92.3%, 84.9-90.6%, and 84.3-86.0%; and 86.6-86.7%, 86.8-87.2%, and 67.8-69.2% for the three- and four-class (frontal, 50.3-58.2%) models, respectively. The deep learning-based models could help enhance EEG interpretation. Although they performed well, the resolution of region-specific focal IED misinterpretations and further model improvement are needed.

Detection method of absence seizures based on Resnet and bidirectional GRU

Background

Epilepsy is a common chronic neurological disease. Its repeated seizure attacks have a great negative impact on patients’ physical and mental health. The diagnosis of epilepsy mainly depends on electroencephalogram (EEG) signals detection and analysis. There are two main EEG signals detection methods for epilepsy. One is the detection based on abnormal waveform, the other is the analysis of EEG signals based on the traditional machine learning. The feature extraction method of the traditional machine learning is difficult to capture the high-dimension information between adjacent sequences.

Methods

In this paper, redundant information was removed from the data by Gaussian filtering, downsampling, and short-time Fourier transform. Convolutional Neural Networks (CNN) was used to extract the high-dimensional features of the preprocessed data, and then Gate Recurrent Unit (GRU) was used to combine the sequence information before and after, to fully integrate the adjacent information EEG signals and improve the accuracy of the model detection.

Results

Four models were designed and compared. The experimental results showed that the prediction model based on deep residual network and bidirectional GRU had the best effect, and the test accuracy of the absence epilepsy test set reached 92%.

Conclusions

The prediction time of the network is only 10 sec when predicting four-hour EEG signals. It can be effectively used in EEG software to provide reference for doctors in EEG analysis and save doctors’ time, which has great practical value.

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Objective.Clinical diagnosis of epilepsy relies partially on identifying interictal epileptiform discharges (IEDs) in scalp electroencephalograms (EEGs). This process is expert-biased, tedious, and can delay the diagnosis procedure. Beyond automatically detecting IEDs, there are far fewer studies on automated methods to differentiate epileptic EEGs (potentially without IEDs) from normal EEGs. In addition, the diagnosis of epilepsy based on a single EEG tends to be low. Consequently, there is a strong need for automated systems for EEG interpretation. Traditionally, epilepsy diagnosis relies heavily on IEDs. However, since not all epileptic EEGs exhibit IEDs, it is essential to explore IED-independent EEG measures for epilepsy diagnosis. The main objective is to develop an automated system for detecting epileptic EEGs, both with or without IEDs. In order to detect epileptic EEGs without IEDs, it is crucial to include EEG features in the algorithm that are not directly related to IEDs.Approach.In this study, we explore the background characteristics of interictal EEG for automated and more reliable diagnosis of epilepsy. Specifically, we investigate features based on univariate temporal measures (UTMs), spectral, wavelet, Stockwell, connectivity, and graph metrics of EEGs, besides patient-related information (age and vigilance state). The evaluation is performed on a sizeable cohort of routine scalp EEGs (685 epileptic EEGs and 1229 normal EEGs) from five centers across Singapore, USA, and India.Main results.In comparison with the current literature, we obtained an improved Leave-One-Subject-Out (LOSO) cross-validation (CV) area under the curve (AUC) of 0.871 (Balanced Accuracy (BAC) of 80.9%) with a combination of three features (IED rate, and Daubechies and Morlet wavelets) for the classification of EEGs with IEDs vs. normal EEGs. The IED-independent feature UTM achieved a LOSO CV AUC of 0.809 (BAC of 74.4%). The inclusion of IED-independent features also helps to improve the EEG-level classification of epileptic EEGs with and without IEDs vs. normal EEGs, achieving an AUC of 0.822 (BAC of 77.6%) compared to 0.688 (BAC of 59.6%) for classification only based on the IED rate. Specifically, the addition of IED-independent features improved the BAC by 21% in detecting epileptic EEGs that do not contain IEDs.Significance.These results pave the way towards automated detection of epilepsy. We are one of the first to analyze epileptic EEGs without IEDs, thereby opening up an underexplored option in epilepsy diagnosis.

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

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

Multilevel Feature Learning Method for Accurate Interictal Epileptiform Spike Detection

Interictal epileptiform spike (referred to as spike) detected from electroencephalograms lasting only 20- to 200-ms can provide a reliable evidence-based indicator for clinical seizure type diagnosis. Recent feature representation approaches focus either on the concrete-level or on abstract-level information mining of the spike, thus demonstrating suboptimal detection performance. Additionally, existing abstract-level information mining methods of the spike based deep learning networks have not realized the effective feature representation of long-term dependent distinguished information within similar waveform cycles caused by morphological heterogeneity, which affects detection performance. Thus, a multilevel feature learning method for accurate spike detection was proposed in this study. Specifically, the spatio-temporal-frequency multidomain information in concrete-level first are inferred the common mimetic properties of the spike using the multidomain feature extractors. Then, the effective feature representation of long-term dependent distinguished information within similar waveform cycles caused by morphological heterogeneity is suitably captured using the temporal convolutional network. Finally, the spatio-temporal-frequency multidomain long-term dependent feature representation of spike is calculated using the element-wise manner to fuse the feature representation in concrete- and abstract-levels. The experimental results indicate that the proposed method can achieve an accuracy of 90.62±1.38%, sensitivity of 90.38±1.52%, specificity of 91.00±1.60%, precision of 90.33±4.71%, and the false detection rate per minute is 0.148±0.020m^-1, which are higher than when using the feature representation in the concrete- or abstract-level alone. Additionally, the detection results indicate that the proposed method avoids the subjectivity and inefficiency of visual inspection, and it enables a highly accurate detection of the spike.

Decoding Intracranial EEG With Machine Learning: A Systematic Review

Advances in intracranial electroencephalography (iEEG) and neurophysiology have enabled the study of previously inaccessible brain regions with high fidelity temporal and spatial resolution. Studies of iEEG have revealed a rich neural code subserving healthy brain function and which fails in disease states. Machine learning (ML), a form of artificial intelligence, is a modern tool that may be able to better decode complex neural signals and enhance interpretation of these data. To date, a number of publications have applied ML to iEEG, but clinician awareness of these techniques and their relevance to neurosurgery, has been limited. The present work presents a review of existing applications of ML techniques in iEEG data, discusses the relative merits and limitations of the various approaches, and examines potential avenues for clinical translation in neurosurgery. One-hundred-seven articles examining artificial intelligence applications to iEEG were identified from 3 databases. Clinical applications of ML from these articles were categorized into 4 domains: i) seizure analysis, ii) motor tasks, iii) cognitive assessment, and iv) sleep staging. The review revealed that supervised algorithms were most commonly used across studies and often leveraged publicly available timeseries datasets. We conclude with recommendations for future work and potential clinical applications.

Big data analysis and artificial intelligence in epilepsy - common data model analysis and machine learning-based seizure detection and forecasting

There has been significant interest in big data analysis and artificial intelligence (AI) in medicine. Ever-increasing medical data and advanced computing power have enabled the number of big data analyses and AI studies to increase rapidly. Here we briefly introduce epilepsy, big data, and AI and review big data analysis using a common data model. Studies in which AI has been actively applied, such as those of electroencephalography epileptiform discharge detection, seizure detection, and forecasting, will be reviewed. We will also provide practical suggestions for pediatricians to understand and interpret big data analysis and AI research and work together with technical expertise.

Engineering nonlinear epileptic biomarkers using deep learning and Benford's law

In this study, we designed two deep neural networks to encode 16 features for early seizure detection in intracranial EEG and compared them and their frequency responses to 16 widely used engineered metrics to interpret their properties: epileptogenicity index (EI), phase locked high gamma (PLHG), time and frequency domain Cho Gaines distance (TDCG, FDCG), relative band powers, and log absolute band powers (from alpha, beta, theta, delta, low gamma, and high gamma bands). The deep learning models were pretrained for seizure identification on the time and frequency domains of 1 s, single-channel clips of 127 seizures (from 25 different subjects) using "leave-one-out" (LOO) cross validation. Each neural network extracted unique feature spaces that were interpreted using spectral power modulations before being used to train a Random Forest Classifier (RFC) for seizure identification. The Gini Importance of each feature was calculated from the pretrained RFC, enabling the most significant features (MSFs) for each task to be identified. The MSFs were extracted to train another RFC for UPenn and Mayo Clinic's Seizure Detection Kaggle Challenge. They obtained an AUC score of 0.93, demonstrating a transferable method to identify and interpret biomarkers for seizure detection.

Multiview Feature Fusion Representation for Interictal Epileptiform Spikes Detection

Interictal epileptiform spikes (IES) of scalp electroencephalogram (EEG) signals have a strong relation with the epileptogenic region. Since IES are highly unlikely to be detected in scalp EEG signals, the primary diagnosis depends heavily on the visual evaluation of IES. However, visual inspection of EEG signals, the standard IES detection procedure is time-consuming, highly subjective, and error-prone. Furthermore, the highly complex, nonlinear, and nonstationary characteristics of EEG signals lead to the incomplete representation of EEG signals in existing computer-aided methods and consequently unsatisfactory detection performance. Therefore, a novel multiview feature fusion representation (MVFFR) method was developed and combined with a robustness classifier to detect EEG signals with/without IES. MVFFR comprises two steps: First, temporal, frequency, temporal-frequency, spatial, and nonlinear domain features are transformed by the IES to express the latent information effectively. Second, the unsupervised infinite feature-selection method determines the most distinct feature fusion representations. Experimental results using a balanced dataset of six patients showed that MVFFR achieved the optimal detection performance (accuracy: 89.27%, sensitivity: 89.01%, specificity: 89.54%, and precision: 89.82%) compared with other feature ranking methods, and the MVFFR-related method were complementary and indispensable. Additionally, in an independent test, MVFFR maintained excellent generalization capacity with a false detection rate per minute of 0.15 on the unbalanced dataset of one patient.

A Review of Network and Computer Analysis of Epileptiform Discharge Free EEG to Characterize and Detect Epilepsy

Objectives. There is emerging evidence that network/computer analysis of epileptiform discharge free electroencephalograms (EEGs) can be used to detect epilepsy, improve diagnosis and resource use. Such methods are automated and can be performed on shorter recordings of EEG. We assess the evidence and its strength in the area of seizure detection from network/computer analysis of epileptiform discharge free EEG. Methods. A scoping review using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidance was conducted with a literature search of Embase, Medline and PsychINFO. Predesigned inclusion/exclusion criteria were applied to selected articles. Results. The initial search found 3398 articles. After duplicate removal and screening, 591 abstracts were reviewed, 64 articles were selected and read leading to 20 articles meeting the requisite inclusion/exclusion criteria. These were 9 reports and 2 cross-sectional studies using network analysis to compare and/or classify EEG. One review of 17 reports and 10 cross-sectional studies only aimed to classify the EEGs. One cross-sectional study discussed EEG abnormalities associated with autism. Conclusions. Epileptiform discharge free EEG features derived from network/computer analysis differ significantly between people with and without epilepsy. Diagnostic algorithms report high accuracies and could be clinically useful. There is a lack of such research within the intellectual disability (ID) and/or autism populations, where epilepsy is more prevalent and there are additional diagnostic challenges.

Higher-order tensor decomposition based scalp-to-intracranial EEG projection for detection of interictal epileptiform discharges

Objective.Interictal epileptiform discharges (IEDs) occur between two seizures onsets. IEDs are mainly captured by intracranial recordings and are often invisible over the scalp. This study proposes a model based on tensor factorization to map the time-frequency (TF) features of scalp EEG (sEEG) to the TF features of intracranial EEG (iEEG) in order to detect IEDs from over the scalp with high sensitivity.Approach.Continuous wavelet transform is employed to extract the TF features. Time, frequency, and channel modes of IED segments from iEEG recordings are concatenated into a four-way tensor. Tucker and CANDECOMP/PARAFAC decomposition techniques are employed to decompose the tensor into temporal, spectral, spatial, and segmental factors. Finally, TF features of both IED and non-IED segments from scalp recordings are projected onto the temporal components for classification.Main results.The model performance is obtained in two different approaches: within- and between-subject classification approaches. Our proposed method is compared with four other methods, namely a tensor-based spatial component analysis method, TF-based method, linear regression mapping model, and asymmetric-symmetric autoencoder mapping model followed by convolutional neural networks. Our proposed method outperforms all these methods in both within- and between-subject classification approaches by respectively achieving 84.2% and 72.6% accuracy values.Significance.The findings show that mapping sEEG to iEEG improves the performance of the scalp-based IED detection model. Furthermore, the tensor-based mapping model outperforms the autoencoder- and regression-based mapping models.

AiED: Artificial intelligence for the detection of intracranial interictal epileptiform discharges

OBJECTIVE

Deep learning provides an appealing solution for the ongoing challenge of automatically classifying intracranial interictal epileptiform discharges (IEDs). We report results from an automated method consisting of a template-matching algorithm and convolutional neural network (CNN) for the detection of intracranial IEDs ("AiED").

METHODS

1000 intracranial electroencephalogram (EEG) epochs extracted randomly from 307 subjects with refractory epilepsy were annotated independently by two expert neurophysiologists. These annotated epochs were divided into 1062 two-second epochs with IEDs and 1428 two-second epochs without IEDs, which were transformed into spectrograms prior to training the neural network. The highest performing network was validated on an annotated external test set.

RESULTS

The final network had an F1-score of 0.95 (95% CI: 0.91-0.98) and an average Area Under the Receiver Operating Characteristic of 0.98 (95% CI: 0.96-1.00). For the external test set, it showed an overall F1-score of 0.71, correctly identifying 100% of all high-amplitude IED complexes, 96.23% of all high-amplitude isolated IEDs, and 66.15% of all IEDs of atypical morphology.

CONCLUSIONS

Template-matching combined with a CNN offers a fast, robust method for detecting intracranial IEDs.

SIGNIFICANCE

"AiED" is generalizable and achieves comparable performance to human reviewers; it may support clinical and research EEG analyses.

Attention-Based Parallel Multiscale Convolutional Neural Network for Visual Evoked Potentials EEG Classification

Electroencephalography (EEG) decoding is an important part of Visual Evoked Potentials-based Brain-Computer Interfaces (BCIs), which directly determines the performance of BCIs. However, long-time attention to repetitive visual stimuli could cause physical and psychological fatigue, resulting in weaker reliable response and stronger noise interference, which exacerbates the difficulty of Visual Evoked Potentials EEG decoding. In this state, subjects' attention could not be concentrated enough and the frequency response of their brains becomes less reliable. To solve these problems, we propose an attention-based parallel multiscale convolutional neural network (AMS-CNN). Specifically, the AMS-CNN first extract robust temporal representations via two parallel convolutional layers with small and large temporal filters respectively. Then, we employ two sequential convolution blocks for spatial fusion and temporal fusion to extract advanced feature representations. Further, we use attention mechanism to weight the features at different moments according to the output-related interest. Finally, we employ a full connected layer with softmax activation function for classification. Two fatigue datasets collected from our lab are implemented to validate the superior classification performance of the proposed method compared to the state-of-the-art methods. Analysis reveals the competitiveness of multiscale convolution and attention mechanism. These results suggest that the proposed framework is a promising solution to improving the decoding performance of Visual Evoked Potential BCIs.

A Study on Seizure Detection of EEG Signals Represented in 2D

A seizure is a neurological disorder caused by abnormal neuronal discharges in the brain, which severely reduces the quality of life of patients and often endangers their lives. Automatic seizure detection is an important research area in the treatment of seizure and is a prerequisite for seizure intervention. Deep learning has been widely used for automatic detection of seizures, and many related research works decomposed the electroencephalogram (EEG) raw signal with a time window to obtain EEG signal slices, then performed feature extraction on the slices, and represented the obtained features as input data for neural networks. There are various methods for EEG signal decomposition, feature extraction, and representation, and most of the studies have been based on fixed hardware resources for the design of the scheme, which reduces the adaptability of the scheme in different application scenarios and makes it difficult to optimize the algorithms in the scheme. To address the above issues, this paper proposes a deep learning-based model for seizure detection, mainly characterized by the two-dimensional representation of EEG features and the scalability of neural networks. The model modularizes the main steps of seizure detection and improves the adaptability of the model to different hardware resource constraints, in order to increase the convenience of the algorithm optimization or the replacement of each module. The proposed model consists of five parts, and the model was tested using two epilepsy datasets separately. The experimental results showed that the proposed model has strong generality and good classification accuracy for seizure detection.

Time-Frequency Decomposition of Scalp Electroencephalograms Improves Deep Learning-Based Epilepsy Diagnosis

Epilepsy diagnosis based on Interictal Epileptiform Discharges (IEDs) in scalp electroencephalograms (EEGs) is laborious and often subjective. Therefore, it is necessary to build an effective IED detector and an automatic method to classify IED-free versus IED EEGs. In this study, we evaluate features that may provide reliable IED detection and EEG classification. Specifically, we investigate the IED detector based on convolutional neural network (ConvNet) with different input features (temporal, spectral, and wavelet features). We explore different ConvNet architectures and types, including 1D (one-dimensional) ConvNet, 2D (two-dimensional) ConvNet, and noise injection at various layers. We evaluate the EEG classification performance on five independent datasets. The 1D ConvNet with preprocessed full-frequency EEG signal and frequency bands (delta, theta, alpha, beta) with Gaussian additive noise at the output layer achieved the best IED detection results with a false detection rate of 0.23/min at 90% sensitivity. The EEG classification system obtained a mean EEG classification Leave-One-Institution-Out (LOIO) cross-validation (CV) balanced accuracy (BAC) of 78.1% (area under the curve (AUC) of 0.839) and Leave-One-Subject-Out (LOSO) CV BAC of 79.5% (AUC of 0.856). Since the proposed classification system only takes a few seconds to analyze a 30-min routine EEG, it may help in reducing the human effort required for epilepsy diagnosis.

Increased hippocampal excitability in miR-324-null mice

MicroRNAs are non-coding RNAs that act to downregulate the expression of target genes by translational repression and degradation of messenger RNA molecules. Individual microRNAs have the ability to specifically target a wide array of gene transcripts, therefore allowing each microRNA to play key roles in multiple biological pathways. miR-324 is a microRNA predicted to target thousands of RNA transcripts and is expressed far more highly in the brain than in any other tissue, suggesting that it may play a role in one or multiple neurological pathways. Here we present data from the first global miR-324-null mice, in which increased excitability and interictal discharges were identified in vitro in the hippocampus. RNA sequencing was used to identify differentially expressed genes in miR-324-null mice which may contribute to this increased hippocampal excitability, and 3'UTR luciferase assays and western blotting revealed that two of these, Suox and Cd300lf, are novel direct targets of miR-324. Characterisation of microRNAs that produce an effect on neurological activity, such as miR-324, and identification of the pathways they regulate will allow a better understanding of the processes involved in normal neurological function and in turn may present novel pharmaceutical targets in treating neurological disease.

Deep learning for robust detection of interictal epileptiform discharges

OBJECTIVE

Automatic detection of interictal epileptiform discharges (IEDs, short as ``spikes'') from an epileptic brain can help predict seizure recurrence and support the diagnosis of epilepsy. Developing fast, reliable and robust detection methods for IEDs based on scalp or intracortical EEG may facilitate online seizure monitoring and closed-loop neurostimulation.

APPROACH

We developed a new deep learning approach, which employs a long short-term memory (LSTM) network architecture (``IEDnet'') and an auxiliary classifier generative adversarial network (AC-GAN), to train on both expert-annotated and augmented spike events from intracranial electroencephalography (iEEG) recordings of epilepsy patients. We validated our IEDnet with two real-world iEEG datasets, and compared IEDnet with the support vector machine (SVM) and random forest (RF) classifiers on their detection performances.

MAIN RESULTS

IEDnet achieved excellent cross-validated detection performances in terms of both sensitivity and specificity, and outperformed SVM and RF. Synthetic spike samples augmented by AC-GAN further improved the detection performance. In addition, the performance of IEDnet was robust with respect to the sampling frequency and noise. Furthermore, we also demonstrated the cross-institutional generalization ability of IEDnet while testing between two datasets.

SIGNIFICANCE

IEDnet achieves excellent detection performances in identifying interictal spikes. AC-GAN can produce augmented iEEG samples to improve supervised deep learning.

Incorporating Uncertainty in Data Labeling into Automatic Detection of Interictal Epileptiform Discharges from Concurrent Scalp-EEG via Multi-way Analysis

Interictal epileptiform discharges (IEDs) are elicited from an epileptic brain, whereas they can also be due to other neurological abnormalities. The diversity in their morphologies, their strengths, and their sources within the brain cause a great deal of uncertainty in their labeling by clinicians. The aim of this study is therefore to exploit and incorporate this uncertainty (the probability of the waveform being an IED) in the IED detection system which combines spatial component analysis (SCA) with the IED probabilities referred to as SCA-IEDP-based method. For comparison, we also propose and study SCA-based method in which probability of the waveform being an IED is ignored. The proposed models are employed to detect IEDs in two different classification approaches: (1) subject-dependent and (2) subject-independent classification approaches. The proposed methods are compared with two other state-of-the-art methods namely, time-frequency features and tensor factorization methods. The proposed SCA-IEDP model has achieved superior performance in comparison with the traditional SCA and other competing methods. It achieved 79.9% and 63.4% accuracy values in subject-dependent and subject-independent classification approaches, respectively. This shows that considering the IED probabilities in designing an IED detection system can boost its performance.

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

Ataxic gait monitoring and assessment of neurological disorders belong to important multidisciplinary areas that are supported by digital signal processing methods and machine learning tools. This paper presents the possibility of using accelerometric data to optimise deep learning convolutional neural network systems to distinguish between ataxic and normal gait. The experimental dataset includes 860 signal segments of 16 ataxic patients and 19 individuals from the control set with the mean age of 38.6 and 39.6 years, respectively. The proposed methodology is based upon the analysis of frequency components of accelerometric signals simultaneously recorded at specific body positions with a sampling frequency of 60 Hz. The deep learning system uses all of the frequency components in a range of 〈0,30 〉 Hz. Our classification results are compared with those obtained by standard methods, which include the support vector machine, Bayesian methods, and the two-layer neural network with features estimated as the relative power in selected frequency bands. Our results show that the appropriate selection of sensor positions can increase the accuracy from 81.2% for the foot position to 91.7% for the spine position. Combining the input data and the deep learning methodology with five layers increased the accuracy to 95.8%. Our methodology suggests that artificial intelligence methods and deep learning are efficient methods in the assessment of motion disorders and they have a wide range of further applications.

An Epilepsy Detection Method Using Multiview Clustering Algorithm and Deep Features

The automatic detection of epilepsy is essentially the classification of EEG signals of seizures and nonseizures, and its purpose is to distinguish the different characteristics of seizure brain electrical signals and normal brain electrical signals. In order to improve the effect of automatic detection, this study proposes a new classification method based on unsupervised multiview clustering results. In addition, considering the high-dimensional characteristics of the original data samples, a deep convolutional neural network (DCNN) is introduced to extract the sample features to obtain deep features. The deep feature reduces the sample dimension and increases the sample separability. The main steps of our proposed novel EEG detection method contain the following three steps: first, a multiview FCM clustering algorithm is introduced, and the training samples are used to train the center and weight of each view. Then, the class center and weight of each view obtained by training are used to calculate the view-weighted membership value of the new prediction sample. Finally, the classification label of the new prediction sample is obtained. Experimental results show that the proposed method can effectively detect seizures.

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis

Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands 〈 3 , 8 〉 and 〈 8 , 15 〉 Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.

Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning

OBJECTIVE

Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings.

METHODS

An epileptologist annotated 13,959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation.

RESULTS

On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precision-recall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation.

CONCLUSIONS

Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes.

SIGNIFICANCE

Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.

EEG-based image classification via a region-level stacked bi-directional deep learning framework

BACKGROUND

As a physiological signal, EEG data cannot be subjectively changed or hidden. Compared with other physiological signals, EEG signals are directly related to human cortical activities with excellent temporal resolution. After the rapid development of machine learning and artificial intelligence, the analysis and calculation of EEGs has made great progress, leading to a significant boost in performances for content understanding and pattern recognition of brain activities across the areas of both neural science and computer vision. While such an enormous advance has attracted wide range of interests among relevant research communities, EEG-based classification of brain activities evoked by images still demands efforts for further improvement with respect to its accuracy, generalization, and interpretation, yet some characters of human brains have been relatively unexplored.

METHODS

We propose a region-level stacked bi-directional deep learning framework for EEG-based image classification. Inspired by the hemispheric lateralization of human brains, we propose to extract additional information at regional level to strengthen and emphasize the differences between two hemispheres. The stacked bi-directional long short-term memories are used to capture the dynamic correlations hidden from both the past and the future to the current state in EEG sequences.

RESULTS

Extensive experiments are carried out and our results demonstrate the effectiveness of our proposed framework. Compared with the existing state-of-the-arts, our framework achieves outstanding performances in EEG-based classification of brain activities evoked by images. In addition, we find that the signals of Gamma band are not only useful for achieving good performances for EEG-based image classification, but also play a significant role in capturing relationships between the neural activations and the specific emotional states.

CONCLUSIONS

Our proposed framework provides an improved solution for the problem that, given an image used to stimulate brain activities, we should be able to identify which class the stimuli image comes from by analyzing the EEG signals. The region-level information is extracted to preserve and emphasize the hemispheric lateralization for neural functions or cognitive processes of human brains. Further, stacked bi-directional LSTMs are used to capture the dynamic correlations hidden in EEG data. Extensive experiments on standard EEG-based image classification dataset validate that our framework outperforms the existing state-of-the-arts under various contexts and experimental setups.

Automatic Seizure Detection Based on S-Transform and Deep Convolutional Neural Network

Automatic seizure detection is significant for the diagnosis of epilepsy and reducing the massive workload of reviewing continuous EEGs. In this work, a novel approach, combining Stockwell transform (S-transform) with deep Convolutional Neural Networks (CNN), is proposed to detect seizure onsets in long-term intracranial EEG recordings. Primarily, raw EEG data is filtered with wavelet decomposition. Then, S-transform is used to obtain a proper time-frequency representation of each EEG segment. After that, a 15-layer deep CNN using dropout and batch normalization serves as a robust feature extractor and classifier. Finally, smoothing and collar technique are applied to the outputs of CNN to improve the detection accuracy and reduce the false detection rate (FDR). The segment-based and event-based evaluation assessments and receiver operating characteristic (ROC) curves are employed for the performance evaluation on a public EEG database containing 21 patients. A segment-based sensitivity of 97.01% and a specificity of 98.12% are yielded. For the event-based assessment, this method achieves a sensitivity of 95.45% with an FDR of 0.36/h.

Motion Symmetry Evaluation Using Accelerometers and Energy Distribution

Analysis of motion symmetry constitutes an important area with many applications in engineering, robotics, neurology and biomedicine. This paper presents the use of microelectromechanical sensors (MEMS), including accelerometers and gyrometers, to acquire data via mobile devices so as to monitor physical activities and their irregularities. Special attention is devoted to the analysis of the symmetry of the motion of the body when the same exercises are performed by the right and the left limb. The analyzed data include the motion of the legs on a home exercise bike under different levels of load. The method is based on signal analysis using the discrete wavelet transform and the evaluation of signal segment features such as the relative energy at selected decomposition levels. The subsequent classification of the evaluated features is performed by k-nearest neighbours, a Bayesian approach, a support vector machine, and neural networks. The highest average classification accuracy attained is 91.0% and the lowest mean cross-validation error is 0.091, resulting from the use of a neural network. This paper presents the advantages of the use of simple sensors, their combination and intelligent data processing for the numerical evaluation of motion features in the rehabilitation and monitoring of physical activities.

A deep learning approach for real-time detection of sleep spindles

OBJECTIVE

Sleep spindles have been implicated in memory consolidation and synaptic plasticity during NREM sleep. Detection accuracy and latency in automatic spindle detection are critical for real-time applications.

APPROACH

Here we propose a novel deep learning strategy (SpindleNet) to detect sleep spindles based on a single EEG channel. While the majority of spindle detection methods are used for off-line applications, our method is well suited for online applications.

MAIN RESULTS

Compared with other spindle detection methods, SpindleNet achieves superior detection accuracy and speed, as demonstrated in two publicly available expert-validated EEG sleep spindle datasets. Our real-time detection of spindle onset achieves detection latencies of 150-350 ms (~two-three spindle cycles) and retains excellent performance under low EEG sampling frequencies and low signal-to-noise ratios. SpindleNet has good generalization across different sleep datasets from various subject groups of different ages and species.

SIGNIFICANCE

SpindleNet is ultra-fast and scalable to multichannel EEG recordings, with an accuracy level comparable to human experts, making it appealing for long-term sleep monitoring and closed-loop neuroscience experiments.

Deep learning for electroencephalogram (EEG) classification tasks: a review

OBJECTIVE

Electroencephalography (EEG) analysis has been an important tool in neuroscience with applications in neuroscience, neural engineering (e.g. Brain-computer interfaces, BCI's), and even commercial applications. Many of the analytical tools used in EEG studies have used machine learning to uncover relevant information for neural classification and neuroimaging. Recently, the availability of large EEG data sets and advances in machine learning have both led to the deployment of deep learning architectures, especially in the analysis of EEG signals and in understanding the information it may contain for brain functionality. The robust automatic classification of these signals is an important step towards making the use of EEG more practical in many applications and less reliant on trained professionals. Towards this goal, a systematic review of the literature on deep learning applications to EEG classification was performed to address the following critical questions: (1) Which EEG classification tasks have been explored with deep learning? (2) What input formulations have been used for training the deep networks? (3) Are there specific deep learning network structures suitable for specific types of tasks?

APPROACH

A systematic literature review of EEG classification using deep learning was performed on Web of Science and PubMed databases, resulting in 90 identified studies. Those studies were analyzed based on type of task, EEG preprocessing methods, input type, and deep learning architecture.

MAIN RESULTS

For EEG classification tasks, convolutional neural networks, recurrent neural networks, deep belief networks outperform stacked auto-encoders and multi-layer perceptron neural networks in classification accuracy. The tasks that used deep learning fell into five general groups: emotion recognition, motor imagery, mental workload, seizure detection, event related potential detection, and sleep scoring. For each type of task, we describe the specific input formulation, major characteristics, and end classifier recommendations found through this review.

SIGNIFICANCE

This review summarizes the current practices and performance outcomes in the use of deep learning for EEG classification. Practical suggestions on the selection of many hyperparameters are provided in the hope that they will promote or guide the deployment of deep learning to EEG datasets in future research.

Deep Neural Architectures for Mapping Scalp to Intracranial EEG

Data is often plagued by noise which encumbers machine learning of clinically useful biomarkers and electroencephalogram (EEG) data is no exemption. Intracranial EEG (iEEG) data enhances the training of deep learning models of the human brain, yet is often prohibitive due to the invasive recording process. A more convenient alternative is to record brain activity using scalp electrodes. However, the inherent noise associated with scalp EEG data often impedes the learning process of neural models, achieving substandard performance. Here, an ensemble deep learning architecture for nonlinearly mapping scalp to iEEG data is proposed. The proposed architecture exploits the information from a limited number of joint scalp-intracranial recording to establish a novel methodology for detecting the epileptic discharges from the sEEG of a general population of subjects. Statistical tests and qualitative analysis have revealed that the generated pseudo-intracranial data are highly correlated with the true intracranial data. This facilitated the detection of IEDs from the scalp recordings where such waveforms are not often visible. As a real-world clinical application, these pseudo-iEEGs are then used by a convolutional neural network for the automated classification of intracranial epileptic discharges (IEDs) and non-IED of trials in the context of epilepsy analysis. Although the aim of this work was to circumvent the unavailability of iEEG and the limitations of sEEG, we have achieved a classification accuracy of 68% an increase of 6% over the previously proposed linear regression mapping.