A deep learning framework with multi-perspective fusion for interictal epileptiform discharges detection in scalp electroencephalogram

Advancing epilepsy diagnosis: A meta-analysis of artificial intelligence approaches for interictal epileptiform discharge detection

INTRODUCTION

Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are an important biomarker for epilepsy. Currently, the gold standard for IED detection is the visual analysis performed by experts. However, this process is expert-biased, and time-consuming. Developing fast, accurate, and robust detection methods for IEDs based on EEG may facilitate epilepsy diagnosis. We aim to assess the performance of deep learning (DL) and classic machine learning (ML) algorithms in classifying EEG segments into IED and non-IED categories, as well as distinguishing whether the entire EEG contains IED or not.

METHODS

We systematically searched PubMed, Embase, and Web of Science following PRISMA guidelines. We excluded studies that only performed the detection of IEDs instead of binary segment classification. Risk of Bias was evaluated with Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Meta-analysis with the overall area under the Summary Receiver Operating Characteristic (SROC), sensitivity, and specificity as effect measures, was performed with R software.

RESULTS

A total of 23 studies, comprising 3,629 patients, were eligible for synthesis. Eighteen models performed discharge-level classification, and 6 whole-EEG classification. For the IED-level classification, 3 models were validated in an external dataset with more than 50 patients and achieved a sensitivity of 84.9 % (95 % CI: 82.3-87.2) and a specificity of 68.7 % (95 % CI: 7.9-98.2). Five studies reported model performance using both internal validation (cross-validation) and external datasets. The meta-analysis revealed higher performance for internal validation, with 90.4 % sensitivity and 99.6 % specificity, compared to external validation, which showed 78.1 % sensitivity and 80.1 % specificity.

CONCLUSION

Meta-analysis showed higher performance for models validated with resampling methods compared to those using external datasets. Only a minority of models use more robust validation techniques, which often leads to overfitting.

V2IED: Dual-view learning framework for detecting events of interictal epileptiform discharges

Interictal epileptiform discharges (IED) as large intermittent electrophysiological events are associated with various severe brain disorders. Automated IED detection has long been a challenging task, and mainstream methods largely focus on singling out IEDs from backgrounds from the perspective of waveform, leaving normal sharp transients/artifacts with similar waveforms almost unattended. An open issue still remains to accurately detect IED events that directly reflect the abnormalities in brain electrophysiological activities, minimizing the interference from irrelevant sharp transients with similar waveforms only. This study then proposes a dual-view learning framework (namely V2IED) to detect IED events from multi-channel EEG via aggregating features from the two phases: (1) Morphological Feature Learning: directly treating the EEG as a sequence with multiple channels, a 1D-CNN (Convolutional Neural Network) is applied to explicitly learning the deep morphological features; and (2) Spatial Feature Learning: viewing the EEG as a 3D tensor embedding channel topology, a CNN captures the spatial features at each sampling point followed by an LSTM (Long Short-Term Memories) to learn the evolution of these features. Experimental results from a public EEG dataset against the state-of-the-art counterparts indicate that: (1) compared with the existing optimal models, V2IED achieves a larger area under the receiver operating characteristic (ROC) curve in detecting IEDs from normal sharp transients with a 5.25% improvement in accuracy; (2) the introduction of spatial features improves performance by 2.4% in accuracy; and (3) V2IED also performs excellently in distinguishing IEDs from background signals especially benign variants.

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.

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.

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.

Satelight: Self-attention-based model for epileptic spike detection from multi-electrode EEG

OBJECTIVE

Because of the lack of highly skilled experts, automated technologies that support electroencephalogram (EEG)-based in epilepsy diagnosis are advancing. Deep convolutional neural network-based models have been used successfully for detecting epileptic spikes, one of the biomarkers, from EEG. However, a sizeable number of supervised EEG records are required for training.

APPROACH

This study introduces the Satelight model, which uses the self-attention (SA) mechanism. The model was trained using a clinical EEG dataset labeled by  ve specialists, including 16,008 epileptic spikes and 15,478 artifacts from 50 children. The SA mechanism is expected to reduce the number of parameters and efficiently extract features from a small amount of EEG data. To validate the effectiveness, we compared various spike detection approaches with the clinical EEG data.

MAIN RESULTS

The experimental results showed that the proposed method detected epileptic spikes more effectively than other models (accuracy = 0:876 and false positive rate = 0:133).

SIGNIFICANCE

The proposed model had only one-tenth the number of parameters as the other effective model, despite having such a high detection performance. Further exploration of the hidden parameters revealed that the model automatically attended to the EEG's characteristic waveform locations of interest.

Moving the field forward: detection of epileptiform abnormalities on scalp electroencephalography using deep learning—clinical application perspectives

The application of deep learning approaches for the detection of interictal epileptiform discharges is a nascent field, with most studies published in the past 5 years. Although many recent models have been published demonstrating promising results, deficiencies in descriptions of data sets, unstandardized methods, variation in performance evaluation and lack of demonstrable generalizability have made it difficult for these algorithms to be compared and progress to clinical validity. A few recent publications have provided a detailed breakdown of data sets and relevant performance metrics to exemplify the potential of deep learning in epileptiform discharge detection. This review provides an overview of the field and equips computer and data scientists with a synopsis of EEG data sets, background and epileptiform variation, model evaluation parameters and an awareness of the performance metrics of high impact and interest to the trained clinical and neuroscientist EEG end user. The gold standard and inter-rater disagreements in defining epileptiform abnormalities remain a challenge in the field, and a hierarchical proposal for epileptiform discharge labelling options is recommended. Standardized descriptions of data sets and reporting metrics are a priority. Source code-sharing and accessibility to public EEG data sets will increase the rigour, quality and progress in the field and allow validation and real-world clinical translation.

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.

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.

Scalp EEG recordings of pediatric epilepsy patients: A dataset for automatic detection of interictal epileptiform discharges from routine EEG

Interictal Epileptiform Discharges (IEDs) in routine EEG is crucial evidence of epilepsy in one patient. Though some studies have reported on automated detection of IEDs, the availability of open benchmark datasets for evaluating these methods is limited. This article presents a scalp EEG dataset of pediatric epilepsy patients. The dataset contains 19 channel EEG recordings of 21 subjects who are advised to undergo routine EEG tests to diagnose epilepsy. Among these 21 subjects, IEDs are found in EEG recordings of 11 subjects as confirmed by neurologists. The routine EEG recordings of the remaining 10 subjects are free from IEDs. A 32 channel EEG machine is used to record the routine EEG, and an international 10-20 electrode placement system is used to place the electrodes on the subject's scalp. A longitudinal bipolar montage channel configuration is used to collect the signals. IEDs present in routine EEG of epileptic patients are annotated by a neuro-technician and are provided with the dataset. The raw EEG data is further segmented into 10 s epochs based on the annotations for easy analysis and validation in automated IED detection systems. These 10 s epochs are also included in the dataset. The dataset is very useful for modeling novel automated IED detection systems that reduce the burdens of neurologists or neurophysiologists. In addition, the usability of the proposed dataset has also been experimented on a model based on exponential energy and support vector machine. The classification performance of the model indicates that the proposed dataset can be used as a benchmark dataset for automated IED detection.