Seizure Classification Research Articles

Feature Selection with Deep Belief Network for Epileptic Seizure Detection on EEG Signals

The term Epilepsy refers to a most commonly occurring brain disorder after a migraine. Early identification of incoming seizures significantly impacts the lives of people with Epilepsy. Automated detection of epileptic seizures (ES) has dramatically improved the life quality of the patients. Recent Electroencephalogram (EEG) related seizure detection mechanisms encountered several difficulties in real-time. The EEGs are the non-stationary signal, and seizure patterns would change with patients and recording sessions. Further, EEG data were disposed to wide noise varieties that adversely moved the recognition accuracy of ESs. Artificial intelligence (AI) methods in the domain of ES analysis use traditional deep learning (DL), and machine learning (ML) approaches. This article introduces an Oppositional Aquila Optimizer-based Feature Selection with Deep Belief Network for Epileptic Seizure Detection (OAOFS-DBNECD) technique using EEG signals. The primary aim of the presented OAOFS-DBNECD system is to categorize and classify the presence of ESs. The suggested OAOFS-DBNECD technique transforms the EEG signals into .csv format at the initial stage. Next, the OAOFS technique selects an optimal subset of features using the pre-processed data. For seizure classification, the presented OAOFS-DBNECD technique applies Artificial Ecosystem Optimizer (AEO) with a deep belief network (DBN) model. An extensive range of simulations was performed on the benchmark dataset to ensure the enhanced performance of the presented OAOFS-DBNECD algorithm. The comparison study shows the significant outcomes of the OAOFS-DBNECD approach over other methodologies. In addition, the result of the suggested approach has been evaluated using the CHB-MIT database, and the findings demonstrate accuracy of 97.81%. These findings confirmed the best seizure categorization accuracy on the EEG data considered.

Stereotactic radiosurgery as the initial management option for small-volume hypothalamic hamartomas with intractable epilepsy: a 35-year institutional experience and systematic review.

Young patients with hypothalamic hamartomas (HHs) often present with intractable epilepsy. Currently there are no established management guidelines for HH. The authors retrospectively reviewed their single-institution experience to delineate the role of stereotactic radiosurgery (SRS). Seven patients with HHs (4 females; median age 13.7 years, range 2.5-25 years) with no prior resection underwent SRS between 1987 and 2022. The clinical history, epilepsy profile, radiographic findings, and neurological outcomes were characterized. HH topographical types were classified according to the Régis classification. Outcome measures included Engel seizure classification, HH response, and the need for additional surgical interventions. All patients had Engel class IV epilepsy. A Leksell Gamma Knife was used to deliver a median margin dose of 18 Gy (range 16-20 Gy) to a median hamartoma volume of 0.37 cm3 (range 0.20-0.89 cm3). Seizure reduction was confirmed in 6 patients, and 2 patients had regression of their hamartoma. Two patients underwent resection and/or laser interstitial thermal therapy after SRS. At follow-up, 1 patient was seizure free, 4 patients achieved Engel class II, 1 patient had Engel class III, and 1 patient had Engel class IV seizure outcomes. SRS as the initial management option for HH was associated with a low risk of adverse effects. In this institutional series reviewing small-volume HHs treated with SRS, no adverse radiation effect was detected, and the majority of patients experienced seizure reduction. SRS should be considered as the first-line treatment for seizure control in patients with small-volume HHs.

Variational mode decomposition and binary grey wolf optimization-based automated epilepsy seizure classification framework.

This work proposes a variational mode decomposition (VMD) and binary grey wolf optimization (BGWO) based seizure classification framework. VMD decomposes the EEG signal into band-limited intrinsic mode function (BL-IMFs) non-recursively. The frequency domain, time domain, and information theory-based features are extracted from the BL-IMFs. Further, an optimal feature subset is selected using BGWO. Finally, the selected features were utilized for classification using six different supervised machine learning algorithms. The proposed framework has been validated experimentally by 58 test cases from the CHB-MIT scalp EEG and the Bonn University database. The proposed framework performance is quantified by average sensitivity, specificity, and accuracy. The selected features, along with Bayesian regularized shallow neural networks (BR-SNNs), resulted in maximum accuracy of 99.53 and 99.64 for 1 and 2s epochs, respectively, for database 1. The proposed framework has achieved 99.79 and 99.84 accuracy for 1 and 2s epochs, respectively, for database 2.

Seizure detection using integrated metaheuristic algorithm based ensemble extreme learning machine

In biomedical research, the brain signal analysis occupies an important space in recent days. Mostly Epileptic seizure detection is a challenging task for all brain signal researcher. In this paper ensemble approach is considered for seizure classification and detection. It is essential of early detection for the patient to save the life. Initially Wavelet transform is used to extract the relevant features. As the feature dimension is high, features are reduced using linear discriminant analysis (LDA). The metaheuristic algorithms named as Water cycle algorithm and accelerated particle swarm optimization (APSO) are integrated to optimize the weights of ensemble extreme learning machine (EELM) for classification. The features are aligned as input to WCA-APSO based EELM model. To validate the proposed integrated algorithm three benchmark functions are utilized for optimization to exhibit the uniqueness. The data is taken from university of BONN database for experimentation. The performance is measured with the parameters like sensitivity, Specificity, and Accuracy are obtained as 99.32%, 99.68%, and 99.16%, The result found superior as compared to earlier methods and outperforms the classification of Epileptic seizure signals.

Effects of Data Augmentation with the BNNSMOTE Algorithm in Seizure Detection Using 1D-MobileNet.

Automatic seizure detection technology has important implications for reducing the workload of neurologists for epilepsy diagnosis and treatment. Due to the unpredictable nature of seizures, the imbalanced classification of seizure and nonseizure data continues to be challenging. In this work, we first propose a novel algorithm named the borderline nearest neighbor synthetic minority oversampling technique (BNNSMOTE) to address the imbalanced classification problem and improve seizure detection performance. The algorithm uses the nearest neighbor notion to generate nonseizure samples near the boundary, then determines the seizure samples that are difficult to learn at the boundary, and lastly selects seizure samples at random to be used in the synthesis of new samples. In view of the characteristic that electroencephalogram (EEG) signals are one-dimensional signals, we then develop a 1D-MobileNet model to validate the algorithm's performance. Results demonstrate that the proposed algorithm outperforms previous seizure detection methods on the CHB-MIT dataset, achieving an average accuracy of 99.40%, a recall value of 87.46%, a precision of 97.17%, and an F1-score of 91.90%, respectively. We also had considerable success when we used additional datasets for verification at the same time. Our algorithm's data augmentation effects are more pronounced and perform better at seizure detection than the existing imbalanced techniques. Besides, the model's parameters and calculation volume have been significantly reduced, making it more suitable for mobile terminals and embedded devices.

Cognitive decline and quality of life after resective epilepsy surgery

ObjectivesThe objectives of this study were to examine the association between cognitive decline and quality of life (QoL) change in a large sample of individuals with drug-resistant epilepsy who underwent resective surgery and to examine whether the association between cognitive decline and QoL is differentially affected by seizure classification outcome (Engel Class 1 vs. 2–4) or side of surgery (left vs. right hemisphere). Materials and methodsThe sample comprised 224 adults (ages ≥ 18) with drug-resistant focal epilepsy treated with resective surgery who underwent comprehensive pre-operative and post-operative evaluations including neuropsychological testing and the Quality of Life in Epilepsy Inventory - 31 between 1991 and 2020. Linear mixed-effects models were fit to examine subject-specific trajectories and assess the effects of time (pre- to post-operative), cognitive decline (number of measures that meaningfully declined), and the interaction between time and cognitive decline on pre- to post-operative change in QoL. ResultsIncreases in QoL following resection were observed (B = −10.72 [SE = 1.22], p < .001; mean difference between time point 1 and time point 2 QoL rating = 8.11). There was also a main effect of cognitive decline on QoL (B = −.85 [SE = .27], p = .002). Follow-up analyses showed that the number of cognitive measures that declined was significantly associated with post-surgical QoL, (r = −.20 p = .003), but not pre-surgical QoL, (r = −.04 p = .594), and with pre-to post-surgery raw change in QoL score, (r = −.18 p = .009). A cognitive decline by time point interaction was observed, such that those who had greater cognitive decline had less improvement in overall QoL following resection (B = .72 [SE = .27], p = .009). Similar results were observed within the Engel Class 1 outcome subgroup. However, within the Engel Class 2–4 outcome subgroup, QoL improved following resection, but there was no main effect of cognitive decline or interaction between cognitive decline and time point on QoL change. There was no main effect of resection hemisphere on overall QoL, nor were there interactions with hemisphere by time, hemisphere by cognitive decline, or hemisphere by time by cognitive decline. ConclusionsQuality of life improves following epilepsy surgery. Participants who had cognitive decline across a greater number of measures experienced less improvement in QoL post-operatively overall, but there was no clear pattern of domain-specific cognitive decline associated with change in QoL. Our results indicate that cognitive decline in a diffuse set of cognitive domains negatively influences post-operative QoL, particularly for those who experience good seizure outcomes (i.e., seizure freedom), regardless of the site or side of resection.

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

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

Adaptive octopus deep transfer learning based epileptic seizure classification on field programmable gate arrays

Adaptive octopus deep transfer learning based epileptic seizure classification on field programmable gate arrays

A simple and rapid focal seizure screening tool in resource-limited setting

Background &amp; Objective: A substantial proportion of patients were managed by general clinicians in resource-limited settings. Therefore, we aim to develop a simple and rapid focal seizure screening tool that can assist non-neurologists in seizure classification. Methods: We conducted a self-administered qualitative questionnaire study on seizure manifestation developed based on the validated comprehensive questionnaires by Reutens et al. for clinical diagnosis of seizures. Logistic regression analyses were conducted to determine the features of seizure which form the items of a focal seizure screening tool. A receiver operating characteristic (ROC) curve analysis was conducted to determine the optimal cut-off score. Results: Among the 199 subjects, 145 (73%) had focal seizures. Three categories of symptoms, i.e., (i) aura (fear, déjà vu, and epigastric aura), (ii) unilateral motor phenomena, and (iii) oral automatism, are significantly associated with the diagnosis of focal seizure. The logistic regression model containing these 3 items / features was statistically significant, χ2 (3, N=199) = 22.93, p&lt;0.001, and correctly classified 71.4% of cases. A focal seizure screening tool was developed by assigning a score of 1 to each category of symptoms. The area under the curve of ROC curve is 0.706 (95% CI: 0.629-0.783), p&lt;0.001. A score of ≥2 is the most optimal cut-off with a sensitivity of 50.3%, specificity of 85.2%, positive predictive value (PPV) of 91.0%, and negative predictive value (NPV) of 41.8%. Conclusion: A simple and rapid self-administered focal seizure screening tool was established with high specificity and PPV.

Identification and classification of epileptic EEG signals using invertible constant-Q transform-based deep convolutional neural network

Context. Epilepsy is the most widespread disorder of the nervous system, affecting humans of all ages and races. The most common diagnostic test in epilepsy is the electroencephalography (EEG). Objective. In this paper, a novel automated deep learning approach based on integrating a pre-trained convolutional neural network (CNN) structure, called AlexNet, with the constant-Q non-stationary Gabor transform (CQ-NSGT) algorithm is proposed for classifying seizure versus seizure-free EEG records. Approach. The CQ-NSGT method is introduced to transform the input 1D EEG signal into 2D spectrogram which is sent to the AlexNet CNN model. The AlexNet architecture is utilized to capture the discriminating features of the 2D image corresponding to each EEG signal in order to distinguish seizure and non-seizure subjects using multi-layer perceptron algorithm. Main results. The robustness of the introduced CQ-NSGT technique in transforming the 1D EEG signals into 2D spectrograms is assessed by comparing its classification results with the continuous wavelet transform method, and the results elucidate the high performance of the CQ-NSGT technique. The suggested epileptic seizure classification framework is investigated with clinical EEG data acquired from the Bonn University database, and the experimental results reveal the superior performance of the proposed framework over other state-of-the-art approaches with an accuracy of 99.56%, sensitivity of 99.12%, specificity of 99.67%, and precision of 98.69%. Significance. This elucidates the importance of the proposed automated system in helping neurologists to accurately interpret and classify epileptic EEG records without necessitating tedious visual inspection or massive data analysis for long-term EEG signals.

Interactive local and global feature coupling for EEG-based epileptic seizure detection

Automatic seizure detection based on scalp electroencephalogram (EEG) can accelerate the progress of epilepsy diagnosis. Current seizure detection methods based on deep learning usually rely on single convolutional neural network (CNN) or recurrent neural network (RNN) models. In terms of feature extraction, single model often has limitations. Since CNN is good at extracting local features, and Transformer can capture global information, we put forward a seizure detection method based on interactive local and global feature coupling. Local feature and global representation of the EEG are respectively extracted by convolution operation and self-attention mechanism. To make up of the shortcomings of local feature and global representation, a feature coupling block (FCB) is utilized to fuse the two kinds of information in an interactive way. The enhanced feature representation is fed to the classifier for seizure and normal EEG classification. Extensive experiments are conducted on CHB-MIT and Siena scalp EEG datasets. Experimental results demonstrate that the method can effectively perform epileptic seizure detection from the original EEG signals without extra feature extraction.

A Novel Approach for Multichannel Epileptic Seizure Classification Based on Internet of Things Framework Using Critical Spectral Verge Feature Derived from Flower Pollination Algorithm

A novel approach for multichannel epilepsy seizure classification which will help to automatically locate seizure activity present in the focal brain region was proposed. This paper suggested an Internet of Things (IoT) framework based on a smart phone by utilizing a novel feature termed multiresolution critical spectral verge (MCSV), based on frequency-derived information for epileptic seizure classification which was optimized using a flower pollination algorithm (FPA). A wireless sensor technology (WSN) was utilized to record the electroencephalography (EEG) signal of epileptic patients. Next, the EEG signal was pre-processed utilizing a multiresolution-based adaptive filtering (MRAF) method. Then, the maximal frequency point at which the power spectral density (PSD) of each EEG segment was greater than the average spectral power of the corresponding frequency band was computed. This point was further optimized to extract a point termed as critical spectral verge (CSV) to extract the exact high frequency oscillations representing the actual seizure activity present in the EEG signal. Next, a support vector machine (SVM) classifier was used for channel-wise classification of the seizure and non-seizure regions using CSV as a feature. This process of classification using the CSV feature extracted from the MRAF output is referred to as the MCSV approach. As a final step, cloud-based services were employed to analyze the EEG information from the subject's smart phone. An exhaustive analysis was undertaken to assess the performance of the MCSV approach for two datasets. The presented approach showed an improved performance with a 93.83% average sensitivity, a 97.94% average specificity, a 97.38% average accuracy with the SVM classifier, and a 95.89% average detection rate as compared with other state-of-the-art studies such as deep learning. The methods presented in the literature were unable to precisely localize the origination of the seizure activity in the brain region and reported a low seizure detection rate. This work introduced an optimized CSV feature which was effectively used for multichannel seizure classification and localization of seizure origination. The proposed MCSV approach will help diagnose epileptic behavior from multichannel EEG signals which will be extremely useful for neuro-experts to analyze seizure details from different regions of the brain.

Approximate zero-crossing: a new interpretable, highly discriminative and low-complexity feature for EEG and iEEG seizure detection

Objective. Long-term monitoring of people with epilepsy based on electroencephalography (EEG) and intracranial EEG (iEEG) has the potential to deliver key clinical information for personalised epilepsy treatment. More specifically, in outpatient settings, the available solutions are not satisfactory either due to poor classification performance or high complexity to be executed in resource-constrained devices (e.g. wearable systems). Therefore, we hypothesize that obtaining high discriminative features is the main avenue to improve low-complexity seizure-detection algorithms. Approach. Inspired by how neurologists recognize ictal EEG data, and to tackle this problem by targeting resource-constrained wearable devices, we introduce a new interpretable and highly discriminative feature for EEG and iEEG, namely approximate zero-crossing (AZC). We obtain AZC by applying a polygonal approximation to mimic how our brain selects prominent patterns among noisy data and then using a zero-crossing count as a measure of the dominating frequency. By employing Kullback–Leiber divergence, leveraging CHB-MIT and SWEC-ETHZ iEEG datasets, we compare the AZC discriminative power against a set of 56 classical literature features (CLF). Moreover, we assess the performances of a low-complexity seizure detection method using only AZC features versus employing the CLF set. Main results. Three AZC features obtained with different approximation thresholds are among the five with the highest median discriminative power. Moreover, seizure classification based on only AZC features outperforms an equivalent CLF-based method. The former detects 102 and 194 seizures, against 99 and 161 for the latter (CHB-MIT and SWEC-ETHZ, respectively). Moreover, the AZC-based method keeps a similar false-alarm rate (i.e. an average of 2.1 and 1.0, against 2.0 and 0.5, per day). Significance. We propose a new feature and demonstrate its capability in seizure classification for both scalp and intracranial EEG. We envision the use of such a feature to improve outpatient monitoring with resource-constrained devices.

Novel 3D video action recognition deep learning approach for near real time epileptic seizure classification

Seizure semiology is a well-established method to classify epileptic seizure types, but requires a significant amount of resources as long-term Video-EEG monitoring needs to be visually analyzed. Therefore, computer vision based diagnosis support tools are a promising approach. In this article, we utilize infrared (IR) and depth (3D) videos to show the feasibility of a 24/7 novel object and action recognition based deep learning (DL) monitoring system to differentiate between epileptic seizures in frontal lobe epilepsy (FLE), temporal lobe epilepsy (TLE) and non-epileptic events. Based on the largest 3Dvideo-EEG database in the world (115 seizures/+680,000 video-frames/427GB), we achieved a promising cross-subject validation f1-score of 0.833±0.061 for the 2 class (FLE vs. TLE) and 0.763 ± 0.083 for the 3 class (FLE vs. TLE vs. non-epileptic) case, from 2 s samples, with an automated semi-specialized depth (Acc.95.65%) and Mask R-CNN (Acc.96.52%) based cropping pipeline to pre-process the videos, enabling a near-real-time seizure type detection and classification tool. Our results demonstrate the feasibility of our novel DL approach to support 24/7 epilepsy monitoring, outperforming all previously published methods.

Similarity-Based Adaptive Window for Improving Classification of Epileptic Seizures with Imbalance EEG Data Stream.

Data stream mining techniques have recently received increasing research interest, especially in medical data classification. An unbalanced representation of the classification's targets in these data is a common challenge because classification techniques are biased toward the major class. Many methods have attempted to address this problem but have been exaggeratedly biased toward the minor class. In this work, we propose a method for balancing the presence of the minor class within the current window of the data stream while preserving the data's original majority as much as possible. The proposed method utilized similarity analysis for selecting specific instances from the previous window. This group of minor-class was then added to the current window's instances. Implementing the proposed method using the Siena dataset showed promising results compared to the Skew ensemble method and some other research methods.

Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity

Dynamic complexity in brain functional connectivity has hindered the effective use of signal processing or machine learning methods to diagnose neurological disorders such as epilepsy. This paper proposed a new graph-generative neural network (GGN) model for the dynamic discovery of brain functional connectivity via deep analysis of scalp electroencephalogram (EEG) signals recorded from various regions of a patient’s scalp. Brain functional connectivity graphs are generated for the extraction of spatial–temporal resolution of various onset epilepsy seizure patterns. Our supervised GGN model was substantiated by seizure detection and classification experiments. We train the GGN model using a clinically proven dataset of over 3047 epileptic seizure cases. The GGN model achieved a 91% accuracy in classifying seven types of epileptic seizure attacks, which outperformed the 65%, 74%, and 82% accuracy in using the convolutional neural network (CNN), graph neural networks (GNN), and transformer models, respectively. We present the GGN model architecture and operational steps to assist neuroscientists or brain specialists in using dynamic functional connectivity information to detect neurological disorders. Furthermore, we suggest to merge our spatial–temporal graph generator design in upgrading the conventional CNN and GNN models with dynamic convolutional kernels for accuracy enhancement.

A Prospective Hospital-Based Study on the Clinico-Etiological Profile of the First Episode of a Seizure in Children.

Background This study aims to examine the clinico-etiological profile of children with the first episode of a seizureand categorize seizure types based on age groups in a tertiary care hospital. Methodology This was aprospective observational studyconducted at a tertiary care medical institute in India over two years. Children (one month to 12 years of age) with the first episode of a seizure were included in the study population. The data collected included demographic profile, history, examination, biochemical profile, electroencephalogram (EEG), and neuroimaging.Children were categorized as generalized-onset, focal-onset, and unknown-onset seizures based on the International League Against Epilepsy2017 seizureclassification. Children were also classified according to specific etiologies such as structural, metabolic, or other specific causes. All the children were followed up at the hospital's outpatient clinic or through a telephonic interview. Results A total of 220 children were examined in this study. Among them, 64% were male and 36% were female, with a male-to-female ratio of 1.75:1. Among the 220 children, 21.8% had a family history of seizure. The most common type of seizures were generalized-onset seizures (n = 110, 50%), followed by focal-onset seizures (n = 96, 43.6%). Overall, 9% of children presented with status epilepticus as their first-episode seizure. An abnormal EEG was recorded for 122 (76%) children. While 60% of children had abnormal neuroimaging findings, the remaining had normal neuroimaging. Febrile seizures (n = 92, 41.9%) were the most common cause of the first episode of a seizure. Most of the febrile seizures occurred between the ageof one and four (n = 60, 65.2%). Epilepsy syndromes were the second most common etiology, followed by central nervous system (CNS) infections, structural brain abnormalities, metabolic disorders, vascular lesions, toxins, and immune-mediated causes, in that order. In 14 (6.36%) children, the etiology was unknown at the time of the study. Conclusions First-episode seizures in children cause physical, mental, and financial stress on the parents. The collection of detailed history, examinations, and appropriate investigations can help identifythe etiology of seizures. It was possible to determine the etiology of the first episode of a seizure in the majority of the patients. Generalized-onset seizures were the most common. Febrile seizures, epilepsy syndrome, CNS infections, vascular lesions, and metabolic disorders were the main etiological factors, in that order.

Epileptic Seizure Classification Using Battle Royale Search and Rescue Optimization-Based Deep LSTM.

Epilepsy is a severe threat to society due to the treatment time, cost, and unpredictable nature of the disease, thereby imposing an urgent need for intelligent analysis. Electroencephalogram (EEG) is a commonly deployed test for detecting epilepsy that analyses the electrical activity of an individual's brain. This work proposes an optimized deep sequential model to improve the seizure classification performance based on a hybrid feature set derived from EEG signals. A novel hybridized Battle Royale Search and Rescue optimization (BRRO) algorithm is proposed for optimizing a deep learning (DL) model. Also, the proposed hybrid feature set utilizes empirical mode decomposition, variational mode decomposition, and empirical wavelet transform to capture the temporal property of the data set. The proposed method is validated using publicly available data sets. The results manifest that the proposed optimized algorithm provides better results than the other alternatives.

A medium-weight deep convolutional neural network-based approach for onset epileptic seizures classification in EEG signals.

Epileptic condition can be detected in EEG data seconds before it occurs, according to evidence. To overcome the related long-term mortality and morbidity from epileptic seizures, it is critical to make an initial diagnosis, uncover underlying causes, and avoid applicable risk factors. Progress in diagnosing onset epileptic seizures can ensure that seizures and destroyed damages are detectable at the time of manifestation. Previous seizure detection models had problems with the presence of multiple features, the lack of an appropriate signal descriptor, and the time-consuming analysis, all of which led to uncertainty and different interpretations. Deep learning has recently made tremendous progress in categorizing and detecting epilepsy. This work proposes an effective classification strategy in response to these issues. The discrete wavelet transform (DWT) is used to breakdown the EEG signal, and a deep convolutional neural network (DCNN) is used to diagnose epileptic seizures in the first phase. Using a medium-weight DCNN (mw-DCNN) architecture, we use a preprocess phase to improve the decision-maker method. The proposed approach was tested on the CHEG-MIT Scalp EEG database's collected EEG signals. The results of the studies reveal that the mw-DCNN algorithm produces proper classification results under various conditions. To solve the uncertainty challenge, K-fold cross-validation was used to assess the algorithm's repeatability at the test level, and the accuracies were evaluated in the range of 99%-100%. The suggested structure can assist medical specialistsin analyzing epileptic seizures' EEG signals more precisely.

Spatiotemporal analysis of interictal EEG for automated seizure detection and classification

ObjectiveSeizure type classification is important as therapy differs for different epilepsy subtypes.Currently, skilled neurologists classifyseizuresbased on visual analysis. However, manual EEG inspection is time-consuming, laborious,subjective, and prone to misclassification due to artifacts andEEGvariability. This work aims to address these limitations. MethodsIn this work, a quick, robust, and accurate spatiotemporal analytical algorithm is developed to classify epileptic seizures.TheEEG dataset is sampled at 125 Hz using aNicolet EEG system.Robust preprocessing, feature extraction, andoptimal classifiers captured IEDs (Interictal Epileptiform Discharges), includingspikes, sharps, slowwaves, and Spike-Wave Discharges (SWD). ResultsThe developed classifier resultsarevalidated againstclinicalimpressionsprovided by experienced epileptologists. Thealgorithm automatically classifies the EEG datainto four types: normal, focal, generalized, and absence, with 93.18 % accuracy (n = 88). ConclusionTheresultssuggest a novel way toscreen epileptic subjects without false positives (accuracy: 94.32 %, n = 88) and tentatively identify the seizure type. Blind validation further confirms the generalizability of the classifier (accuracy: 90.90 %, n = 11). SignificanceThe developed algorithm reduces the workload of neurologists for epilepsy screening and identifies seizure onset zone, temporal spread, and overall scalp distribution of epileptic activities.