Search

Background: The localization of seizure onset zones (SOZs) is a critical step before the surgical treatment of epilepsy. Methods and Results: In this paper, we propose an SOZ detection method based on convolutional neural networks and EEG signals. This method aims to locate SOZs through the seizure status of each channel in multi-channel EEG signals. First, we preprocess the data with filtering, segmentation, resampling, and standardization to ensure their quality and consistency. Then, the single-channel UCI epilepsy seizure recognition dataset is used to train and test the convolutional neural network (CNN) model, achieving an accuracy of 98.70%, a sensitivity of 97.53%, and a specificity of 98.98%. Next, the multi-channel clinical EEG dataset collected by a hospital is divided into 21 single-channel site datasets and input into the model for detection, and then the seizure results of 21 sites per second are obtained. Finally, the seizure sites are visualized through the international 10–20 system electrode distribution map, diagrams of the change process of the seizure sites during seizures are drawn, and patients' SOZs are located. Conclusions: Our proposed method well classifies seizure and non-seizure data and successfully locates SOZs by detecting the seizure results of 21 sites through a single-channel model. This study can effectively assist doctors in locating the SOZs of patients and provide help for the diagnosis and treatment of epilepsy. [ABSTRACT FROM AUTHOR]

Abstract Methods to quantify cortical hyperexcitability are of enormous interest for mapping epileptic networks in patients with focal epilepsy. We hypothesize that, in the resting state, cortical hyperexcitability increases firing-rate correlations between neuronal populations within seizure onset zones (SOZs). This hypothesis predicts that in the gamma frequency band (40–200 Hz), amplitude envelope correlations (AECs), a relatively straightforward measure of functional connectivity, should be elevated within SOZs compared to other areas. To test this prediction, we analyzed archived samples of interictal electrocorticographic (ECoG) signals recorded from patients who became seizure-free after surgery targeting SOZs identified by multiday intracranial recordings. We show that in the gamma band, AECs between nodes within SOZs are markedly elevated relative to those elsewhere. AEC-based node strength, eigencentrality, and clustering coefficient are also robustly increased within the SOZ with maxima in the low-gamma band (permutation test Z-scores > 8) and yield moderate discriminability of the SOZ using ROC analysis (maximal mean AUC ~ 0.73). By contrast to AECs, phase locking values (PLVs), a measure of narrow-band phase coupling across sites, and PLV-based graph metrics discriminate the seizure onset nodes weakly. Our results suggest that gamma band AECs may provide a clinically useful marker of cortical hyperexcitability in focal epilepsy.

Methods to quantify cortical hyperexcitability are of enormous interest for mapping epileptic networks in patients with focal epilepsy. We hypothesize that, in the resting state, cortical hyperexcitability increases firing-rate correlations between neuronal populations within seizure onset zones (SOZs). This hypothesis predicts that in the gamma frequency band (40–200 Hz), amplitude envelope correlations (AECs), a relatively straightforward measure of functional connectivity, should be elevated within SOZs compared to other areas. To test this prediction, we analyzed archived samples of interictal electrocorticographic (ECoG) signals recorded from patients who became seizure-free after surgery targeting SOZs identified by multiday intracranial recordings. We show that in the gamma band, AECs between nodes within SOZs are markedly elevated relative to those elsewhere. AEC-based node strength, eigencentrality, and clustering coefficient are also robustly increased within the SOZ with maxima in the low-gamma band (permutation test Z-scores > 8) and yield moderate discriminability of the SOZ using ROC analysis (maximal mean AUC ~ 0.73). By contrast to AECs, phase locking values (PLVs), a measure of narrow-band phase coupling across sites, and PLV-based graph metrics discriminate the seizure onset nodes weakly. Our results suggest that gamma band AECs may provide a clinically useful marker of cortical hyperexcitability in focal epilepsy. [ABSTRACT FROM AUTHOR]

Background: The localization of seizure onset zones (SOZs) is a critical step before the surgical treatment of epilepsy. Methods and Results: In this paper, we propose an SOZ detection method based on convolutional neural networks and EEG signals. This method aims to locate SOZs through the seizure status of each channel in multi-channel EEG signals. First, we preprocess the data with filtering, segmentation, resampling, and standardization to ensure their quality and consistency. Then, the single-channel UCI epilepsy seizure recognition dataset is used to train and test the convolutional neural network (CNN) model, achieving an accuracy of 98.70%, a sensitivity of 97.53%, and a specificity of 98.98%. Next, the multi-channel clinical EEG dataset collected by a hospital is divided into 21 single-channel site datasets and input into the model for detection, and then the seizure results of 21 sites per second are obtained. Finally, the seizure sites are visualized through the international 10–20 system electrode distribution map, diagrams of the change process of the seizure sites during seizures are drawn, and patients’ SOZs are located. Conclusions: Our proposed method well classifies seizure and non-seizure data and successfully locates SOZs by detecting the seizure results of 21 sites through a single-channel model. This study can effectively assist doctors in locating the SOZs of patients and provide help for the diagnosis and treatment of epilepsy.

Stereoelectroencephalography (SEEG) offers unique neural data from in-depth brain structures with fine temporal resolutions to better investigate the origin of epileptic brain activities. Although oscillatory patterns from different frequency bands and functional connectivity computed from the SEEG datasets are employed to study the epileptic zones, direct electrical stimulation-evoked electrophysiological recordings of synaptic responses, namely cortical-cortical evoked potentials (CCEPs), from the same SEEG electrodes are not explored for the localization of epileptic zones. Here we proposed a two-stream model with unsupervised learning and graph convolutional network tailored to the SEEG and CCEP datasets in individual patients to perform localization of epileptic zones. We compared our localization results with the clinically marked electrode sites determined for surgical resections. Our model had good classification capability when compared to other state-of-the-art methods. Furthermore, based on our prediction results we performed group-level brain-area mapping analysis for temporal, frontal and parietal epilepsy patients and found that epileptic and non-epileptic brain networks were distinct in patients with different types of focal epilepsy. Our unsupervised data-driven model provides personalized localization analysis for the epileptic zones. The epileptic and non-epileptic brain areas disclosed by the prediction model provide novel insights into the network-level pathological characteristics of epilepsy.

This paper devises a new detector based on singular value decomposition (SVD) and improved fuzzy c -means (FCM) clustering for automatically detecting high-frequency oscillations (HFOs) that are used for localizing seizure onset zones (SOZs) in epilepsy. First, HFO candidates (HFOCs) are obtained by the root mean square method. Next, a time-frequency analysis method is applied to eliminate spikes from HFOCs, which consists of the Stockwell transform, SVD combined with the k -medoids clustering algorithm, Stockwell inverse transform, and threshold method. Then, four kinds of distinctive features, i.e. mean singular values, line lengths, power ratios and spectral centroid of the rest of HFOCs, are extracted and augmented as feature vectors. These vectors are used as the input of the improved FCM clustering algorithm optimized by the simulated annealing algorithm combined with the genetic algorithm. Finally, the localization of SOZs is accomplished based on the concentrations of the detected HFOs. The superiority of the devised detector over other five existing ones is demonstrated by comparing their localization performance. [ABSTRACT FROM AUTHOR]

• SEEG data from a combination of awake, sleep and seizure states and CCEP mapping. • Graph representation incorporating oscillatory and synaptic connectivity features. • A two-stream model with unsupervised learning to identify epileptic zones accurately. • Brain-area specific functional network analysis reveals epileptic hubs. Stereoelectroencephalography (SEEG) offers unique neural data from in-depth brain structures with fine temporal resolutions to better investigate the origin of epileptic brain activities. Although oscillatory patterns from different frequency bands and functional connectivity computed from the SEEG datasets are employed to study the epileptic zones, direct electrical stimulation-evoked electrophysiological recordings of synaptic responses, namely cortical-cortical evoked potentials (CCEPs), from the same SEEG electrodes are not explored for the localization of epileptic zones. Here we proposed a two-stream model with unsupervised learning and graph convolutional network tailored to the SEEG and CCEP datasets in individual patients to perform localization of epileptic zones. We compared our localization results with the clinically marked electrode sites determined for surgical resections. Our model had good classification capability when compared to other state-of-the-art methods. Furthermore, based on our prediction results we performed group-level brain-area mapping analysis for temporal, frontal and parietal epilepsy patients and found that epileptic and non-epileptic brain networks were distinct in patients with different types of focal epilepsy. Our unsupervised data-driven model provides personalized localization analysis for the epileptic zones. The epileptic and non-epileptic brain areas disclosed by the prediction model provide novel insights into the network-level pathological characteristics of epilepsy. [ABSTRACT FROM AUTHOR]

Background: To study the characters of high-frequency oscillations (HFOs) in the seizure onset zones (SOZ) and the nonseizure onset zones (NSOZ) in the electrocorticography (ECoG) of patients with neocortical epilepsy. Methods: Only patients with neocortical epilepsy who were seizure-free after surgery as determined with ECoG were included. We selected patients with normal magnetic resonance imaging before surgery in order to avoid the influence of HFOs by other lesions. Three minutes preictal and 10 min interictal ECoG as recorded in 39 channels in the SOZ and 256 channels in the NSOZ were analyzed. Ripples and fast ripples (FRs) were analyzed by Advanced Source Analysis software (ASA, The Netherlands). Average duration of HFOs was analyzed in SOZ and NSOZ separately. Results: For ripples, the permillage time occupied by HFOs was 0.83 in NSOZ and 1.17 in SOZ during the interictal period. During preictal period, they were 2.02 in NSOZ and 7.93 in SOZ. For FRs, the permillage time occupied by HFOs was 0.02 in NSOZ and 0.42 in SOZ during the interictal period. During preictal period, they were 0.03 in NSOZ and 2 in SOZ. Conclusions: High-frequency oscillations are linked to SOZ in neocortical epilepsy. Our study demonstrates the prevalent occurrence of HFOs in SOZ. More and more burst of HFOs, especially FRs, means the onset of seizures.

• The Stockwell entropy based on Hilbert transform detects events of interest (EoIs) effectively compared with simple Hilbert transform by accurately detecting both the EoI and non-EoI. • The power method based on Shannon-entropy-based complex Morlet wavelet transform obtains channels of interests with lower computational complexity than the power spectral density method based on SECMWT does. • The adaptive-genetic-algorithm-based matching pursuit (AGA-MP) integrated with the k-medoids clustering method is found to detect high-frequency oscillations (HFOs) more effectively than the AGA-MP method by discerning HFOs from normal activity and artifacts. • The devised new localization method has superiority in improving the localization performance (i.e. sensitivity and specificity) over some existing methods. High-frequency oscillations (HFOs) are spontaneous electroencephalogram patterns that have been regarded as potential biomarkers of epileptic seizure onset zones (SOZs). Accurately detected HFOs are used to localize SOZs, which is crucial for the presurgical assessment. Since the visual marking of HFOs is time-consuming, a method is desirable to automatically detect HFOs for localizing SOZs in clinical practice. However, the existing methods cannot obtain satisfactory performance, which are not suitable for clinical application. In order to solve this problem, we present a new localization method for epileptic SOZs in this study. Firstly, a threshold method is used to detect events of interest (EoIs). Secondly, a time-frequency analysis method is adopted to acquire channels of interest (CoIs) by calculating the average power of EoIs on each channel. Then, the k -medoids clustering method is employed to detect HFOs of CoIs. Finally, the concentrations of detected HFOs are used to localize SOZs. The superiority of our localization method is demonstrated by comparing its sensitivity and specificity with some existing methods. [ABSTRACT FROM AUTHOR]