Localization Of Epileptic Foci Research Articles

Localization of epileptic focus in children with intractable epilepsy: correlation between Tc-99m HMPAO brain-perfusion SPECT, traditional MRI, and EEG

Localization of epileptic focus in children with intractable epilepsy: correlation between Tc-99m HMPAO brain-perfusion SPECT, traditional MRI, and EEG

Stereo-electroencephalography (SEEG) : The New Frontier in Localization of Epileptic Foci

Stereo-electroencephalography (SEEG) : The New Frontier in Localization of Epileptic Foci

Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation.

Accurate identification of high-frequency oscillation (HFO) is an important prerequisite for precise localization of epileptic foci and good prognosis of drug-refractory epilepsy. Exploring a high-performance automatic detection method for HFOs can effectively help clinicians reduce the error rate and reduce manpower. Due to the limited analysis perspective and simple model design, it is difficult to meet the requirements of clinical application by the existing methods. Therefore, an end-to-end bi-branch fusion model is proposed to automatically detect HFOs. With the filtered band-pass signal (signal branch) and time-frequency image (TFpic branch) as the input of the model, two backbone networks for deep feature extraction are established, respectively. Specifically, a hybrid model based on ResNet1d and long short-term memory (LSTM) is designed for signal branch, which can focus on both the features in time and space dimension, while a ResNet2d with a Convolutional Block Attention Module (CBAM) is constructed for TFpic branch, by which more attention is paid to useful information of TF images. Then the outputs of two branches are fused to realize end-to-end automatic identification of HFOs. Our method is verified on 5 patients with intractable epilepsy. In intravalidation, the proposed method obtained high sensitivity of 94.62%, specificity of 92.7%, and F1-score of 93.33%, and in cross-validation, our method achieved high sensitivity of 92.00%, specificity of 88.26%, and F1-score of 89.11% on average. The results show that the proposed method outperforms the existing detection paradigms of either single signal or single time-frequency diagram strategy. In addition, the average kappa coefficient of visual analysis and automatic detection results is 0.795. The method shows strong generalization ability and high degree of consistency with the gold standard meanwhile. Therefore, it has great potential to be a clinical assistant tool.

Identifying epilepsy based on machine-learning technique with diffusion kurtosis tensor.

IntroductionEpilepsy is a serious hazard to human health. Minimally invasive surgery is an extremely effective treatment to refractory epilepsy currently if the location of epileptic foci is given. However, it is challenging to locate the epileptic foci since a multitude of patients are MRI‐negative. It is well known that DKI (diffusion kurtosis imaging) can analyze the pathological changes of local tissues and other regions of epileptic foci at the molecular level. In this article, we propose a new localization way for epileptic foci based on machine‐learning method with kurtosis tensor in DKI.MethodsWe recruited 59 children with hippocampus epilepsy and 70 age‐ and sex‐matched normal controls; their T1‐weighted images and DKI were collected simultaneously. Then, the hippocampus in DKI is segmented based on a mask as a local brain region, and DKE is utilized to estimate the kurtosis tensor of each subject's hippocampus. Finally, the kurtosis tensor is fed into SVM (support vector machine) to identify epilepsy.ResultsThe classifier produced 95.24% accuracy for patient versus normal controls, which is higher than that obtained with FA (fractional anisotropy) and MK (mean kurtosis). Experimental results show that the kurtosis tensor is a kind of remarkable feature to identify epilepsy, which indicates that DKI images can act as an important biomarker for epilepsy from the view of clinical diagnosis.ConclusionAlthough the classification task for epileptic patients and normal controls discussed in this article did not directly achieve the location of epileptic foci and only identified epilepsy on certain brain region, the epileptic foci can be located with the results of identifying results on other brain regions.

18F-FDG PET/MR in focal epilepsy: A new step for improving the detection of epileptogenic lesions

PurposeHybrid PET/MR is a promising tool in focal drug-resistant epilepsy, however the additional value for the detection of epileptogenic lesions and surgical decision-making remains to be established. MethodsWe retrospectively compared 18F-FDG PET/MR images with those obtained by a previous 18F-FDG PET co-registered with MRI (PET+MR) in 25 consecutive patients (16 females, 13–60 years) investigated for focal drug-resistant epilepsy. Visual analysis was performed by two readers blinded from imaging modalities, asked to assess the technical characteristics (co-registration, quality of images), the confidence in results, the location of PET abnormalities and the presence of a structural lesion on MRI. Clinical impact on surgical strategy and outcome was assessed independently. ResultsThe location of epileptic focus was temporal in 9 patients and extra-temporal in 16 others. MRI was initially considered negative in 21 patients. PET stand-alone demonstrated metabolic abnormalities in 19 cases (76%), and the co-registration with MRI allowed the detection of 4 additional structural lesions. Compared to PET+MR, the PET/MR sensitivity was increased by 13% and new structural lesions (mainly focal cortical dysplasias) were detected in 6 patients (24%). Change of surgical decision-making was substantial for 10 patients (40%), consisting in avoiding invasive monitoring in 6 patients and modifying the planning in 4 others. Seizure-free outcome (follow-up>1 year) was obtained in 12/14 patients who underwent a cortical resection. ConclusionHybrid PET/MR may improve the detection of epileptogenic lesions, allowing to optimize the presurgical work-up and to increase the proportion of successful surgery even in the more complex cases.

PDMS-Parylene Hybrid, Flexible Micro-ECoG Electrode Array for Spatiotemporal Mapping of Epileptic Electrophysiological Activity from Multicortical Brain Regions.

Epilepsy detection and focus location are urgent issues that need to be solved in epilepsy research. A cortex conformable and fine spatial accuracy electrocorticogram (ECoG) sensor array, especially for real-time detection of multicortical functional regions and delineating epileptic focus remains a challenge. Here, we fabricated a polydimethylsiloxane (PDMS)-parylene hybrid, flexible micro-ECoG electrode array. The multiwalled carbon nanotubes (MWCNTs)/poly(3,4-ethylenedioxythiophene):poly(styrene sulfonate) (PEDOT:PSS) nanocomposite-modified electrode interface significantly improved the sensing performance with low impedance (20.68 ± 6.65 kΩ), stable phase offset, and high sensitivity. The electrophysiological activities of multicortical brain regions (somatosensory cortex, parietal association cortex, and visual cortex) were simultaneously monitored during normal and epileptic statuses. The epileptic ECoG activities spread spatiotemporally from the starting point toward the adjacent cortex. Significant variations of the waveform, power, and frequency band were observed. The ECoG potential (123 ± 23 μV) at normal status was prominently up to 417 ± 87 μV at the spike wave stage. Besides, the power for epileptic activity (11.049 ± 4.513 μW) was 10 times higher than that (1.092 ± 0.369 μW) for normal activity. In addition, the theta frequency band was found to be a characteristic frequency band of epileptic signals. These joint analysis results of multicortical regions indicated that the active micron-scale region on the parietal association cortex was more likely to be the epileptogenic focus. Cortical mapping with high spatial detail provides the accurate delineation of lesions. The flexible micro-ECoG electrode array is a powerful tool for constructing a spatiotemporal map of the cortex. It provides a technical platform for epileptic focus location, biomedical diagnosis, and brain-computer interaction.

Impact of reconstruction parameters on lesion detection and localization in joint ictal/inter-ictal SPECT reconstruction.

Previously, a joint ictal/inter-ictal SPECT reconstruction was proposed to reconstruct a differential image representing the change of brain SPECT image from an inter-ictal to an ictal study. The so-called joint method yielded better performance for epileptic foci localization than the conventional subtraction method. In this study, we evaluated the performance of different reconstruction settings of the joint reconstruction of ictal/inter-ictal SPECT data, which creates a differential image showing the difference between ictal and inter-ictal images, in lesion detection and localization in epilepsy imaging. Differential images reconstructed from phantom data using the joint and the subtraction methods were compared based on lesion detection performance (channelized Hotelling observer signal-to-noise ratio (SNRCHO) averaged across four lesion-to-background contrast levels) at the optimal iteration. The joint-initial method which was the joint method that was initialized by the subtraction method at optimal iteration was also used to reconstruct differential images. These three methods with respective optimal iteration and the subtraction method with four iterations were applied to epileptic patient datasets. A human observer lesion localization study was performed based on localization receiver operating characteristic (LROC) analysis. From the phantom study, at their respective optimal iteration, the joint method yielded an improvement in lesion detection performance over the subtraction method of 26%, which increased to 145% when using the joint-initial method. From the patient study, the joint-initial method yielded the highest area under the LROC curve as compared with those of the joint and the subtraction methods with optimal iteration and with 4 iterations (0.44 vs 0.41, 0.39 and 0.36, respectively). In lesion detection and localization, the joint method at optimal iteration outperformed the subtraction method at optimal iteration and at iteration typically used in clinical practice. Furthermore, initialization by the subtraction method improved the performance of the joint method.

Phase-Amplitude Coupling and Epileptogenic Zone Localization of Frontal Epilepsy Based on Intracranial EEG.

Objective: This study aimed to explore the characteristics of phase-amplitude coupling in patients with frontal epilepsy based on their electrocorticography data, in order to identify the localization of epileptic regions and further guide clinical resection surgery.Methods: We adopted the modulation index based on the Kullback-Leibler distance, phase-amplitude coupling co-modulogram, and time-varying phase-amplitude modulogram to explore the temporal-spatial patterns and characterization of PAC strength during the period from inter- seizure to post-seizure. Taking the resected area as the gold standard, the epileptogenic zone was located based on MI values of 7 different seizure periods, and the accuracy of localization was measured by the area under the receiver operating curve.Results: (1) The PAC in the inter- and pre-seizure periods was weak and paroxysmal, but strong PAC channels were confined more to the seizure-onset zone and resection region. PAC during the seizure period was intense and persistent, but gradually deviated from the seizure-onset zone. (2) The characteristics of coupling strength of the inter- and pre-seizure EEG can be used to accurately locate the epileptogenic zone, which is better than that in periods after the beginning of a seizure. (3) In an epileptic seizure, the preferred phases of coupling were usually in the rising branches at the pre- and early-seizure stages, while those in the middle- and terminal-seizure were usually in the falling branch. We thus speculate that the coupling occurred in the rising branch can promote the recruitment of abnormal discharge, while the coupling occurred in the falling branch can inhibit the abnormal discharge.Conclusion: The findings suggest that the phase-amplitude coupling during inter- and pre-seizure is a promising marker of epileptic focus location. The preferred phase of coupling changed regularly with the time of epileptic seizure, suggesting that the surge and suppression of abnormal discharges are related to different phases.

Dynamic FDG-PET in localization of focal epilepsy: A pilot study

Epilepsy surgery remains underutilized, in part because non-invasive methods of potential seizure foci localization are inadequate. We used high-resolution, parametric quantification from dynamic 2-[18F] fluoro-2-deoxy-d-glucose positron emission tomography (dFDG-PET) imaging to locate hypometabolic foci in patients whose standard clinical static PET images were normal. We obtained dFDG-PET brain images with simultaneous EEG in a one-hour acquisition on seven patients with no MRI evidence of focal epilepsy to record uptake and focal radiation decay. Images were attenuation- and motion-corrected and co-registered with high-resolution T1-weighted patient MRI and segmented into 18 regions of interest (ROI) per hemisphere. Tracer uptake was calibrated with a model corrected blood input function with partial volume (PV) corrections to generate tracer parametric maps compared between mean radiation values between hemispheres with z-scores. We identified ROI with the lowest negative z scores (<−1.65 SD) as hypometabolic. Dynamic 2-[18F] fluoro-2-deoxy-d-glucose positron emission tomography ( found focal regions of altered metabolism in all cases in which standard clinical FDG-PET found no abnormalities. This pilot study of dynamic FDG-PET suggests that further research is merited to evaluate whether glucose dynamics offer improved clinical utility for localization of epileptic foci over standard static techniques.

EEG Signal Connectivity for Characterizing Interictal Activity in Patients With Mesial Temporal Lobe Epilepsy.

Over the last decade, several methods for analysis of epileptiform signals in electroencephalography (EEG) have been proposed. These methods mainly use EEG signal features in either the time or the frequency domain to separate regular, interictal, and ictal brain activity. The aim of this work was to evaluate the feasibility of using functional connectivity (FC) based feature extraction methods for the analysis of epileptiform discharges in EEG signals. These signals were obtained from EEG-fMRI sessions of 10 patients with mesial temporal lobe epilepsy (MTLE) with unilateral hippocampal atrophy. The connectivity functions investigated were motif synchronization, imaginary coherence, and magnitude squared coherence in the alpha, beta, and gamma bands of the EEG. EEG signals were sectioned into 1-s epochs and classified according to (using neurologist markers): activity far from interictal epileptiform discharges (IED), activity immediately before an IED and, finally, mid-IED activity. Connectivity matrices for each epoch for each FC function were built, and graph theory was used to obtain the following metrics: strength, cluster coefficient, betweenness centrality, eigenvector centrality (both local and global), and global efficiency. The statistical distributions of these metrics were compared among the three classes, using ANOVA, for each FC function. We found significant differences in all global (p < 0.001) and local (p < 0.00002) graph metrics of the far class compared with before and mid for motif synchronization on the beta band; local betweenness centrality also pointed to a degree of lateralization on the frontotemporal structures. This analysis demonstrates the potential of FC measures, computed using motif synchronization, for the characterization of epileptiform activity of MTLE patients. This methodology may be helpful in the analysis of EEG-fMRI data applied to epileptic foci localization. Nonetheless, the methods must be tested with a larger sample and with other epileptic phenotypes.

Magnetoencephalography for epileptic focus localization based on Tucker decomposition with ripple window.

AimsTo improve the Magnetoencephalography (MEG) spatial localization precision of focal epileptic.Methods306‐channel simulated or real clinical MEG is estimated as a lower‐dimensional tensor by Tucker decomposition based on Higher‐order orthogonal iteration (HOOI) before the inverse problem using linearly constraint minimum variance (LCMV). For simulated MEG data, the proposed method is compared with dynamic imaging of coherent sources (DICS), multiple signal classification (MUSIC), and LCMV. For clinical real MEG of 31 epileptic patients, the ripples (80–250 Hz) were detected to compare the source location precision with spikes using the proposed method or the dipole‐fitting method.ResultsThe experimental results showed that the positional accuracy of the proposed method was higher than that of LCMV, DICS, and MUSIC for simulation data. For clinical real MEG data, the positional accuracy of the proposed method was higher than that of dipole‐fitting regardless of whether the time window was ripple window or spike window. Also, the positional accuracy of the ripple window was higher than that of the spike window regardless of whether the source location method was the proposed method or the dipole‐fitting method. For both shallow and deep sources, the proposed method provided effective performance.ConclusionTucker estimation of MEG for source imaging by ripple window is a promising approach toward the presurgical evaluation of epileptics.

Hybrid Convolutional Neural Network for Localization of Epileptic Focus Based on iEEG.

Epileptic focus localization by analysing intracranial electroencephalogram (iEEG) plays a critical role in successful surgical therapy of resection of the epileptogenic lesion. However, manual analysis and classification of the iEEG signal by clinicians are arduous and time-consuming and excessively depend on the experience. Due to individual differences of patients, the iEEG signal from different patients usually shows very diverse features even if the features belong to the same class. Accordingly, automatic detection of epileptic focus is required to improve the accuracy and to shorten the time for treatment. In this paper, we propose a novel feature fusion-based iEEG classification method, a deep learning model termed Time-Frequency Hybrid Network (TF-HybridNet), in which short-time Fourier transform (STFT) and 1d convolution layers are performed on the input iEEG in parallel to extract features of the time-frequency domain and feature maps. And then, the time-frequency features and feature maps are fused and fed to a 2d convolutional neural network (CNN). We used the Bern-Barcelona iEEG dataset for evaluating the performance of TF-HybridNet, and the experimental results show that our approach is able to differentiate the focal from nonfocal iEEG signal with an average classification accuracy of 94.3% and demonstrates an improved accuracy rate compared to the model using only STFT or one-dimensional convolutional layers as feature extraction.

Epileptic focus location in the cerebral cortex using linear techniques and complex networks

The epileptic focus is an area of the cerebral cortex that is essential for the generation of seizures. It is the region where epileptic seizures begin, or the site with the most ictal activity, also known as the epileptogenic zone. On a clinical approach, the identification and study of the epileptic focus can aid in the diagnosis and treatment of patients with epilepsy; thereby, the automatic determination of its quantitative characteristics could be helpful. In this paper, we present a methodology based on clinical guidelines for the automatic identification of the epileptic focus and its dynamics using complex networks and linear techniques. This methodology identifies the EEG channels with the most frequent and lasting ictal events. Furthermore, the propagation of seizures on the cortex can be determined as well as the EEG channels through which seizures propagate. Our approach leads to estimate the connectivity parameters of the cerebral networks generated during seizure events such as the degree and clustering coefficient of the network’s nodes with the highest prevalence. The efficiency of seizure identification was computed in about 97.2%. This methodology allows to identify the zone with the highest ictal activity and its dynamical characteristics, and whether the identified channels are located in the same region in the cerebral cortex or if they are contiguous. All this information could help neurologists in the diagnosis and analysis of the dynamics of epileptic seizures in case the primary studies were non-conclusive.

Narrative review of epilepsy: getting the most out of your neuroimaging.

Neuroimaging represents an important step in the evaluation of pediatric epilepsy. The crucial role of brain imaging in the diagnosis, follow-up and presurgical assessment of patients with epilepsy is noted and has to be familiar to all neuroradiologists and trainees approaching pediatric brain imaging. Morphological qualitative imaging shows the majority of cerebral lesions/alterations underlying focal epilepsy and can highlight some features which are useful in the differential diagnosis of the different types of epilepsy. Recent advances in MRI acquisitions including diffusion-weighted imaging (DWI), post-acquisition image processing techniques, and quantification of imaging data are increasing the accuracy of lesion detection during the last decades. Functional MRI (fMRI) can be really useful and helps to identify cortical eloquent areas that are essential for language, motor function, and memory, and diffusion tensor imaging (DTI) can reveal white matter tracts that are vital for these functions, thus reducing the risk of epilepsy surgery causing new morbidities. Also positron emission tomography (PET), single photon emission computed tomography (SPECT), simultaneous electroencephalogram (EEG) and fMRI, and electrical and magnetic source imaging can be used to assess the exact localization of epileptic foci and help in the design of intracranial EEG recording strategies. The main role of these “hybrid” techniques is to obtain quantitative and qualitative informations, a necessary step to evaluate and demonstrate the complex relationship between abnormal structural and functional data and to manage a “patient-tailored” surgical approach in epileptic patients.

A deep learning framework for 18F-FDG PET imaging diagnosis in pediatric patients with temporal lobe epilepsy

PurposeEpilepsy is one of the most disabling neurological disorders, which affects all age groups and often results in severe consequences. Since misdiagnoses are common, many pediatric patients fail to receive the correct treatment. Recently, 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) imaging has been used for the evaluation of pediatric epilepsy. However, the epileptic focus is very difficult to be identified by visual assessment since it may present either hypo- or hyper-metabolic abnormality with unclear boundary. This study aimed to develop a novel symmetricity-driven deep learning framework of PET imaging for the identification of epileptic foci in pediatric patients with temporal lobe epilepsy (TLE).MethodsWe retrospectively included 201 pediatric patients with TLE and 24 age-matched controls who underwent 18F-FDG PET-CT studies. 18F-FDG PET images were quantitatively investigated using 386 symmetricity features, and a pair-of-cube (PoC)-based Siamese convolutional neural network (CNN) was proposed for precise localization of epileptic focus, and then metabolic abnormality level of the predicted focus was calculated automatically by asymmetric index (AI). Performances of the proposed framework were compared with visual assessment, statistical parametric mapping (SPM) software, and Jensen-Shannon divergence-based logistic regression (JS-LR) analysis.ResultsThe proposed deep learning framework could detect the epileptic foci accurately with the dice coefficient of 0.51, which was significantly higher than that of SPM (0.24, P < 0.01) and significantly (or marginally) higher than that of visual assessment (0.31–0.44, P = 0.005–0.27). The area under the curve (AUC) of the PoC classification was higher than that of the JS-LR (0.93 vs. 0.72). The metabolic level detection accuracy of the proposed method was significantly higher than that of visual assessment blinded or unblinded to clinical information (90% vs. 56% or 68%, P < 0.01).ConclusionThe proposed deep learning framework for 18F-FDG PET imaging could identify epileptic foci accurately and efficiently, which might be applied as a computer-assisted approach for the future diagnosis of epilepsy patients.Trial registrationNCT04169581. Registered November 13, 2019Public site: https://clinicaltrials.gov/ct2/show/NCT04169581

A study of medial and lateral temporal lobe epilepsy based on stereoelectroencephalography.

BackgroundPatients with temporal lobe epilepsy (TLE) originating from different seizure onset zones had distinct electrophysiological characteristics and surgical outcomes. In this study, we aimed to investigate the relationship between the origin and prognosis of TLE, and the stereoelectroencephalography (SEEG) features.MethodsThirty patients with TLE, who underwent surgical treatment in our functional neurosurgery department from January 2016 to December 2017, were enrolled in this study. All patients underwent anterior temporal lobectomy after an invasive pre-operative evaluation with SEEG. Depending on the epileptic focus location, patients were divided into those with medial temporal lobe seizures (MTLS) and those with lateral temporal lobe seizures (LTLS). The Engel classification was used to evaluate operation effectiveness, and the Kaplan-Meier analysis was used to detect seizure-free duration.ResultsThe mean follow-up time was 25.7 ± 4.8 months. Effectiveness was 63.3% for Engel I (n = 19), 13.3% for Engel II, 3.3% for Engel III, and 20.0% for Engel IV. According to the SEEG, 60.0% (n = 18) had MTLS, and 40.0% (n = 12) had LTLS. Compared with the MTLS group, the operation age of those with LTLS was significantly greater (26.9 ± 6.9 vs. 29.9 ± 12.5 years, t = −0.840, P = 0.009) with longer epilepsy duration (11.9 ± 6.0 vs. 17.9 ± 12.1 years, t = −1.801, P = 0.038). Patients with MTLS had a longer time interval between ictal onset to seizure (67.3 ± 59.1 s vs. 29.3 ± 24.4 s, t = 2.017, P = 0.008). The most common SEEG ictal pattern was a sharp/spike-wave rhythm in the MTLS group (55.6%) and low-voltage fast activity in the LTLS group (58.3%). Compared with the LTLS group, patients with MTLS had a more favorable prognosis (41.7% vs. 77.8%, P = 0.049). Post-operative recurrence was more likely to occur within three months after the operation for both groups, and there appeared to be a stable long-term outcome.ConclusionPatients with MTLS, who accounted for three-fifths of patients with TLE, showed a more favorable surgical outcome.

Identifying Epilepsy Based on Deep Learning Using DKI Images.

Epilepsy is a serious hazard to human health. Minimally invasive surgery is currently an extremely effective treatment to refractory epilepsy. However, it is challenging to localize the lesion for most patients because they are MRI negative. The identification of epileptic foci in local brain region will be helpful to the localization of epileptic foci because we can infer whether there is a lesion from the results of the classification. For the sake of simplicity and the data we collected, only the hippocampus was segmented as a local brain region and classified in this paper. We recruited 59 children with hippocampus epilepsy and 70 age- and sex-matched normal controls, and diffusion kurtosis images (DKI) for all subjects were collected because DKI can understand the pathological changes of local tissues and other regions of epileptic foci at the molecular level. Then, a mask of hippocampus was made to segment the hippocampus of FA, MD, and MK images for all subjects, which are the parameter images of DKI and were used to perform the independent-sample t-test and the classification task. At last, a convolutional neural network (CNN) based on transfer learning technique was developed to extract features of FA, MD, MK, and the fusion of FA and MK, and support vector machine was employed to classify epilepsy and normal control. Finally, the classifier produced 90.8% accuracy for patient vs. normal controls. Experimental results showed that the features extraction based on CNN is very effective, and the high accuracy of classification means that FA and MK are two remarkable features to identify epilepsy, which indicates that DKI images can act as an important biomarker for epilepsy from the point of view of clinical diagnosis.

Localization of epileptic seizure focus by computerized analysis of fMRI recordings

By computerized analysis of cortical activity recorded via fMRI for pediatric epilepsy patients, we implement algorithmic localization of epileptic seizure focus within one of eight cortical lobes. Our innovative machine learning techniques involve intensive analysis of large matrices of mutual information coefficients between pairs of anatomically identified cortical regions. Drastic selection of pairs of regions with biologically significant inter-connectivity provides efficient inputs for our multi-layer perceptron (MLP) classifier. By imposing rigorous parameter parsimony to avoid overfitting, we construct a small-size MLP with very good percentages of successful classification.

Early prediction of encephalopathic transformation in children with benign epilepsy with centro-temporal spikes

BackgroundMost children with Benign epilepsy with centro-temporal spikes (BECTS) undergo remission during late adolescence and do not require treatment. In a small group of patients, the condition may evolve to encephalopathic syndromes including epileptic encephalopathy with continuous spike-and-wave during sleep (ECSWS), or Landau-Kleffner Syndrome (LKS). Development of prediction models for early identification of at-risk children is of utmost importance. AimTo develop a predictive model of encephalopathic transformation using data-driven approaches, reveal complex interactions to identify potential risk factors. MethodsData were collected from a cohort of 91 patients diagnosed with BECTS treated between the years 2005–2017 at a pediatric neurology institute. Data on the initial presentation was collected based on a novel BECTS ontology and used to discover potential risk factors and to build a predictive model. Statistical and machine learning methods were compared. ResultsA subgroup of 18 children had encephalopathic transformation. The least absolute shrinkage and selection operator (LASSO) regression Model with Elastic Net was able to successfully detect children with ECSWS or LKS. Sensitivity and specificity were 0.83 and 0.44. The most notable risk factors were fronto-temporal and temporo-parietal localization of epileptic foci, semiology of seizure involving dysarthria or somatosensory auras. ConclusionNovel prediction model for early identification of patients with BECTS at risk for ECSWS or LKS. This model can be used as a screening tool and assist physicians to consider special management for children predicted at high-risk. Clinical application of machine learning methods opens new frontiers of personalized patient care and treatment.

A new approach for automatic detection of focal EEG signals using wavelet packet decomposition and quad binary pattern method

A comprehensive feature representation for electroencephalogram (EEG) signal to achieve effective epileptic focus localization using a one-dimensional quad binary pattern (QBP) is proposed in this work. The wavelet packet decomposition (WPD), entropies, and QBP methods are applied to EEG signals for identifying the non-focal and focal classes. The proposed approach consists of three strategies, based on the local pattern transformation of EEG signals using QBP. The time-domain EEG signals are transformed into the QBP domain, and histogram features are extracted in the first strategy. Secondly, the nonlinear features like sample entropy, log energy entropy, fuzzy entropy, permutation entropy, and approximate entropy are computed from the EEG signals and concatenated with the QBP features. In the third strategy, the EEG signals are decomposed into sub-bands by employing WPD, and histogram features based on QBP are extracted from each sub-band. The computed feature sets are used to classify the non-focal and focal EEG signals using an artificial neural network (ANN). For the selection of best settings in WPD, the EEG signals are decomposed in seven commonly used wavelet families with different decomposition levels, and the wavelet family providing the highest classification accuracy with the minimal computational cost is found out. The proposed approach is validated using the widely recognized Bern-Barcelona EEG dataset. The proposed method achieved a classification accuracy of 95.74 % on this dataset using the proposed WPD based QBP approach. In conclusion, the proposed approach is efficient in identifying the focal EEG signals and can be useful for accurate detection of focal regions in the epilepsy diagnosis.