iEEG Signals Research Articles

Combination of Channel Reordering Strategy and Dual CNN-LSTM for Epileptic Seizure Prediction Using Three iEEG Datasets.

Intracranial electroencephalogram (iEEG) signals are generally recorded using multiple channels, and channel selection is therefore a significant means in studying iEEG-based seizure prediction. For n channels, [Formula: see text] channel cases can be generated for selection. However, by this means, an increase in n can cause an exponential increase in computational consumption, which may result in a failure of channel selection when n is too large. Hence, it is necessary to explore reasonable channel selection strategies under the premise of controlling computational consumption and ensuring high classification accuracy. Given this, we propose a novel method of channel reordering strategy combined with dual CNN-LSTM for effectively predicting seizures. First, for each patient with n channels, interictal and preictal iEEG samples from each single channel are input into the CNN-LSTM model for classification. Then, the F1-score of each single channel is calculated, and the channels are reordered in descending order according to the size of F1-scores (channel reordering strategy). Next, iEEG signals with an increasing number of channels are successively fed into the CNN-LSTM model for classification again. Finally, according to the classification results from n channel cases, the channel case with the highest classification rate is selected. Our method is evaluated on the three iEEG datasets: the Freiburg, the SWEC-ETHZ and the American Epilepsy Society Seizure Prediction Challenge (AES-SPC). At the event-based level, the sensitivities of 100%, 100% and 90.5%, and the false prediction rates (FPRs) of 0.10/h, 0/h and 0.47/h, are achieved for the three datasets, respectively. Moreover, compared to an unspecific random predictor, our method also shows a better performance for all patients and dogs from the three datasets. At the segment-based level, the sensitivities-specificities-accuracies-AUCs of 88.1%-94.0%-93.5%-0.9101, 99.1%-99.7%-99.6%-0.9935, and 69.2%-79.9%-78.2%-0.7373, are attained for the three datasets, respectively. Our method can effectively predict seizures and address the challenge of an excessive number of channels during channel selection.

Rényi entropy-complexity causality space: a novel neurocomputational tool for detecting scale-free features in EEG/iEEG data.

Scale-free brain activity, linked with learning, the integration of different time scales, and the formation of mental models, is correlated with a metastable cognitive basis. The spectral slope, a key aspect of scale-free dynamics, was proposed as a potential indicator to distinguish between different sleep stages. Studies suggest that brain networks maintain a consistent scale-free structure across wakefulness, anesthesia, and recovery. Although differences in anesthetic sensitivity between the sexes are recognized, these variations are not evident in clinical electroencephalographic recordings of the cortex. Recently, changes in the slope of the power law exponent of neural activity were found to correlate with changes in Rényi entropy, an extended concept of Shannon's information entropy. These findings establish quantifiers as a promising tool for the study of scale-free dynamics in the brain. Our study presents a novel visual representation called the Rényi entropy-complexity causality space, which encapsulates complexity, permutation entropy, and the Rényi parameter q. The main goal of this study is to define this space for classical dynamical systems within theoretical bounds. In addition, the study aims to investigate how well different time series mimicking scale-free activity can be discriminated. Finally, this tool is used to detect dynamic features in intracranial electroencephalography (iEEG) signals. To achieve these goals, the study implementse the Bandt and Pompe method for ordinal patterns. In this process, each signal is associated with a probability distribution, and the causal measures of Rényi entropy and complexity are computed based on the parameter q. This method is a valuable tool for analyzing simulated time series. It effectively distinguishes elements of correlated noise and provides a straightforward means of examining differences in behaviors, characteristics, and classifications. For the iEEG experimental data, the REM state showed a greater number of significant sex-based differences, while the supramarginal gyrus region showed the most variation across different modes and analyzes. Exploring scale-free brain activity with this framework could provide valuable insights into cognition and neurological disorders. The results may have implications for understanding differences in brain function between the sexes and their possible relevance to neurological disorders.

Text and image generation from intracranial electroencephalography using an embedding space for text and images

Objective. Invasive brain–computer interfaces (BCIs) are promising communication devices for severely paralyzed patients. Recent advances in intracranial electroencephalography (iEEG) coupled with natural language processing have enhanced communication speed and accuracy. It should be noted that such a speech BCI uses signals from the motor cortex. However, BCIs based on motor cortical activities may experience signal deterioration in users with motor cortical degenerative diseases such as amyotrophic lateral sclerosis. An alternative approach to using iEEG of the motor cortex is necessary to support patients with such conditions. Approach. In this study, a multimodal embedding of text and images was used to decode visual semantic information from iEEG signals of the visual cortex to generate text and images. We used contrastive language-image pretraining (CLIP) embedding to represent images presented to 17 patients implanted with electrodes in the occipital and temporal cortices. A CLIP image vector was inferred from the high-γ power of the iEEG signals recorded while viewing the images. Main results. Text was generated by CLIPCAP from the inferred CLIP vector with better-than-chance accuracy. Then, an image was created from the generated text using StableDiffusion with significant accuracy. Significance. The text and images generated from iEEG through the CLIP embedding vector can be used for improved communication.

A multiscale symbolic approach to decoding delta and ripple oscillation bands as biomarkers for epileptiform discharges.

We use a multiscale symbolic approach to study the complex dynamics of temporal lobe refractory epilepsy employing high-resolution intracranial electroencephalogram (iEEG). We consider the basal and preictal phases and meticulously analyze the dynamics across frequency bands, focusing on high-frequency oscillations up to 240 Hz. Our results reveal significant periodicities and critical time scales within neural dynamics across frequency bands. By bandpass filtering neural signals into delta, theta, alpha, beta, gamma, and ripple high-frequency bands (HFO), each associated with specific neural processes, we examine the distinct nonlinear dynamics. Our method introduces a reliable approach to pinpoint intrinsic time lag scales τ within frequency bands of the basal and preictal signals, which are crucial for the study of refractory epilepsy. Using metrics such as permutation entropy (H), Fisher information (F), and complexity (C), we explore nonlinear patterns within iEEG signals. We reveal the intrinsic τmax that maximize complexity within each frequency band, unveiling the nonlinear subtle patterns of the temporal structures within the basal and preictal signal. Examining the H×F and C×F values allows us to identify differences in the delta band and a band between 200 and 220 Hz (HFO 6) when comparing basal and preictal signals. Differences in Fisher information in the delta and HFO 6 bands before seizures highlight their role in capturing important system dynamics. This offers new perspectives on the intricate relationship between delta oscillations and HFO waves in patients with focal epilepsy, highlighting the importance of these patterns and their potential as biomarkers.

TMS provokes target-dependent intracranial rhythms across human cortical and subcortical sites

BackgroundTranscranial magnetic stimulation (TMS) is believed to alter ongoing neural activity and cause circuit-level changes in brain function. While the electrophysiological effects of TMS have been extensively studied with scalp electroencephalography (EEG), this approach generally evaluates low-frequency neural activity at the cortical surface. However, TMS can be safely used in patients with intracranial electrodes (iEEG), allowing for direct assessment of deeper and more localized oscillatory responses across the frequency spectrum. Objective/HypothesisOur study used iEEG to understand the effects of TMS on human neural activity in the spectral domain. We asked (1) which brain regions respond to cortically-targeted TMS, and in what frequency bands, (2) whether deeper brain structures exhibit oscillatory responses, and (3) whether the neural responses to TMS reflect evoked versus induced oscillations. MethodsWe recruited 17 neurosurgical patients with indwelling electrodes and recorded neural activity while patients underwent repeated trials of single-pulse TMS at either the dorsolateral prefrontal cortex (DLPFC) or parietal cortex. iEEG signals were analyzed using spectral methods to understand the oscillatory responses to TMS. ResultsStimulation to DLPFC drove widespread low-frequency increases (3–8 Hz) in frontolimbic cortices and high-frequency decreases (30–110 Hz) in frontotemporal areas, including the hippocampus. Stimulation to parietal cortex specifically provoked low-frequency responses in the medial temporal lobe. While most low-frequency activity was consistent with phase-locked evoked responses, anterior frontal regions exhibited induced theta oscillations following DLPFC stimulation. ConclusionsBy combining TMS with intracranial EEG recordings, our results suggest that TMS is an effective means to perturb oscillatory neural activity in brain-wide networks, including deeper structures not directly accessed by stimulation itself.

Benchmarking signal quality and spatiotemporal distribution of interictal spikes in prolonged human iEEG recordings using CorTec wireless brain interchange

Neuromodulation through implantable pulse generators (IPGs) represents an important treatment approach for neurological disorders. While the field has observed the success of state-of-the-art interventions, such as deep brain stimulation (DBS) or responsive neurostimulation (RNS), implantable systems face various technical challenges, including the restriction of recording from a limited number of brain sites, power management, and limited external access to the assessed neural data in a continuous fashion. To the best of our knowledge, for the first time in this study, we investigated the feasibility of recording human intracranial EEG (iEEG) using a benchtop version of the Brain Interchange (BIC) unit of CorTec, which is a portable, wireless, and externally powered implant with sensing and stimulation capabilities. We developed a MATLAB/SIMULINK-based rapid prototyping environment and a graphical user interface (GUI) to acquire and visualize the iEEG captured from all 32 channels of the BIC unit. We recorded prolonged iEEG (~ 24 h) from three human subjects with externalized depth leads using the BIC and commercially available clinical amplifiers simultaneously in the epilepsy monitoring unit (EMU). The iEEG signal quality of both streams was compared, and the results demonstrated a comparable power spectral density (PSD) in all the systems in the low-frequency band (< 80 Hz). However, notable differences were primarily observed above 100 Hz, where the clinical amplifiers were associated with lower noise floor (BIC-17 dB vs. clinical amplifiers < − 25 dB). We employed an established spike detector to assess and compare the spike rates in each iEEG stream. We observed over 90% conformity between the spikes rates and their spatial distribution captured with BIC and clinical systems. Additionally, we quantified the packet loss characteristic in the iEEG signal during the wireless data transfer and conducted a series of simulations to compare the performance of different interpolation methods for recovering the missing packets in signals at different frequency bands. We noted that simple linear interpolation has the potential to recover the signal and reduce the noise floor with modest packet loss levels reaching up to 10%. Overall, our results indicate that while tethered clinical amplifiers exhibited noticeably better noise floor above 80 Hz, epileptic spikes can still be detected successfully in the iEEG recorded with the externally powered wireless BIC unit opening the road for future closed-loop neuromodulation applications with continuous access to brain activity.

Epileptic tissue localization using graph-based networks in the high frequency oscillation range of intracranial electroencephalography

PurposeHigh frequency oscillations (HFOs) are an emerging biomarker of epilepsy. However, very few studies have investigated the functional connectivity of interictal iEEG signals in the frequency range of HFOs. Here, we study the corresponding functional networks using graph theory, and we assess their predictive value for automatic electrode classification in a cohort of 20 drug resistant patients. MethodsCoherence-based connectivity analysis was performed on the iEEG recordings, and six different local graph measures were computed in both sub-bands of the HFO frequency range (80–250 Hz and 250–500 Hz). Correlation analysis was implemented between the local graph measures and the ripple and fast ripple rates. Finally, the WEKA software was employed for training and testing different predictive models on the aforementioned local graph measures. ResultsThe ripple rate was significantly correlated with five out of six local graph measures in the functional network. For fast ripples, their rate was also significantly (but negatively) correlated with most of the local metrics. The results from WEKA showed that the Logistic Regression algorithm was able to classify highly HFO-contaminated electrodes with an accuracy of 82.5 % for ripples and 75.4 % for fast ripples. ConclusionFunctional connectivity networks in the HFO band could represent an alternative to the direct use of distinct HFO events, while also providing important insights about hub epileptic areas that can represent possible surgical targets. Automatic electrode classification through FC-based classifiers can help bypass the burden of manual HFO annotation, providing at the same time similar amount of information about the epileptic tissue.

Neural response properties predict perceived contents and locations elicited by intracranial electrical stimulation of human auditory cortex.

Intracranial electrical stimulation (iES) of auditory cortex can elicit sound experiences with a variety of perceived contents (hallucination or illusion) and locations (contralateral or bilateral side), independent of actual acoustic inputs. However, the neural mechanisms underlying this elicitation heterogeneity remain undiscovered. Here, we collected subjective reports following iES at 3062 intracranial sites in 28 patients (both sexes) and identified 113 auditory cortical sites with iES-elicited sound experiences. We then decomposed the sound-induced intracranial electroencephalogram (iEEG) signals recorded from all 113 sites into time-frequency features. We found that the iES-elicited perceived contents can be predicted by the early high-γ features extracted from sound-induced iEEG. In contrast, the perceived locations elicited by stimulating hallucination sites and illusion sites are determined by the late high-γ and long-lasting α features, respectively. Our study unveils the crucial neural signatures of iES-elicited sound experiences in human and presents a new strategy to hearing restoration for individuals suffering from deafness.

Deep Learning-Based Visual Complexity Analysis of Electroencephalography Time-Frequency Images: Can It Localize the Epileptogenic Zone in the Brain?

In drug-resistant epilepsy, a visual inspection of intracranial electroencephalography (iEEG) signals is often needed to localize the epileptogenic zone (EZ) and guide neurosurgery. The visual assessment of iEEG time-frequency (TF) images is an alternative to signal inspection, but subtle variations may escape the human eye. Here, we propose a deep learning-based metric of visual complexity to interpret TF images extracted from iEEG data and aim to assess its ability to identify the EZ in the brain. We analyzed interictal iEEG data from 1928 contacts recorded from 20 children with drug-resistant epilepsy who became seizure-free after neurosurgery. We localized each iEEG contact in the MRI, created TF images (1–70 Hz) for each contact, and used a pre-trained VGG16 network to measure their visual complexity by extracting unsupervised activation energy (UAE) from 13 convolutional layers. We identified points of interest in the brain using the UAE values via patient- and layer-specific thresholds (based on extreme value distribution) and using a support vector machine classifier. Results show that contacts inside the seizure onset zone exhibit lower UAE than outside, with larger differences in deep layers (L10, L12, and L13: p &lt; 0.001). Furthermore, the points of interest identified using the support vector machine, localized the EZ with 7 mm accuracy. In conclusion, we presented a pre-surgical computerized tool that facilitates the EZ localization in the patient’s MRI without requiring long-term iEEG inspection.

Odor representations from the two nostrils are temporally segregated in human piriform cortex

The human olfactory system has two discrete channels of sensory input, arising from olfactory epithelia housed in the left and right nostrils. Here, we asked whether the primary olfactory cortex (piriform cortex [PC]) encodes odor information arising from the two nostrils as integrated or distinct stimuli. We recorded intracranial electroencephalogram (iEEG) signals directly from PC while human subjects participated in an odor identification task where odors were delivered to the left, right, or both nostrils. We analyzed the time course of odor identity coding using machine-learning approaches and found that uni-nostril odor inputs to the ipsilateral nostril are encoded ∼480-ms faster than odor inputs to the contralateral nostril on average. During naturalistic bi-nostril odor sampling, odor information emerged in two temporally segregated epochs, with the first epoch corresponding to the ipsilateral and the second epoch corresponding to the contralateral odor representations. These findings reveal that PC maintains distinct representations of odor input from each nostril through temporal segregation, highlighting an olfactory coding scheme at the cortical level that can parse odor information across nostrils within the course of a single inhalation.

Implementation of Machine Learning and Deep Learning Techniques for the Detection of Epileptic Seizures Using Intracranial Electroencephalography

The diagnosis of epilepsy primarily relies on the visual and subjective assessment of the patient’s electroencephalographic (EEG) or intracranial electroencephalographic (iEEG) signals. Neurophysiologists, based on their experience, look for characteristic discharges such as spikes and multi-spikes. One of the main challenges in epilepsy research is developing an automated system capable of detecting epileptic seizures with high sensitivity and precision. Moreover, there is an ongoing search for universal features in iEEG signals that can be easily interpreted by neurophysiologists. This article explores the possibilities, issues, and challenges associated with utilizing artificial intelligence for seizure detection using the publicly available iEEG database. The study presents standard approaches for analyzing iEEG signals, including chaos theory, energy in different frequency bands (alpha, beta, gamma, theta, and delta), wavelet transform, empirical mode decomposition, and machine learning techniques such as support vector machines. It also discusses modern deep learning algorithms such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. Our goal was to gather and comprehensively compare various artificial intelligence techniques, including both traditional machine learning methods and deep learning techniques, which are most commonly used in the field of seizure detection. Detection results were tested on a separate dataset, demonstrating classification accuracy, sensitivity, precision, and specificity of seizure detection. The best results for seizure detection were obtained with features related to iEEG signal energy (accuracy of 0.97, precision of 0.96, sensitivity of 0.99, and specificity of 0.96), as well as features related to chaos, Lyapunov exponents, and fractal dimension (accuracy, precision, sensitivity, and specificity all equal to 0.95). The application of CNN and LSTM networks yielded significantly better results (CNN: Accuracy of 0.99, precision of 0.98, sensitivity of 1, and specificity of 0.99; LSTM: Accuracy of 0.98, precision of 0.96, sensitivity of 1, and specificity of 0.99). Additionally, the use of the gradient-weighted class activation mapping algorithm identified iEEG signal fragments that played a significant role in seizure detection.

IEEG Signal Data Augmentation in Convolutional Neural Networks for Epileptic Focus Localization

Epileptic focus localization plays a crucial role in the diagnosis and treatment of epilepsy. Convolutional Neural Networks (CNNs) have exhibited promising outcomes in automatically detecting epileptic focus through the analysis of intracranial electroencephalogram (iEEG) signals. However, the limited availability of labeled iEEG dataset, which require specialist annotations, has constrained the effectiveness of CNNs. In this study, data augmentation techniques, including time shifting, amplitude scaling and noise addition, were employed to enhance the diversity and information content of the data. These techniques aimed to enable machine learning models to extract features from various aspects of iEEG data, thereby improving the accuracy of the models. Three deep learning models, namely DeepConvNet, ShallowConvNet and EEGNet, were introduced for the identification of epileptic foci. To evaluate the proposed methods, the Bern-Barcelona iEEG dataset was utilized. The experimental results demonstrated that the augmented dataset, formed by applying the three data augmentation techniques, achieved higher accuracies across all three deep learning models compared to the original dataset. This finding underscores the feasibility and efficacy of the proposed data augmentation and feature extraction methods in automated epilepsy detection.

Model Parameter Estimation As Features to Predict the Duration of Epileptic Seizures From Onset.

The durations of epileptic seizures are linked to severity and risk for patients. It is unclear if the spatiotemporal evolution of a seizure has any relationship with its duration. Understanding such mechanisms may help reveal treatments for reducing the duration of a seizure. Here, we present a novel method to predict whether a seizure is going to be short or long at its onset using features that can be interpreted in the parameter space of a brain model. The parameters of a Jansen-Rit neural mass model were tracked given intracranial electroencephalography (iEEG) signals, and were processed as time series features using MINIROCKET. By analysing 2954 seizures from 10 patients, patient-specific classifiers were built to predict if a seizure would be short or long given 7 s of iEEG at seizure onset. The method achieved an area under the receiver operating characteristic curve (AUC) greater than 0.6 for five of 10 patients. The behaviour in the parameter space has shown different mechanisms are associated with short/long seizures.Clinical relevance-This shows that it is possible to classify whether a seizure will be short or long based on its early characteristics. Timely interventions and treatments can be applied if the duration of the seizures can be predicted.

Validating MEG source imaging of resting state oscillatory patterns with an intracranial EEG atlas

BackgroundMagnetoencephalography (MEG) is a widely used non-invasive tool to estimate brain activity with high temporal resolution. However, due to the ill-posed nature of the MEG source imaging (MSI) problem, the ability of MSI to identify accurately underlying brain sources along the cortical surface is still uncertain and requires validation. MethodWe validated the ability of MSI to estimate the background resting state activity of 45 healthy participants by comparing it to the intracranial EEG (iEEG) atlas (https://mni-open-ieegatlas.research.mcgill.ca/). First, we applied wavelet-based Maximum Entropy on the Mean (wMEM) as an MSI technique. Next, we converted MEG source maps into intracranial space by applying a forward model to the MEG-reconstructed source maps, and estimated virtual iEEG (ViEEG) potentials on each iEEG channel location; we finally quantitatively compared those with actual iEEG signals from the atlas for 38 regions of interest in the canonical frequency bands. ResultsThe MEG spectra were more accurately estimated in the lateral regions compared to the medial regions. The regions with higher amplitude in the ViEEG than in the iEEG were more accurately recovered. In the deep regions, MEG-estimated amplitudes were largely underestimated and the spectra were poorly recovered. Overall, our wMEM results were similar to those obtained with minimum norm or beamformer source localization. Moreover, the MEG largely overestimated oscillatory peaks in the alpha band, especially in the anterior and deep regions. This is possibly due to higher phase synchronization of alpha oscillations over extended regions, exceeding the spatial sensitivity of iEEG but detected by MEG. Importantly, we found that MEG-estimated spectra were more comparable to spectra from the iEEG atlas after the aperiodic components were removed. ConclusionThis study identifies brain regions and frequencies for which MEG source analysis is likely to be reliable, a promising step towards resolving the uncertainty in recovering intracerebral activity from non-invasive MEG studies.

Single-neuron mechanisms of neural adaptation in the human temporal lobe

A central function of the human brain is to adapt to new situations based on past experience. Adaptation is reflected behaviorally by shorter reaction times to repeating or similar stimuli, and neurophysiologically by reduced neural activity in bulk-tissue measurements with fMRI or EEG. Several potential single-neuron mechanisms have been hypothesized to cause this reduction of activity at the macroscopic level. We here explore these mechanisms using an adaptation paradigm with visual stimuli bearing abstract semantic similarity. We recorded intracranial EEG (iEEG) simultaneously with spiking activity of single neurons in the medial temporal lobes of 25 neurosurgical patients. Recording from 4917 single neurons, we demonstrate that reduced event-related potentials in the macroscopic iEEG signal are associated with a sharpening of single-neuron tuning curves in the amygdala, but with an overall reduction of single-neuron activity in the hippocampus, entorhinal cortex, and parahippocampal cortex, consistent with fatiguing in these areas.

A simultaneous intracranial EEG-surface EMG analysis of generalized tonic-clonic seizures (P10-1.004)

<h3>Objective:</h3> To analyze the neurophysiology of generalized tonic-clonic (GTC) seizures using intracranial-EEG and surface-EMG data. <h3>Background:</h3> The precise mechanism of a GTC seizure is not well understood. A polygraphic analysis with intracranial-EEG (iEEG) and surface-EMG (sEMG) offers a unique opportunity to study this mechanism from a neurophysiological standpoint. <h3>Design/Methods:</h3> We studied two patients with refractory focal epilepsy, admitted to the epilepsy-monitoring unit with iEEG and sEMG. Both patients underwent direct electrical cortical stimulation for cortical mapping. iEEG and EMG signals were recorded using Nihon-Kohden’s JE-120 256-channel amplifier with a sampling rate of 2000Hz. A GTC seizure was provoked in both patients during their respective stimulation sessions. <h3>Results:</h3> The tonic phase demonstrated continuous spike activity in iEEG with highest power in 50–100Hz range. The sEMG activity demonstrated an interference pattern in both agonists and antagonists, consistent with a tetanic contraction with a very similar power spectrum as the iEEG. The clonic phase was characterized by polyspike and slow-wave pattern. The polyspikes and slow-waves were time-locked with synchronized tetanic sEMG bursts and silent-periods in agonists and antagonists, respectively. The polyspikes were superimposed with ~400–600Hz high-frequency oscillations (HFOs). The frequency of the serrations of the motor unit potentials in the sEMG bursts was a subharmonic of the HFOs. The iEEG-sEMG latency was ~17–21ms, consistent with corticospinal conduction. There was a progressive increase of the sEMG burst and silent-period duration during the clonic phase, associated with corresponding increases in the polyspike and slow-wave durations. <h3>Conclusions:</h3> This study shows a very close relationship between iEEG and sEMG activity in a GTC seizure. The very similar power spectra of the iEEG and sEMG activities indicate that a GTC seizure is a direct result of cortical electrical activity varying in a crescendo-decrescendo manner. The transition from tonic to clonic phase is due to the “weakening” of the seizure discharge intensity. <b>Disclosure:</b> Dr. Acar has nothing to disclose. Dr. Ticku has nothing to disclose. Dr. Fotedar has nothing to disclose.

Swin-TCNet: Swin-based temporal-channel cascade network for motor imagery iEEG signal recognition

Intracranial electroencephalography (iEEG) can record neuronal activities in different brain areas by placing strip or mesh electrodes on the surface of the brain. Benefiting from the high temporal and spatial resolution of iEEG signals, iEEG-based motor imagery has gained great attention, and made significant progress under the frameworks of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). However, both CNN- and RNN-based methods have limitations in perceiving the long-range global dependencies of local features in time and spatial dimensions. To exploit the temporal and spatial relationship of iEEG signals, we propose a Swin-Based Temporal Cascade Channel Network (Swin-TCNet) for motor imagery classification tasks, which is composed of three modules: Temporal-Swin (TS), Channel-Swin (CS) and Classifier. The TS and CS modules respectively extract the global dependencies of iEEG signals in the time and channel dimensions, and the Classifier assigns the class labels to the inputs. In addition, we introduce a Temporal-Channel Swin (TC-Swin) block instead of the standard Swin block to effectively reduce the computational complexity. We validate our model on the public imagined handwriting movement dataset collected by Stanford University. The experimental results demonstrate that our model can raise the classification accuracy by 2%–9% compared with 6 state-of-the-art models.

Intracerebral Electrophysiological Recordings to Understand the Neural Basis of Human Face Recognition.

Understanding how the human brain recognizes faces is a primary scientific goal in cognitive neuroscience. Given the limitations of the monkey model of human face recognition, a key approach in this endeavor is the recording of electrophysiological activity with electrodes implanted inside the brain of human epileptic patients. However, this approach faces a number of challenges that must be overcome for meaningful scientific knowledge to emerge. Here we synthesize a 10 year research program combining the recording of intracerebral activity (StereoElectroEncephaloGraphy, SEEG) in the ventral occipito-temporal cortex (VOTC) of large samples of participants and fast periodic visual stimulation (FPVS), to objectively define, quantify, and characterize the neural basis of human face recognition. These large-scale studies reconcile the wide distribution of neural face recognition activity with its (right) hemispheric and regional specialization and extend face-selectivity to anterior regions of the VOTC, including the ventral anterior temporal lobe (VATL) typically affected by magnetic susceptibility artifacts in functional magnetic resonance imaging (fMRI). Clear spatial dissociations in category-selectivity between faces and other meaningful stimuli such as landmarks (houses, medial VOTC regions) or written words (left lateralized VOTC) are found, confirming and extending neuroimaging observations while supporting the validity of the clinical population tested to inform about normal brain function. The recognition of face identity - arguably the ultimate form of recognition for the human brain - beyond mere differences in physical features is essentially supported by selective populations of neurons in the right inferior occipital gyrus and the lateral portion of the middle and anterior fusiform gyrus. In addition, low-frequency and high-frequency broadband iEEG signals of face recognition appear to be largely concordant in the human association cortex. We conclude by outlining the challenges of this research program to understand the neural basis of human face recognition in the next 10 years.

Channel Increment Strategy-Based 1D Convolutional Neural Networks for Seizure Prediction Using Intracranial EEG.

The application of intracranial electroencephalogram (iEEG) to predict seizures remains challenging. Although channel selection has been utilized in seizure prediction and detection studies, most of them focus on the combination with conventional machine learning methods. Thus, channel selection combined with deep learning methods can be further analyzed in the field of seizure prediction. Given this, in this work, a novel iEEG-based deep learning method of One-Dimensional Convolutional Neural Networks (1D-CNN) combined with channel increment strategy was proposed for the effective seizure prediction. First, we used 4-sec sliding windows without overlap to segment iEEG signals. Then, 4-sec iEEG segments with an increasing number of channels (channel increment strategy, from one channel to all channels) were sequentially fed into the constructed 1D-CNN model. Next, the patient-specific model was trained for classification. Finally, according to the classification results in different channel cases, the channel case with the best classification rate was selected for each patient. Our method was tested on the Freiburg iEEG database, and the system performances were evaluated at two levels (segment- and event-based levels). Two model training strategies (Strategy-1 and Strategy-2) based on the K-fold cross validation (K-CV) were discussed in our work. (1) For the Strategy-1, a basic K-CV, a sensitivity of 90.18%, specificity of 94.81%, and accuracy of 94.42% were achieved at the segment-based level. At the event-based level, an event-based sensitivity of 100%, and false prediction rate (FPR) of 0.12/h were attained. (2) For the Strategy-2, the difference from the Strategy-1 is that a trained model selection step is added during model training. We obtained a sensitivity, specificity, and accuracy of 86.23%, 96.00% and 95.13% respectively at the segment-based level. At the event-based level, we achieved an event-based sensitivity of 98.65% with 0.08/h FPR. Our method also showed a better performance in seizure prediction compared to many previous studies and the random predictor using the same database. This may have reference value for the future clinical application of seizure prediction.

Online Seizure Prediction System: A Novel Probabilistic Approach for Efficient Prediction of Epileptic Seizure with iEEG Signal

Background: 1% of people around the world are suffering from epilepsy. It is, therefore crucial to propose an efficient automated seizure prediction tool implemented in a portable device that uses the electroencephalogram (EEG) signal to enhance epileptic patients’ life quality. Methods: In this study, we focused on time-domain features to achieve discriminative information at a low CPU cost extracted from the intracranial electroencephalogram (iEEG) signals of six patients. The probabilistic framework based on XGBoost classifier requires the mean and maximum probability of the non-seizure and the seizure occurrence period segments. Once all these parameters are set for each patient, the medical decision maker can send alarm based on well-defined thresholds. Results: While finding a unique model for all patients is really challenging, and our modelling results demonstrated that the proposed algorithm can be an efficient tool for reliable and clinically relevant seizure forecasting. Using iEEG signals, the proposed algorithm can forecast seizures, informing a patient about 75 minutes before a seizure would occur, a period large enough for patients to take practical actions to minimize the potential impacts of the seizure. Conclusion: We posit that the ability to distinguish interictal intracranial EEG from pre-ictal signals at some low computational cost may be the first step towards an implanted portable semi-automatic seizure suppression system in the near future. It is believed that our seizure prediction technique can conceivably be coupled with treatment techniques aimed at interrupting the process even prior to a seizure initiates to develop.