Intracerebral EEG Artifact Identification Using Convolutional Neural Networks

Computer-assisted analysis of routine EEG to identify hidden biomarkers of epilepsy: A systematic review

Background

Computational analysis of routine electroencephalogram (rEEG) could improve the accuracy of epilepsy diagnosis. We aim to systematically assess the diagnostic performances of computed biomarkers for epilepsy in individuals undergoing rEEG.

Methods

We searched MEDLINE, EMBASE, EBM reviews, IEEE Explore and the grey literature for studies published between January 1961 and December 2022. We included studies reporting a computational method to diagnose epilepsy based on rEEG without relying on the identification of interictal epileptiform discharges or seizures. Diagnosis of epilepsy as per a treating physician was the reference standard. We assessed the risk of bias using an adapted QUADAS-2 tool.

Results

We screened 10 166 studies, and 37 were included. The sample size ranged from 8 to 192 (mean=54). The computed biomarkers were based on linear (43%), non-linear (27%), connectivity (38%), and convolutional neural networks (10%) models. The risk of bias was high or unclear in all studies, more commonly from spectrum effect and data leakage. Diagnostic accuracy ranged between 64% and 100%. We observed high methodological heterogeneity, preventing pooling of accuracy measures.

Conclusion

The current literature provides insufficient evidence to reliably assess the diagnostic yield of computational analysis of rEEG.

Significance

We provide guidelines regarding patient selection, reference standard, algorithms, and performance validation.

Automatic semantic segmentation of EHG recordings by deep learning: An approach to a screening tool for use in clinical practice

BACKGROUND AND OBJECTIVE

Preterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice.

METHODS

For this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing.

RESULTS

U-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals.

CONCLUSIONS

As automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.

Weak coupling of neurons enables very high-frequency and ultra-fast oscillations through the interplay of synchronized phase shifts

Recently, in the past decade, high-frequency oscillations (HFOs), very high-frequency oscillations (VHFOs), and ultra-fast oscillations (UFOs) were reported in epileptic patients with drug-resistant epilepsy. However, to this day, the physiological origin of these events has yet to be understood. Our study establishes a mathematical framework based on bifurcation theory for investigating the occurrence of VHFOs and UFOs in depth EEG signals of patients with focal epilepsy, focusing on the potential role of reduced connection strength between neurons in an epileptic focus. We demonstrate that synchronization of a weakly coupled network can generate very and ultra high-frequency signals detectable by nearby microelectrodes. In particular, we show that a bistability region enables the persistence of phase-shift synchronized clusters of neurons. This phenomenon is observed for different hippocampal neuron models, including Morris-Lecar, Destexhe-Paré, and an interneuron model. The mechanism seems to be robust for small coupling, and it also persists with random noise affecting the external current. Our findings suggest that weakened neuronal connections could contribute to the production of oscillations with frequencies above 1000 Hz, which could advance our understanding of epilepsy pathology and potentially improve treatment strategies. However, further exploration of various coupling types and complex network models is needed.

Parameterized aperiodic and periodic components of single-channel EEG enables reliable seizure detection

Although it is clinically important, a reliable and economical solution to automatic seizure detection for patients at home is yet to be developed. Traditional algorithms rely on multi-channel EEG signals and features of canonical EEG power description. This study is aimed to propose an effective single-channel EEG seizure detection method centered on novel EEG power parameterization and channel selection algorithms. We employed the publicly available multi-channel CHB-MIT Scalp EEG database to gauge the effectiveness of our approach. We first adapted a power spectra parameterization algorithm to characterize the aperiodic and periodic components of the ictal and inter-ictal EEGs. We selected four features based on their statistical significance and interpretability, and developed a ranking approach to channel selection for each patient. We then tested the effectiveness of our approaches to channel and feature selection for automatic seizure detection using support vector machine (SVM) as the classifier. The performance of our algorithm was evaluated using five-fold cross-validation and compared to those methods of comparable complexity (using one or two channels of EEG), in terms of accuracy, specificity, sensitivity, precision and F1 score. Some channels of EEG signals show strikingly different distributions of PSD features between the ictal and inter-ictal states. Four features including the offset and exponent parameters for the aperiodic component and the first and second highest total power (TPW1 and TPW2) form the basis of channel selection and the input of SVM classifier. The selected channel is found to be patient-specific. Our approach has achieved a mean sensitivity of 95.6%, specificity of 99.2%, accuracy of 98.6%, precision of 95.5%, and F1 score of 95.5%. Compared with algorithms in previous studies that used one or two channels of EEG signals, ours outperforms in specificity and accuracy with comparable sensitivity. EEG power spectra parameterization to feature extraction and feature ranking-based channel selection are found to enable efficient and effective automatic seizure detection based on single-channel EEG signal.

Ongoing EEG artifact correction using blind source separation

OBJECTIVE

Analysis of the electroencephalogram (EEG) for epileptic spike and seizure detection or brain-computer interfaces can be severely hampered by the presence of artifacts. The aim of this study is to describe and evaluate a fast automatic algorithm for ongoing correction of artifacts in continuous EEG recordings, which can be applied offline and online.

METHODS

The automatic algorithm for ongoing correction of artifacts is based on fast blind source separation. It uses a sliding window technique with overlapping epochs and features in the spatial, temporal and frequency domain to detect and correct ocular, cardiac, muscle and powerline artifacts.

RESULTS

The approach was validated in an independent evaluation study on publicly available continuous EEG data with 2035 marked artifacts. Validation confirmed that 88% of the artifacts could be removed successfully (ocular: 81%, cardiac: 84%, muscle: 98%, powerline: 100%). It outperformed state-of-the-art algorithms both in terms of artifact reduction rates and computation time.

CONCLUSIONS

Fast ongoing artifact correction successfully removed a good proportion of artifacts, while preserving most of the EEG signals.

SIGNIFICANCE

The presented algorithm may be useful for ongoing correction of artifacts, e.g., in online systems for epileptic spike and seizure detection or brain-computer interfaces.

Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis

Transfer learning offers a route for developing robust deep learning models on small raw electroencephalography (EEG) datasets. Nevertheless, the utility of applying representations learned from large datasets with a lower sampling rate to smaller datasets with higher sampling rates remains relatively unexplored. In this study, we transfer representations learned by a convolutional neural network on a large, publicly available sleep dataset with a 100 Hertz sampling rate to a major depressive disorder (MDD) diagnosis task at a sampling rate of 200 Hertz. Importantly, we find that the early convolutional layers contain representations that are generalizable across tasks. Moreover, our approach significantly increases mean model accuracy from 82.33% to 86.99%, increases the model's use of lower frequencies, (θ-band), and increases its robustness to channel loss. We expect this analysis to provide useful guidance and enable more widespread use of transfer learning in EEG deep learning studies.

Genetic algorithm designed for optimization of neural network architectures for intracranial EEG recordings analysis

Objective.The current practices of designing neural networks rely heavily on subjective judgment and heuristic steps, often dictated by the level of expertise possessed by architecture designers. To alleviate these challenges and streamline the design process, we propose an automatic method, a novel approach to enhance the optimization of neural network architectures for processing intracranial electroencephalogram (iEEG) data.Approach.We present a genetic algorithm, which optimizes neural network architecture and signal pre-processing parameters for iEEG classification.Main results.Our method improved the macroF1 score of the state-of-the-art model in two independent datasets, from St. Anne's University Hospital (Brno, Czech Republic) and Mayo Clinic (Rochester, MN, USA), from 0.9076 to 0.9673 and from 0.9222 to 0.9400 respectively.Significance.By incorporating principles of evolutionary optimization, our approach reduces the reliance on human intuition and empirical guesswork in architecture design, thus promoting more efficient and effective neural network models. The proposed method achieved significantly improved results when compared to the state-of-the-art benchmark model (McNemar's test,p≪ 0.01). The results indicate that neural network architectures designed through machine-based optimization outperform those crafted using the subjective heuristic approach of a human expert. Furthermore, we show that well-designed data preprocessing significantly affects the models' performance.

Utilization of temporal autoencoder for semi-supervised intracranial EEG clustering and classification

Manual visual review, annotation and categorization of electroencephalography (EEG) is a time-consuming task that is often associated with human bias and requires trained electrophysiology experts with specific domain knowledge. This challenge is now compounded by development of measurement technologies and devices allowing large-scale heterogeneous, multi-channel recordings spanning multiple brain regions over days, weeks. Currently, supervised deep-learning techniques were shown to be an effective tool for analyzing big data sets, including EEG. However, the most significant caveat in training the supervised deep-learning models in a clinical research setting is the lack of adequate gold-standard annotations created by electrophysiology experts. Here, we propose a semi-supervised machine learning technique that utilizes deep-learning methods with a minimal amount of gold-standard labels. The method utilizes a temporal autoencoder for dimensionality reduction and a small number of the expert-provided gold-standard labels used for kernel density estimating (KDE) maps. We used data from electrophysiological intracranial EEG (iEEG) recordings acquired in two hospitals with different recording systems across 39 patients to validate the method. The method achieved iEEG classification (Pathologic vs. Normal vs. Artifacts) results with an area under the receiver operating characteristic (AUROC) scores of 0.862 ± 0.037, 0.879 ± 0.042, and area under the precision-recall curve (AUPRC) scores of 0.740 ± 0.740, 0.714 ± 0.042. This demonstrates that semi-supervised methods can provide acceptable results while requiring only 100 gold-standard data samples in each classification category. Subsequently, we deployed the technique to 12 novel patients in a pseudo-prospective framework for detecting Interictal epileptiform discharges (IEDs). We show that the proposed temporal autoencoder was able to generalize to novel patients while achieving AUROC of 0.877 ± 0.067 and AUPRC of 0.705 ± 0.154.

Identification and classification of epileptic EEG signals using invertible constant-Qtransform-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-Qnon-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.

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

OBJECTIVE

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

APPROACH

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

MAIN RESULTS

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

SIGNIFICANCE

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

ABOT: an open-source online benchmarking tool for machine learning-based artefact detection and removal methods from neuronal signals

Brain signals are recorded using different techniques to aid an accurate understanding of brain function and to treat its disorders. Untargeted internal and external sources contaminate the acquired signals during the recording process. Often termed as artefacts, these contaminations cause serious hindrances in decoding the recorded signals; hence, they must be removed to facilitate unbiased decision-making for a given investigation. Due to the complex and elusive manifestation of artefacts in neuronal signals, computational techniques serve as powerful tools for their detection and removal. Machine learning (ML) based methods have been successfully applied in this task. Due to ML's popularity, many articles are published every year, making it challenging to find, compare and select the most appropriate method for a given experiment. To this end, this paper presents ABOT (Artefact removal Benchmarking Online Tool) as an online benchmarking tool which allows users to compare existing ML-driven artefact detection and removal methods from the literature. The characteristics and related information about the existing methods have been compiled as a knowledgebase (KB) and presented through a user-friendly interface with interactive plots and tables for users to search it using several criteria. Key characteristics extracted from over 120 articles from the literature have been used in the KB to help compare the specific ML models. To comply with the FAIR (Findable, Accessible, Interoperable and Reusable) principle, the source code and documentation of the toolbox have been made available via an open-access repository.

A sparse representation strategy to eliminate pseudo-HFO events from intracranial EEG for seizure onset zone localization

Objective.High-frequency oscillations (HFOs) are considered a biomarker of the epileptogenic zone in intracranial EEG recordings. However, automated HFO detectors confound true oscillations with spurious events caused by the presence of artifacts.Approach.We hypothesized that, unlike pseudo-HFOs with sharp transients or arbitrary shapes, real HFOs have a signal characteristic that can be represented using a small number of oscillatory bases. Based on this hypothesis using a sparse representation framework, this study introduces a new classification approach to distinguish true HFOs from the pseudo-events that mislead seizure onset zone (SOZ) localization. Moreover, we further classified the HFOs into ripples and fast ripples by introducing an adaptive reconstruction scheme using sparse representation. By visualizing the raw waveforms and time-frequency representation of events recorded from 16 patients, three experts labeled 6400 candidate events that passed an initial amplitude-threshold-based HFO detector. We formed a redundant analytical multiscale dictionary built from smooth oscillatory Gabor atoms and represented each event with orthogonal matching pursuit by using a small number of dictionary elements. We used the approximation error and residual signal at each iteration to extract features that can distinguish the HFOs from any type of artifact regardless of their corresponding source. We validated our model on sixteen subjects with thirty minutes of continuous interictal intracranial EEG recording from each.Main results.We showed that the accuracy of SOZ detection after applying our method was significantly improved. In particular, we achieved a 96.65% classification accuracy in labeled events and a 17.57% improvement in SOZ detection on continuous data. Our sparse representation framework can also distinguish between ripples and fast ripples.Significance.We show that by using a sparse representation approach we can remove the pseudo-HFOs from the pool of events and improve the reliability of detected HFOs in large data sets and minimize manual artifact elimination.

SEEG-Net: An explainable and deep learning-based cross-subject pathological activity detection method for drug-resistant epilepsy

OBJECTIVE

Precise preoperative evaluation of drug-resistant epilepsy (DRE) requires accurate analysis of invasive stereoelectroencephalography (SEEG). With the tremendous breakthrough of Artificial intelligence (AI), previous studies can help clinical experts to identify pathological activities automatically. However, they still face limitations when applied in real-world clinical DRE scenarios, such as sample imbalance, cross-subject domain shift, and poor interpretability. Our objective is to propose a model that can address the above problems and realizes high-sensitivity SEEG pathological activity detection based on two real clinical datasets.

METHODS

Our proposed innovative and effective SEEG-Net introduces a multiscale convolutional neural network (MSCNN) to increase the receptive field of the model, and to learn SEEG multiple frequency domain features, local and global features. Moreover, we designed a novel focal domain generalization loss (FDG-loss) function to enhance the target sample weight and to learn domain consistency features. Furthermore, to enhance the interpretability and flexibility of SEEG-Net, we explain SEEG-Net from multiple perspectives, such as significantly different features, interpretable models, and model learning process interpretation by Grad-CAM++.

RESULTS

The performance of our proposed method is verified on a public benchmark multicenter SEEG dataset and a private clinical SEEG dataset for a robust comparison. The experimental results demonstrate that the SEEG-Net model achieves the highest sensitivity and is state-of-the-art on cross-subject (for different patients) evaluation, and well deal with the known problems. Besides, we provide an SEEG processing and database construction flow, by maintaining consistency with the real-world clinical scenarios.

SIGNIFICANCE

According to the results, SEEG-Net is constructed to increase the sensitivity of SEEG pathological activity detection. Simultaneously, we settled certain problems about AI assistance in clinical DRE, built a bridge between AI algorithm application and clinical practice.

Decoding Intracranial EEG With Machine Learning: A Systematic Review

Advances in intracranial electroencephalography (iEEG) and neurophysiology have enabled the study of previously inaccessible brain regions with high fidelity temporal and spatial resolution. Studies of iEEG have revealed a rich neural code subserving healthy brain function and which fails in disease states. Machine learning (ML), a form of artificial intelligence, is a modern tool that may be able to better decode complex neural signals and enhance interpretation of these data. To date, a number of publications have applied ML to iEEG, but clinician awareness of these techniques and their relevance to neurosurgery, has been limited. The present work presents a review of existing applications of ML techniques in iEEG data, discusses the relative merits and limitations of the various approaches, and examines potential avenues for clinical translation in neurosurgery. One-hundred-seven articles examining artificial intelligence applications to iEEG were identified from 3 databases. Clinical applications of ML from these articles were categorized into 4 domains: i) seizure analysis, ii) motor tasks, iii) cognitive assessment, and iv) sleep staging. The review revealed that supervised algorithms were most commonly used across studies and often leveraged publicly available timeseries datasets. We conclude with recommendations for future work and potential clinical applications.

Implementation of a Convolutional Neural Network for Eye Blink Artifacts Removal From the Electroencephalography Signal

Electroencephalography (EEG) signals are disrupted by technical and physiological artifacts. One of the most common artifacts is the natural activity that results from the movement of the eyes and the blinking of the subject. Eye blink artifacts (EB) spread across the entire head surface and make EEG signal analysis difficult. Methods for the elimination of electrooculography (EOG) artifacts, such as independent component analysis (ICA) and regression, are known. The aim of this article was to implement the convolutional neural network (CNN) to eliminate eye blink artifacts. To train the CNN, a method for augmenting EEG signals was proposed. The results obtained from the CNN were compared with the results of the ICA and regression methods for the generated and real EEG signals. The results obtained indicate a much better performance of the CNN in the task of removing eye-blink artifacts, in particular for the electrodes located in the central part of the head.

A deep learning approach in automated detection of schizophrenia using scalogram images of EEG signals

This study presents a method with high accuracy performance that aims to automatically detect schizophrenia (SZ) from electroencephalography (EEG) records. Unlike related literature studies using traditional machine learning algorithms, the features required for the training of the network are automatically extracted from the EEG records in our method. In order to obtain the time frequency features of the EEG signals, the signal was converted into 2D by using the Continuous Wavelet Transform method. This study has the highest accuracy performance in the relevant literature by using 2D time frequency features in automatic detection of SZ disease. It is trained with Visual Geometry Group-16 (VGG16), an advanced convolutional neural networks (CNN) deep learning network architecture, to extract key features found on scalogram images and train the network. The study shows a high success in classifying SZ patients and healthy individuals with a very satisfactory accuracy of 98% and 99.5%, respectively, using two different datasets consisting of individuals from different age groups. Using different techniques [Activization Maximization, Saliency Map, and Gradient-weighted Class Activation Mapping (Grad-CAM)] to visualize the learning outcomes of the CNN network, the relationship of frequency components between SZ and the healthy individual is clearly shown. Moreover, with these interpretable outcomes, the difference between SZ patients and healthy individuals can be distinguished very easily help for expert opinion.

A deep neural network with subdomain adaptation for motor imagery brain-computer interface

BACKGROUND

The nonstationarity problem of EEG is very serious, especially for spontaneous signals, which leads to the poor effect of machine learning related to spontaneous signals, especially in related tasks across time, which correspondingly limits the practical use of brain-computer interface (BCI).

OBJECTIVE

In this paper, we proposed a new transfer learning algorithm, which can utilize the labeled motor imagery (MI) EEG data at the previous time to achieve better classification accuracies for a small number of labeled EEG signals at the current time.

METHODS

We introduced an adaptive layer into the full connection layer of a deep convolution neural network. The objective function of the adaptive layer was designed to minimize the Local Maximum Mean Discrepancy (LMMD) and the prediction error while minimizing the distance within each class (DWC) and maximizing the distance between classes within each domain (DBCWD). We verified the effectiveness of the proposed algorithm on two public datasets.

RESULTS

The classification accuracy of the proposed algorithm was higher than other comparison algorithms, and the paired t-test results also showed that the performance of the proposed algorithm was significantly different from that of other algorithms. The results of the confusion matrix and feature visualization showed the effectiveness of the proposed algorithm.

CONCLUSION

Experimental results showed that the proposed algorithm can achieve higher classification accuracy than other algorithms when there was only a small amount of labeled MI EEG data at the current time. It can be promising to be applied to the field of BCI.

Invasive Electrophysiology for Circuit Discovery and Study of Comorbid Psychiatric Disorders in Patients With Epilepsy: Challenges, Opportunities, and Novel Technologies

Intracranial electroencephalographic (iEEG) recordings from patients with epilepsy provide distinct opportunities and novel data for the study of co-occurring psychiatric disorders. Comorbid psychiatric disorders are very common in drug-resistant epilepsy and their added complexity warrants careful consideration. In this review, we first discuss psychiatric comorbidities and symptoms in patients with epilepsy. We describe how epilepsy can potentially impact patient presentation and how these factors can be addressed in the experimental designs of studies focused on the electrophysiologic correlates of mood. Second, we review emerging technologies to integrate long-term iEEG recording with dense behavioral tracking in naturalistic environments. Third, we explore questions on how best to address the intersection between epilepsy and psychiatric comorbidities. Advances in ambulatory iEEG and long-term behavioral monitoring technologies will be instrumental in studying the intersection of seizures, epilepsy, psychiatric comorbidities, and their underlying circuitry.

Direct Electrical Stimulation of the Human Brain Has Inverse Effects on the Theta and Gamma Neural Activities

OBJECTIVE

Our goal was to analyze the electrophysiological response to direct electrical stimulation (DES) systematically applied at a wide range of parameters and anatomical sites, with particular focus on neural activities associated with memory and cognition.

METHODS

We used a large set of intracranial EEG (iEEG) recordings with DES from 45 subjects with electrodes implanted both subdurally on the cortical surface and subcortically into the brain parenchyma. Subjects were stimulated in blocks of alternating frequency and amplitude parameters during quiet wakefulness.

RESULTS

Stimulating at different frequencies and amplitudes of electric current revealed a persistent pattern of response in the slow and the fast neural activities. In particular, amplification of the theta (4-7 Hz) and attenuation of the gamma (29-52 Hz) power-in-band was observed with increasing the stimulation parameters. This opposite effect on the low and high frequency bands was found across a network of selected local and distal sites proportionally to the proximity and magnitude of the electric current. Power increase in the theta and decrease in the gamma band was driven by the total electric charge delivered with either increasing the frequency or amplitude of the stimulation current. This inverse effect on the theta and gamma activities was consistently observed in response to different stimulation frequencies and amplitudes.

CONCLUSION

Our results suggest a uniform DES effect of amplifying theta and suppressing gamma neural activities in the human brain.

SIGNIFICANCE

These findings reveal the utility of simple power-in-band features for understanding and optimizing the effects of electrical stimulation on brain functions.

Artefact Detection in Impedance Pneumography Signals: A Machine Learning Approach

Impedance pneumography has been suggested as an ambulatory technique for the monitoring of respiratory diseases. However, its ambulatory nature makes the recordings more prone to noise sources. It is important that such noisy segments are identified and removed, since they could have a huge impact on the performance of data-driven decision support tools. In this study, we investigated the added value of machine learning algorithms to separate clean from noisy bio-impedance signals. We compared three approaches: a heuristic algorithm, a feature-based classification model (SVM) and a convolutional neural network (CNN). The dataset consists of 47 chronic obstructive pulmonary disease patients who performed an inspiratory threshold loading protocol. During this protocol, their respiration was recorded with a bio-impedance device and a spirometer, which served as a gold standard. Four annotators scored the signals for the presence of artefacts, based on the reference signal. We have shown that the accuracy of both machine learning approaches (SVM: 87.77 ± 2.64% and CNN: 87.20 ± 2.78%) is significantly higher, compared to the heuristic approach (84.69 ± 2.32%). Moreover, no significant differences could be observed between the two machine learning approaches. The feature-based and neural network model obtained a respective AUC of 92.77±2.95% and 92.51±1.74%. These findings show that a data-driven approach could be beneficial for the task of artefact detection in respiratory thoracic bio-impedance signals.

Deep convolutional neural network for the automated detection of Subthalamic nucleus using MER signals

BACKGROUND

Deep brain stimulation (DBS) surgery has been extensively conducted for treating advanced Parkinson's disease (PD) patient's symptoms. DBS hinges on the localization of the subthalamic nucleus (STN) in which a permanent electrode should be accurately placed to produce electrical current. Microelectrode recording (MER) signals are routinely recorded in the procedure of DBS surgery to validate the planned trajectories. However, manual MER signals interpretation with the goal of detecting STN borders requires expertise and prone to inter-observer variability. Therefore, a computerized aided system would be beneficial to automatic detection of the dorsal and ventral borders of the STN in MER.

NEW METHOD

In this study, a new deep learning model based on convolutional neural system for automatic delineation of the neurophysiological borders of the STN along the electrode trajectory was developed.

COMPARISON WITH EXISTING METHODS

The proposed model does not involve any conventional standardization, feature extraction or selection steps.

RESULTS

Promising results of 98.67% accuracy, 99.03% sensitivity, 98.11% specificity, 98.79% precision and 98.91% F1-score for subject based testing were achieved using the proposed convolutional neural network (CNN) model.

CONCLUSIONS

This is the first study on the analysis of MER signals to detect STN using deep CNN. Traditional machine learning (ML) algorithms are often cumbersome and suffer from subjective evaluation. Though, the developed 10-layered CNN model has the capability of extracting substantial features at the convolution stage. Hence, the proposed model has the potential to deliver high performance on STN region detection which shows perspective in aiding the neurosurgeon intraoperatively.

EEG based interpretation of human brain activity during yoga and meditation using machine learning: A systematic review

OBJECTIVES

The present investigation is to study the impact of yoga and meditation on Brain waves concerning physical and mental health. There are mainly three stages (steps) in the brain wave classification:(i) preprocessing, ii) feature extraction, and iii) classification. This work provides a review of interpretation methods of Brain signals (Electroencephalogram (EEG)) EEG during yoga and meditation. Past research has revealed significant mental and physical advantages with yoga and meditation.

METHODS

The research topic reviewed focused on the machine learning strategies applied for the interpretation of brain waves. In addressing the research questions highlighted earlier in the general introduction, we conducted a systematic search of articles from targeted scientific and journal online databases that included PubMed, Web of Science, IEEE Xplore Digital Library (IEEE), and Arxiv databases based on their relevance to the research questions and domain topic. The survey topic is relatively nascent, and therefore, the scope of the search period was limited to the 20-year timeline that was deemed representative of the research topic under investigation. The literature search was based on the keywords "EEG", "yoga*" and "meditation*". The key phrases were concatenated using Boolean expressions and applied to search through the selected online databases yielding a total of 120 articles. The online databases were selected based on the relevancy of content with the research title, research questions, and the domain application. The literature review search, process, and classification were carefully conducted guided by two defined measures; 1.) Inclusion criteria; and 2.) Exclusion criteria. These measures define the criteria for searching and extracting relevant articles relating to the research title and domain of interest.

RESULTS

Our literature search and review indicate a broad spectrum of neural mechanics under a variety of meditation styles have been investigated. A detailed analysis of various mental states using Zen, CHAN, mindfulness, TM, Rajayoga, Kundalini, Yoga, and other meditation styles have been described by means of EEG bands. Classification of mental states using KNN, SVM, Random forest, Fuzzy logic, neural networks, Convolutional Neural Networks has been described. Superior research is still required to classify the EEG signatures corresponding to different mental states.

CONCLUSIONS

Yoga practice may be an effective adjunctive treatment for a clinical and aging population. Advanced research can examine the effects of specific branches of yoga on a designated clinical grouping. Yoga and meditation increased overall healthy brain activity.

A Correlation-Driven Mapping For Deep Learning application in detecting artifacts within the EEG

OBJECTIVE

When developing approaches for automatic preprocessing of electroencephalogram (EEG) signals in non-isolated demanding environment such as intensive care unit (ICU) or even outdoor environment, one of the major concerns is varying nature of characteristics of different artifacts in time, frequency and spatial domains, which in turn causes a simple approach to be not enough for reliable artifact removal. Considering this, current study aims to use correlation-driven mapping to improve artifact detection performance.

APPROACH

A framework is proposed here for mapping signals from multichannel space (regardless of the number of EEG channels) into two-dimensional RGB space, in which the correlation of all EEG channels is simultaneously taken into account, and a deep convolutional neural network (CNN) model can then learn specific patterns in generated 2D representation related to specific artifact.

MAIN RESULTS

The method with a classification accuracy of 92.30% (AUC = 0.96) in a leave-three-subjects-out cross-validation procedure was evaluated using data including 2310 EEG sequences contaminated by artifacts and 2285 artifact-free EEG sequences collected with BrainStatus self-adhesive electrode and wireless amplifier from 15 intensive care patients. For further assessment, several scenarios were also tested including performance variation of proposed method under different segment lengths, different numbers of isoline and different numbers of channel. The results showed outperformance of CNN fed by correlation coefficients data over both spectrogram-based CNN and EEGNet on the same dataset.

SIGNIFICANCE

This study showed the feasibility of utilizing correlation image of EEG channels coupled with deep learning as a promising tool for dimensionality reduction, channels fusion and capturing various artifacts patterns in temporal-spatial domains. A simplified version of proposed approach was also shown to be feasible in real-time application with latency of 0.0181 s for making real-time decision.

Automatic detection of artifacts in EEG by combining deep learning and histogram contour processing

This paper introduces a simple approach combining deep learning and histogram contour processing for automatic detection of various types of artifact contaminating the raw electroencephalogram (EEG). The proposed method considers both spatial and temporal information of raw EEG, without additional need for reference signals like ECG or EOG. The proposed method was evaluated with data including 785 EEG sequences contaminated by artifacts and 785 artifact-free EEG sequences collected from 15 intensive care patients. The obtained results showed an overall accuracy of 0.98, representing high reliability of proposed technique in detecting different types of artifacts and being comparable or outperforming the approaches proposed earlier in the literature.

Major depressive disorder assessment via enhanced k-nearest neighbor method and EEG signals

The aim of this paper is to introduce a novel method using short-term EEG signals to separate depressed patients from healthy controls. Five common frequency bands (delta, theta, alpha, beta and gamma) were extracted from the signals as linear features, as well as, wavelet packet decomposition to break down signals into certain frequency bands. Afterwards, two entropy measures, namely sample entropy and approximate entropy were applied on the wavelet packet coefficients as nonlinear features, and significant features were selected via genetic algorithm (GA). Three machine-learning algorithms were used for classification; including support vector machine (SVM), multilayer perceptron (MLP) a novel enhanced K-nearest neighbors (E-KNN), which uses GA to optimize the feature-space distances and provides a feature importance index. The highest accuracy obtained by using frequency-based features was from gamma oscillations which resulted in 91.38%. Performance of nonlinear features were better compared to the frequency-based features and the results showed 94.28% accuracy. The combination of the features showed 98.44% accuracy with the new proposed E-KNN classifier.

EEG Artifact Removal by Bayesian Deep Learning & ICA

Artifact removal is important for EEG signal processing because artifacts adversely affect analysis results. To preserve normal EEG signal, several methods based on independent component analysis (ICA) have been studied and artifacts are removed by discarding independent components (ICs) classified as artifacts. In this study, a method using Bayesian deep learning and attention module is presented to improve performance of the classifier for ICs. Probability value is computed through the method to predict if a component is artifact and to treat ambiguous inputs. The attention module achieves increasing classification accuracy and shows the map of the region where the classifier concentrates on.

Multicenter intracranial EEG dataset for classification of graphoelements and artifactual signals

EEG signal processing is a fundamental method for neurophysiology research and clinical neurology practice. Historically the classification of EEG into physiological, pathological, or artifacts has been performed by expert visual review of the recordings. However, the size of EEG data recordings is rapidly increasing with a trend for higher channel counts, greater sampling frequency, and longer recording duration and complete reliance on visual data review is not sustainable. In this study, we publicly share annotated intracranial EEG data clips from two institutions: Mayo Clinic, MN, USA and St. Anne's University Hospital Brno, Czech Republic. The dataset contains intracranial EEG that are labeled into three groups: physiological activity, pathological/epileptic activity, and artifactual signals. The dataset published here should support and facilitate training of generalized machine learning and digital signal processing methods for intracranial EEG and promote research reproducibility. Along with the data, we also propose a statistical method that is recommended for comparison of candidate classifier performance utilizing out-of-institution/out-of-patient testing.

Detection of mesial temporal lobe epileptiform discharges on intracranial electrodes using deep learning

OBJECTIVE

Develop a high-performing algorithm to detect mesial temporal lobe (mTL) epileptiform discharges on intracranial electrode recordings.

METHODS

An epileptologist annotated 13,959 epileptiform discharges from a dataset of intracranial EEG recordings from 46 epilepsy patients. Using this dataset, we trained a convolutional neural network (CNN) to recognize mTL epileptiform discharges from a single intracranial bipolar channel. The CNN outputs from multiple bipolar channel inputs were averaged to generate the final detector output. Algorithm performance was estimated using a nested 5-fold cross-validation.

RESULTS

On the receiver-operating characteristic curve, our algorithm achieved an area under the curve (AUC) of 0.996 and a partial AUC (for specificity > 0.9) of 0.981. AUC on a precision-recall curve was 0.807. A sensitivity of 84% was attained at a false positive rate of 1 per minute. 35.9% of the false positive detections corresponded to epileptiform discharges that were missed during expert annotation.

CONCLUSIONS

Using deep learning, we developed a high-performing, patient non-specific algorithm for detection of mTL epileptiform discharges on intracranial electrodes.

SIGNIFICANCE

Our algorithm has many potential applications for understanding the impact of mTL epileptiform discharges in epilepsy and on cognition, and for developing therapies to specifically reduce mTL epileptiform activity.

Design of a Network Permutation Entropy and Its Applications for Chaotic Time Series and EEG Signals

Measuring the complexity of time series provides an important indicator for characteristic analysis of nonlinear systems. The permutation entropy (PE) is widely used, but it still needs to be modified. In this paper, the PE algorithm is improved by introducing the concept of the network, and the network PE (NPE) is proposed. The connections are established based on both the patterns and weights of the reconstructed vectors. The complexity of different chaotic systems is analyzed. As with the PE algorithm, the NPE algorithm-based analysis results are also reliable for chaotic systems. Finally, the NPE is applied to estimate the complexity of EEG signals of normal healthy persons and epileptic patients. It is shown that the normal healthy persons have the largest NPE values, while the EEG signals of epileptic patients are lower during both seizure-free intervals and seizure activity. Hence, NPE could be used as an alternative to PE for the nonlinear characteristics of chaotic systems and EEG signal-based physiological and biomedical analysis.

Exploiting Graphoelements and Convolutional Neural Networks with Long Short Term Memory for Classification of the Human Electroencephalogram

The electroencephalogram (EEG) is a cornerstone of neurophysiological research and clinical neurology. Historically, the classification of EEG as showing normal physiological or abnormal pathological activity has been performed by expert visual review. The potential value of unbiased, automated EEG classification has long been recognized, and in recent years the application of machine learning methods has received significant attention. A variety of solutions using convolutional neural networks (CNN) for EEG classification have emerged with impressive results. However, interpretation of CNN results and their connection with underlying basic electrophysiology has been unclear. This paper proposes a CNN architecture, which enables interpretation of intracranial EEG (iEEG) transients driving classification of brain activity as normal, pathological or artifactual. The goal is accomplished using CNN with long short-term memory (LSTM). We show that the method allows the visualization of iEEG graphoelements with the highest contribution to the final classification result using a classification heatmap and thus enables review of the raw iEEG data and interpret the decision of the model by electrophysiology means.

Multi-feature localization of epileptic foci from interictal, intracranial EEG

OBJECTIVE

When considering all patients with focal drug-resistant epilepsy, as high as 40-50% of patients suffer seizure recurrence after surgery. To achieve seizure freedom without side effects, accurate localization of the epileptogenic tissue is crucial before its resection. We investigate an automated, fast, objective mapping process that uses only interictal data.

METHODS

We propose a novel approach based on multiple iEEG features, which are used to train a support vector machine (SVM) model for classification of iEEG electrodes as normal or pathologic using 30 min of inter-ictal recording.

RESULTS

The tissue under the iEEG electrodes, classified as epileptogenic, was removed in 17/18 excellent outcome patients and was not entirely resected in 8/10 poor outcome patients. The overall best result was achieved in a subset of 9 excellent outcome patients with the area under the receiver operating curve = 0.95.

CONCLUSION

SVM models combining multiple iEEG features show better performance than algorithms using a single iEEG marker. Multiple iEEG and connectivity features in presurgical evaluation could improve epileptogenic tissue localization, which may improve surgical outcome and minimize risk of side effects.

SIGNIFICANCE

In this study, promising results were achieved in localization of epileptogenic regions by SVM models that combine multiple features from 30 min of inter-ictal iEEG recordings.