Multi-dimensional Feature Optimization based Eye Blink Detection under Epileptiform Discharges

Differentiation in theta and gamma activation in weight-shifting learning between people with parkinson's disease of different anxiety severities

Anxiety and postural control deficits may be related in people with Parkinson's disease (PwPD). However, the association between anxiety levels and weight-shifting control remains ambiguous. This study investigated whether 1) weight-shifting control differed between PwPD with and without anxiety, and 2) the learning effect of weight-shifting differed between the two populations. Additionally, we evaluated cortical activities to investigate neural mechanisms underlying weight-shifting control. Twenty-eight PwPD (14 anxiety, 14 nonanxiety) participated in a 5-day weight-shifting study by coupling the bearing weight of their more-affected leg to a sinusoidal target at 0.25 Hz. We tested the weight-shifting control on day 1 (pretest), day 3 (posttest), and day 5 (retention test) with a learning session on day 3. The error and jerk of weight-shifting trajectory and the theta and gamma powers of electroencephalography in prefrontal, frontal, sensorimotor and parietal-occipital areas were measured. At the pretest, the anxiety group showed larger error and smaller jerk of weight-shifting with greater prefrontal theta, frontal gamma, and sensorimotor gamma powers than the nonanxiety group. Anxiety intensity was correlated positively with weight-shifting error and theta power but negatively with weight-shifting jerk. Reduced weight-shifting error with increased theta power after weight-shifting learning was observed in the nonanxiety group. However, the anxiety group showed decreased gamma power after weight-shifting learning without behavior change. Our findings suggest differential weight-shifting control and associated cortical activation between PwPD with and without anxiety. In addition, anxiety would deteriorate weight-shifting control and hinder weight-shifting learning benefits in PwPD, leading to less weight-shifting accuracy and correction.

A Learnable and Explainable Wavelet Neural Network for EEG Artifacts Detection and Classification

Electroencephalography (EEG) artifacts are very common in clinical diagnosis and can heavily impact diagnosis. Manual screening of artifact events is labor-intensive with little benefit. Therefore, exploring algorithms for automatic detection and classification of EEG artifacts can significantly assist clinical diagnosis. In this paper, we propose a learnable and explainable wavelet neural network (WaveNet) for EEG artifact detection and classification. The model is powered by the wavelet decomposition block based on invertible neural network, which can extract signal features without information loss, and a tree generator for building wavelet tree structure automatically. They provide the model with good feature extraction capabilities and explainability. To evaluate the model's performance more fairly, we introduce the base point level matching score (BASE) and the Event-Aligned Compensation Scoring (EACS) at the event level as two metrics for model performance evaluation. On the challenging Temple University EEG Artifact (TUAR) dataset, our model outperforms other baselines in terms of F1-score for both artifact detection and classification tasks. The case study also validates the model's ability to offer explainability for predictions based on frequency band energy, suggesting potential applications in clinical diagnosis.

OVME-REG: Harris hawks optimization algorithm based optimized variational mode extraction for eye blink artifact removal from EEG signal

The electroencephalogram (EEG) recordings from the human brain are useful for detecting various brain syndromes. These recordings are typically contaminated by high amplitude eye blink artifacts, which leads to deliberate misinterpretation of the EEG signal. Recently, variational mode extraction (VME) has been used to detect eye blink artifacts. But, the VME performance is impacted by the balancing parameter and center frequency selection. Therefore, this research uses two metaheuristic algorithms, particle swarm optimization and Harris hawks optimization, to determine the optimal set of the VME parameters. In the proposed method, the optimized VME (OVME) extracts the desired mode to locate the eye blink artifactual intervals. Then, the regression analysis (REG) filters the identified artifactual intervals from short EEG data segments. The significance of the proposed OVME-REG algorithm is that it is adequate for determining the optimum values of the VME algorithm. The analysis is carried out on the CHB-MIT Scalp EEG, BCI Competition, and EEG motor movement/imagery datasets. The proposed OVME-REG method provides an improved performance for suppressing single and repeated eye blink artifacts as compared to the current approaches in terms of (a) high correlation coefficient (93.08%, 87.3%, 82.17%), respectively, (b) low value of RRMSE (0.379, 0.506, 0.502), respectively, (c) high SSIM (0.892, 0.842, 0.694), and (d) low computation time and better preservation of the EEG data.

Dynamic Multi-Graph Convolution-Based Channel-Weighted Transformer Feature Fusion Network for Epileptic Seizure Prediction

Electroencephalogram (EEG) based seizure prediction plays an important role in the closed-loop neuromodulation system. However, most existing seizure prediction methods based on graph convolution network only focused on constructing the static graph, ignoring multi-domain dynamic changes in deep graph structure. Moreover, the existing feature fusion strategies generally concatenated coarse-grained epileptic EEG features directly, leading to the suboptimal seizure prediction performance. To address these issues, we propose a novel multi-branch dynamic multi-graph convolution based channel-weighted transformer feature fusion network (MB-dMGC-CWTFFNet) for the patient-specific seizure prediction with the superior performance. Specifically, a multi-branch (MB) feature extractor is first applied to capture the temporal, spatial and spectral representations fromthe epileptic EEG jointly. Then, we design a point-wise dynamic multi-graph convolution network (dMGCN) to dynamically learn deep graph structures, which can effectively extract high-level features from the multi-domain graph. Finally, by integrating the local and global channel-weighted strategies with the multi-head self-attention mechanism, a channel-weighted transformer feature fusion network (CWTFFNet) is adopted to efficiently fuse the multi-domain graph features. The proposed MB-dMGC-CWTFFNet is evaluated on the public CHB-MIT EEG and a private intracranial sEEG datasets, and the experimental results demonstrate that our proposed method achieves outstanding prediction performance compared with the state-of-the-art methods, indicating an effective tool for patient-specific seizure warning. Our code will be available at: https://github.com/Rockingsnow/MB-dMGC-CWTFFNet.

Cluster Embedding Joint-Probability-Discrepancy Transfer for Cross-Subject Seizure Detection

Transfer learning (TL) has been applied in seizure detection to deal with differences between different subjects or tasks. In this paper, we consider cross-subject seizure detection that does not rely on patient history records, that is, acquiring knowledge from other subjects through TL to improve seizure detection performance. We propose a novel domain adaptation method, named the Cluster Embedding Joint-Probability-Discrepancy Transfer (CEJT), for data distribution structure learning. Specifically, 1) The joint probability distribution discrepancy is minimized to reduce the distribution shift in the source and target domains, and strengthen the discriminative knowledge of classes. 2) A clustering is performed on the target domain, and the class centroids of sources is used as the clustering prototype of the target domain to enhance data structure. It is worth noting that the manifold regularization is used to improve the quality of clustering prototypes. In addition, a correlation-alignment-based source selection metric (SSC) is designed for most favorable subject selection, reducing the computational cost as well as avoiding some negative transfer. Experiments on 15 patients with focal epilepsy from the Children's Hospital, Zhejiang University School of Medicine (CHZU) database shown that CEJT outperforms several state-of-the-art approaches, and can promote the application of seizure detection.

Seizure Prediction Analysis of Infantile Spasms

Infantile spasms (IS) is a typical childhood epileptic disorder with generalized seizures. The sudden, frequent and complex characteristics of infantile spasms are the main causes of sudden death, severe comorbidities and other adverse consequences. Effective prediction is highly critical to infantile spasms subjects, but few related studies have been done in the past. To address this, this study proposes a seizure prediction framework for infantile spasms by combining the statistical analysis and deep learning model. The analysis is conducted on dividing the continuous scalp electroencephalograms (sEEG) into 5 phases: Interictal, Preictal, Seizure Prediction Horizon (SPH), Seizure, and Postictal. The brain network of Phase-Locking Value (PLV) of 5 typical brain rhythms is constructed, and the mechanism of epileptic changes is analyzed by statistical methods. It is found that 1) the connections between the prefrontal, occipital, and central regions show a large variability at each stage of seizure transition, and 2) 4 sub-bands of brain rhythms ( θ , α , β , γ ) are predominant. Group and individual variabilities are validated by using the Resnet18 deep model on data from 25 patients with infantile spasms, where the consistent results to statistical analyses can be observed. The optimized model achieves an average of 79.78 % , 94.46% , 75.46% accuracy, specificity, and recall rate, respectively. The method accomplishes the analysis of the synergy between infantile spasms mechanism, model, data and algorithm, providing a guideline to build an intelligent and systematic model for comprehensive IS seizure prediction.

Application of Deep Learning and WT-SST in Localization of Epileptogenic Zone Using Epileptic EEG Signals

Focal and non-focal Electroencephalogram (EEG) signals have proved to be effective techniques for identifying areas in the brain that are affected by epileptic seizures, known as the epileptogenic zones. The detection of the location of focal EEG signals and the time of seizure occurrence are vital information that help doctors treat focal epileptic seizures using a surgical method. This paper proposed a computer-aided detection (CAD) system for detecting and classifying focal and non-focal EEG signals as the manual process is time-consuming, prone to error, and tedious. The proposed technique employs time-frequency features, statistical, and nonlinear approaches to form a robust features extraction technique. Four detection and classification techniques for focal and non-focal EEG signals were proposed. (1). Combined hybrid features with Support Vector Machine (Hybrid-SVM) (2). Discrete Wavelet Transform with Deep Learning Network (DWT-DNN) (3). Combined hybrid features with DNN (Hybrid-DNN) as an optimized DNN model. Lastly, (4). A newly proposed technique using Wavelet Synchrosqueezing Transform-Deep Convolutional Neural Network (WTSST-DCNN). Prior to feeding the features to classifiers, statistical analyses, including t-tests, were deployed to obtain relevant and significant features at each approach. The proposed feature extraction technique and classification proved effective and suitable for smart Internet of Medical Things (IoMT) devices as performance parameters of accuracy, sensitivity, and specificity are higher than recently related works with a value of 99.7%, 99.5%, and 99.7% respectively.