Enhancing Motor Imagery Classification with Residual Graph Convolutional Networks and Multi-Feature Fusion

Stroke, an abrupt cerebrovascular ailment resulting in brain tissue damage, has prompted the adoption of motor imagery (MI)-based brain-computer interface (BCI) systems in stroke rehabilitation. However, analyzing electroencephalogram (EEG) signals from stroke patients poses challenges. To address the issues of low accuracy and efficiency in EEG classification, particularly involving MI, the study proposes a residual graph convolutional network (M-ResGCN) framework based on the modified S-transform (MST), and introduces the self-attention mechanism into residual graph convolutional network (ResGCN). This study uses MST to extract EEG time-frequency domain features, derives spatial EEG features by calculating the absolute Pearson correlation coefficient (aPcc) between channels, and devises a method to construct the adjacency matrix of the brain network using aPcc to measure the strength of the connection between channels. Experimental results involving 16 stroke patients and 16 healthy subjects demonstrate significant improvements in classification quality and robustness across tests and subjects. The highest classification accuracy reached 94.91% and a Kappa coefficient of 0.8918. The average accuracy and F1 scores from 10 times 10-fold cross-validation are 94.38% and 94.36%, respectively. By validating the feasibility and applicability of brain networks constructed using the aPcc in EEG signal analysis and feature encoding, it was established that the aPcc effectively reflects overall brain activity. The proposed method presents a novel approach to exploring channel relationships in MI-EEG and improving classification performance. It holds promise for real-time applications in MI-based BCI systems.

Time-frequency-space transformer EEG decoding for spinal cord injury

Transformer neural networks based on multi-head self-attention are effective in several fields. To capture brain activity on electroencephalographic (EEG) signals and construct an effective pattern recognition model, this paper explores the multi-channel deep feature decoding method utilizing the self-attention mechanism. By integrating inter-channel features with intra-channel features, the self-attention mechanism generates a deep feature vector that encompasses information from all brain activities. In this paper, a time-frequency-spatial domain analysis of motor imagery (MI) based EEG signals from spinal cord injury patients is performed to construct a transformer neural network-based MI classification model. The proposed algorithm is named time-frequency-spatial transformer. The time-frequency and spatial domain feature vectors extracted from the EEG signals are input into the transformer neural network for multiple self-attention depth feature encoding, a peak classification accuracy of 93.56% is attained through the fully connected layer. By constructing the attention matrix brain network, it can be inferred that the channel connections constructed by the attention heads have similarities to the brain networks constructed by the EEG raw signals. The experimental results reveal that the self-attention coefficient brain network holds significant potential for brain activity analysis. The self-attention coefficient brain network can better illustrate correlated connections and show sample differences. Attention coefficient brain networks can provide a more discriminative approach for analyzing brain activity in clinical settings.

Tracking EEG network dynamics through transitions between eyes-closed, eyes-open, and task states

Our study aimed to verify the possibilities of effectively applying chronnectomics methods to reconstruct the dynamic processes of network transition between three types of brain states, namely, eyes-closed rest, eyes-open rest, and a task state. The study involved dense EEG recordings and reconstruction of the source-level time-courses of the signals. Functional connectivity was measured using the phase lag index, and dynamic analyses concerned coupling strength and variability in alpha and beta frequencies. The results showed significant and dynamically specific transitions regarding processes of eyes opening and closing and during the eyes-closed-to-task transition in the alpha band. These observations considered a global dimension, default mode network, and central executive network. The decrease of connectivity strength and variability that accompanied eye-opening was a faster process than the synchronization increase during eye-opening, suggesting that these two transitions exhibit different reorganization times. While referring the obtained results to network studies, it was indicated that the scope of potential similarities and differences between rest and task-related networks depends on whether the resting state was recorded in eyes closed or open condition.

Event-related Potentials Corresponding to Decision-making Under Uncertain Conditions

BACKGROUND

Decision-making is essential to human functioning, and resolving uncertainty is an essential part of decision-making. Impaired decision-making is present in many pathological conditions, and identifying markers of decision-making under uncertainty will provide a measure of clinical impact in future studies of therapeutic intervention for impaired decision-making.

OBJECTIVE

To describe EEG event-related potentials (ERPs) correlating with decision-making under uncertain conditions when compared with certain conditions.

METHOD

We used a novel card-matching task based on the Wisconsin Card Sorting Test to describe the neural correlates of uncertainty, as measured by EEG, in a group of 27 neurotypical individuals. We evaluated 500-ms intervals in the 2 seconds after card presentation to identify ERPs that are associated with maximal uncertainty compared with maximal certainty.

RESULTS

After correcting for multiple comparisons, we identified an ERP in the 500-1000-ms time frame (certain > uncertain, max amplitude 12.73 µV, latency 914 ms) in the left posterior inferior region of the scalp. We also found a P300-like ERP in the left frontal and parietal regions in the 0-500-ms time frame when the individuals received correct versus incorrect feedback (incorrect feedback > correct feedback, max amplitude 1.625 µV, latency 339 ms).

CONCLUSION

We identified an ERP in the 500-1000-ms time frame (certain > uncertain) that may reflect the resolution of uncertainty, as well as a P300-like ERP when feedback is presented (incorrect feedback > correct feedback). These findings can be used in future studies to improve decision-making and resolve uncertainty on the described markers.

Discrimination of auditory verbal hallucination in schizophrenia based on EEG brain networks

Auditory verbal hallucinations (AVH) are a core positive symptom of schizophrenia and are regarded as a consequence of the functional breakdown in the related sensory process. Yet, the potential mechanism of AVH is still lacking. In the present study, we explored the difference between AVHs (n = 23) and non-AVHs (n = 19) in schizophrenia and healthy controls (n = 29) by using multidimensional electroencephalograms data during an auditory oddball task. Compared to healthy controls, both AVH and non-AVH groups showed reduced P300 amplitudes. Additionally, the results from brain networks analysis revealed that AVH patients showed reduced left frontal to posterior parietal/temporal connectivity compared to non-AVH patients. Moreover, using the fused network properties of both delta and theta bands as features for in-depth learning made it possible to identify the AVH from non-AVH patients at an accuracy of 80.95%. The left frontal-parietal/temporal networks seen in the auditory oddball paradigm might be underlying biomarkers of AVH in schizophrenia. This study demonstrated for the first time the functional breakdown of the auditory processing pathway in the AVH patients, leading to a better understanding of the atypical brain network of the AVH patients.

Global Functional Connectivity at Rest Is Associated with Attention: An Arterial Spin Labeling Study

Neural markers of attention, including those frequently linked to the event-related potential P3 (P300) or P3b component, vary widely within and across participants. Understanding the neural mechanisms of attention that contribute to the P3 is crucial for better understanding attention-related brain disorders. All ten participants were scanned twice with a resting-state PCASL perfusion MRI and an ERP with a visual oddball task to measure brain resting-state functional connectivity (rsFC) and P3 parameters (P3 amplitudes and P3 latencies). Global rsFC (average rsFC across the entire brain) was associated with both P3 amplitudes (r = 0.57, p = 0.011) and P3 onset latencies (r = -0.56, p = 0.012). The observed P3 parameters were correlated with predicted P3 amplitude from the global rsFC (amplitude: r = +0.48, p = 0.037; latency: r = +0.40, p = 0.088) but not correlated with the rsFC over the most significant individual edge. P3 onset latency was primarily related to long-range connections between the prefrontal and parietal/limbic regions, while P3 amplitudes were related to connections between prefrontal and parietal/occipital, between sensorimotor and subcortical, and between limbic/subcortical and parietal/occipital regions. These results demonstrated the power of resting-state PCASL and P3 correlation with brain global functional connectivity.

A Novel Method for Constructing EEG Large-Scale Cortical Dynamical Functional Network Connectivity (dFNC): WTCS

As a kind of biological network, the brain network conduces to understanding the mystery of high-efficiency information processing in the brain, which will provide instructions to develop efficient brain-like neural networks. Large-scale dynamical functional network connectivity (dFNC) provides a more context-sensitive, dynamical, and straightforward sight at a higher network level. Nevertheless, dFNC analysis needs good enough resolution in both temporal and spatial domains, and the construction of dFNC needs to capture the time-varying correlations between two multivariate time series with unmatched spatial dimensions. Effective methods still lack. With well-developed source imaging techniques, electroencephalogram (EEG) has the potential to possess both high temporal and spatial resolutions. Therefore, we proposed to construct the EEG large-scale cortical dFNC based on brain atlas to probe the subtle dynamic activities in the brain and developed a novel method, that is, wavelet coherence-S estimator (WTCS), to assess the dynamic couplings among functional subnetworks with different spatial dimensions. The simulation study demonstrated its robustness and availability of applying to dFNC. The application in real EEG data revealed the appealing "Primary peak" and "P3-like peak" in dFNC network properties and meaningful evolutions in dFNC network topology for P300. Our study brings new insights for probing brain activities at a more dynamical and higher hierarchical level and pushing forward the development of brain-inspired artificial neural networks. The proposed WTCS not only benefits the dFNC studies but also gives a new solution to capture the time-varying couplings between the multivariate time series that is often encountered in signal processing disciplines.

Constructing Time-varying Directed EEG network by Multivariate Nonparametric Dynamical Granger Causality

Time-varying directed electroencephalography (EEG) network is the potential tool for studying the dynamical causality among brain areas at a millisecond level; which conduces to understanding how our brain effectively adapts to information processing, giving inspiration to causality- and brain-inspired machine learning. Currently, its construction still mainly relies on the parametric approach such as multivariate adaptive autoregressive (MVAAR), represented by the most widely used adaptive directed transfer function (ADTF). Restricted by the model assumption, the corresponding performance largely depends on the MVAAR modeling which usually encounters difficulty in fitting complex spectral features. In this study, we proposed to construct EEG directed network with multivariate nonparametric dynamical Granger causality (mndGC) method that infers the causality of a network, instead, in a data-driven way directly and therefore avoids the trap in the model-dependent parametric approach. Comparisons between mndGC and ADTF were conducted both with simulation and real data application. Simulation study demonstrated the superiority of mndGC both in noise resistance and capturing the instantaneous directed network changes. When applying to the real motor imagery (MI) data set, distinguishable network characters between left- and right-hand MI during different MI stages were better revealed by mndGC. Our study extends the nonparametric causality exploration and provides practical suggestions for the time-varying directed EEG network analysis.

Altered temporal variability in brain functional connectivity identified by fuzzy entropy underlines schizophrenia deficits

Investigation of the temporal variability of resting-state brain networks informs our understanding of how neural connectivity aggregates and disassociates over time, further shedding light on the aberrant neural interactions that underlie symptomatology and psychosis development. In the current work, an electroencephalogram-based sliding window analysis was utilized for the first time to measure the nonlinear complexity of dynamic resting-state brain networks of schizophrenia (SZ) patients by applying fuzzy entropy. The results of this study demonstrated the attenuated temporal variability among multiple electrodes that were distributed in the frontal and right parietal lobes for SZ patients when compared with healthy controls (HCs). Meanwhile, a concomitant strengthening of the posterior and peripheral flexible connections that may be attributed to the excessive alertness or sensitivity of SZ patients to the external environment was also revealed. These temporal fluctuation distortions combined reflect an abnormality in the coordination of functional network switching in SZ, which is further the source of worse task performance (i.e., P300 amplitude) and the negative relationship between individual complexity metrics and P300 amplitude. Notably, when using the network metrics as features, multiple linear regressions of P300 amplitudes were also exactly achieved for both the SZ and HC groups. These findings shed light on the pathophysiological mechanisms of SZ from a temporal variability perspective and provide potential biomarkers for quantifying SZ's progressive neurophysiological deterioration.

A survey of brain network analysis by electroencephalographic signals

Brain network analysis is one efficient tool in exploring human brain diseases and can differentiate the alterations from comparative networks. The alterations account for time, mental states, tasks, individuals, and so forth. Furthermore, the changes determine the segregation and integration of functional networks that lead to network reorganization (or reconfiguration) to extend the neuroplasticity of the brain. Exploring related brain networks should be of interest that may provide roadmaps for brain research and clinical diagnosis. Recent electroencephalogram (EEG) studies have revealed the secrets of the brain networks and diseases (or disorders) within and between subjects and have provided instructive and promising suggestions and methods. This review summarized the corresponding algorithms that had been used to construct functional or effective networks on the scalp and cerebral cortex. We reviewed EEG network analysis that unveils more cognitive functions and neural disorders of the human and then explored the relationship between brain science and artificial intelligence which may fuel each other to accelerate their advances, and also discussed some innovations and future challenges in the end.

Identification of the General Anesthesia Induced Loss of Consciousness by Cross Fuzzy Entropy-Based Brain Network

Although the spatiotemporal complexity and network connectivity are clarified to be disrupted during the general anesthesia (GA) induced unconsciousness, it remains to be difficult to exactly monitor the fluctuation of consciousness clinically. In this study, to track the loss of consciousness (LOC) induced by GA, we first developed the multi-channel cross fuzzy entropy method to construct the time-varying networks, whose temporal fluctuations were then explored and quantitatively evaluated. Thereafter, an algorithm was further proposed to detect the time onset at which patients lost their consciousness. The results clarified during the resting state, relatively stable fuzzy fluctuations in multi-channel network architectures and properties were found; by contrast, during the LOC period, the disrupted frontal-occipital connectivity occurred at the early stage, while at the later stage, the inner-frontal connectivity was identified. When specifically exploring the early LOC stage, the uphill of the clustering coefficients and the downhill of the characteristic path length were found, which might help resolve the propofol-induced consciousness fluctuation in patients. Moreover, the developed detection algorithm was validated to have great capacity in exactly capturing the time point (in seconds) at which patients lost consciousness. The findings demonstrated that the time-varying cross-fuzzy networks help decode the GA and are of great significance for developing anesthesia depth monitoring technology clinically.

Blind Visualization of Task-Related Networks From Visual Oddball Simultaneous EEG-fMRI Data: Spectral or Spatiospectral Model?

Various disease conditions can alter EEG event-related responses and fMRI-BOLD signals. We hypothesized that event-related responses and their clinical alterations are imprinted in the EEG spectral domain as event-related (spatio)spectral patterns (ERSPat). We tested four EEG-fMRI fusion models utilizing EEG power spectra fluctuations (i.e., absolute spectral model - ASM; relative spectral model - RSM; absolute spatiospectral model - ASSM; and relative spatiospectral model - RSSM) for fully automated and blind visualization of task-related neural networks. Two (spatio)spectral patterns (high δ 4 band and low β 1 band) demonstrated significant negative linear relationship (p FWE < 0.05) to the frequent stimulus and three patterns (two low δ 2 and δ 3 bands, and narrow θ 1 band) demonstrated significant positive relationship (p < 0.05) to the target stimulus. These patterns were identified as ERSPats. EEG-fMRI F-map of each δ 4 model showed strong engagement of insula, cuneus, precuneus, basal ganglia, sensory-motor, motor and dorsal part of fronto-parietal control (FPCN) networks with fast HRF peak and noticeable trough. ASM and RSSM emphasized spatial statistics, and the relative power amplified the relationship to the frequent stimulus. For the δ 4 model, we detected a reduced HRF peak amplitude and a magnified HRF trough amplitude in the frontal part of the FPCN, default mode network (DMN) and in the frontal white matter. The frequent-related β 1 patterns visualized less significant and distinct suprathreshold spatial associations. Each θ 1 model showed strong involvement of lateralized left-sided sensory-motor and motor networks with simultaneous basal ganglia co-activations and reduced HRF peak and amplified HRF trough in the frontal part of the FPCN and DMN. The ASM θ 1 model preserved target-related EEG-fMRI associations in the dorsal part of the FPCN. For δ 4, β 1, and θ 1 bands, all models provided high local F-statistics in expected regions. The most robust EEG-fMRI associations were observed for ASM and RSSM.