In this paper, a feature extraction algorithm of weighted multiple multiscale entropy is proposed to solve the problem of information loss which is caused in the multiscale process of traditional multiscale entropy. Algorithm constructs the multiple data sequences from large to small on each scale. Then, considering the different contribution degrees of multiple data sequences to the entropy of the scale, the proportion of each sequence in the scale sequence is calculated by combining the correlation between the data sequences, so as to reconstruct the sample entropy of each scale. Compared with the traditional multiscale entropy the feature extraction algorithm based on weighted multiple multiscale entropy not only overcomes the problem of information loss, but also fully considers the correlation of sequences and the contribution to total entropy. It reduces the fluctuation between scales, and digs out the details of electroencephalography (EEG). Based on this algorithm, the EEG characteristics of autism spectrum disorder (ASD) children are analyzed, and the classification accuracy of the algorithm is increased by 23.0%, 10.4% and 6.4% as compared with the EEG extraction algorithm of sample entropy, traditional multiscale entropy and multiple multiscale entropy based on the delay value method, respectively. Based on this algorithm, the 19 channel EEG signals of ASD children and healthy children were analyzed. The results showed that the entropy of healthy children was slightly higher than that of the ASD children except the FP2 channel, and the numerical differences of F3, F7, F8, C3 and P3 channels were statistically significant (P<0.05). By classifying the weighted multiple multiscale entropy of each brain region, we found that the accuracy of the anterior temporal lobe (F7, F8) was the highest. It indicated that the anterior temporal lobe can be used as a sensitive brain area for assessing the brain function of ASD children.
Uncovering the alterations of neural interactions within the brain during epilepsy is important for the clinical diagnosis and treatment. Previous studies have shown that the phase-amplitude coupling (PAC) can be used as a potential biomarker for locating epileptic zones and characterizing the transition of epileptic phases. However, in contrast to the θ-γ coupling widely investigated in epilepsy, few studies have paid attention to the β-γ coupling, as well as its potential applications. In the current study, we use the modulation index (MI) to calculate the scalp electroencephalography (EEG)-based β-γ coupling and investigate the corresponding changes during different epileptic phases. The results show that the β-γ coupling of each brain region changes with the evolution of epilepsy, and in several brain regions, the β-γ coupling decreases during the ictal period but increases in the post-ictal period, where the differences are statistically significant. Moreover, the alterations of β-γ coupling between different brain regions can also be observed, and the strength of β-γ coupling increases in the post-ictal period, where the differences are also significant. Taken together, these findings not only contribute to understanding neural interactions within the brain during the evolution of epilepsy, but also provide a new insight into the clinical treatment.
Aiming at the problem that the feature extraction ability of forehead single-channel electroencephalography (EEG) signals is insufficient, which leads to decreased fatigue detection accuracy, a fatigue feature extraction and classification algorithm based on supervised contrastive learning is proposed. Firstly, the raw signals are filtered by empirical modal decomposition to improve the signal-to-noise ratio. Secondly, considering the limitation of the one-dimensional signal in information expression, overlapping sampling is used to transform the signal into a two-dimensional structure, and simultaneously express the short-term and long-term changes of the signal. The feature extraction network is constructed by depthwise separable convolution to accelerate model operation. Finally, the model is globally optimized by combining the supervised contrastive loss and the mean square error loss. Experiments show that the average accuracy of the algorithm for classifying three fatigue states can reach 75.80%, which is greatly improved compared with other advanced algorithms, and the accuracy and feasibility of fatigue detection by single-channel EEG signals are significantly improved. The results provide strong support for the application of single-channel EEG signals, and also provide a new idea for fatigue detection research.
Epileptic seizures and the interictal epileptiform discharges both have similar waveforms. And a method to effectively extract features that can be used to distinguish seizures is of crucial importance both in theory and clinical practice. We constructed state transfer networks by using visibility graphlet at multiple sampling intervals and analyzed network features. We found that the characteristics waveforms in ictal periods were more robust with various sampling intervals, and those feature network structures did not change easily in the range of the smaller sampling intervals. Inversely, the feature network structures of interictal epileptiform discharges were stable in range of relatively larger sampling intervals. Furthermore, the feature nodes in networks during ictal periods showed long-term correlation along the process, and played an important role in regulating system behavior. For stereo-electroencephalography at around 500 Hz, the greatest difference between ictal and the interictal epileptiform occurred at the sampling interval around 0.032 s. In conclusion, this study effectively reveals the correlation between the features of pathological changes in brain system and the multiple sampling intervals, which holds potential application value in clinical diagnosis for identifying, classifying, and predicting epilepsy.
ObjectiveThe aim of this study is to identify clinical and electroencephalographic features associated with refractoriness to the initial antiepileptic drug in typical benign childhood epilepsy with centrotemporal spikes (BECTS). MethodsA total of 87 children with typical BECTS were retrospectively reviewed in the analyses.The patients were subdivided into two groups:patients whose seizures were controlled with monotherapy, and those requiring two medications. 63 childrenachieved seizure-freedom with monotherapy, while 24 received two medications for seizure control. ResultsDiffusing foci at the follow-up EEG and delayed treatment (duration > 1 year) are two main risk factors associated with more refractory cases (P < 0.001). Delayed diagnosis (37.1%) and non-adherence to treatment (57.2%) contributed to delayed treatment. ConclusionsOur findings suggested that diffusing foci on EEG and delayed treatment are associated with more frequent seizures and refractoriness in BECTS. Diagnostic delays and non-adherence hindered timely care, which may represent opportunities for improved intervention.
The brain-computer interface (BCI) based on motor imagery electroencephalography (EEG) shows great potential in neurorehabilitation due to its non-invasive nature and ease of use. However, motor imagery EEG signals have low signal-to-noise ratios and spatiotemporal resolutions, leading to low decoding recognition rates with traditional neural networks. To address this, this paper proposed a three-dimensional (3D) convolutional neural network (CNN) method that learns spatial-frequency feature maps, using Welch method to calculate the power spectrum of EEG frequency bands, converted time-series EEG into a brain topographical map with spatial-frequency information. A 3D network with one-dimensional and two-dimensional convolutional layers was designed to effectively learn these features. Comparative experiments demonstrated that the average decoding recognition rate reached 86.89%, outperforming traditional methods and validating the effectiveness of this approach in motor imagery EEG decoding.
The quality of sleep has a great relationship with health and working efficiency. The result of sleep stage classification is an important indicator to measure the quality of sleep, and it is also an important way to diagnose and treat sleep disorders. In this paper, the method of detrended cross-correlation analysis (DCCA) was used to analyze sleep stage classification, sleep electroencephalograph signals, which were extracted from the MIT-BIH Polysomnographic Database randomly. The results showed that the average DCCA exponent of the awake period is smaller than that of the first stage of non-rapid eye movement (NREM) sleeps. It is well concluded that the method of studying the sleep electroencephalograph with this method is of great significance to improve the quality of sleep, to diagnose and to treat sleep disorders.
Objective To research clinical manifestations, electrophysiological characteristics of epileptic seizures arising from diagonal sulci (DS), to improve the level of the diagnosis and treatment of frontal epilepsy. MethodsWe reviewed all the patients underwent a detailed presurgical evaluation, including 5 patients with seizures to be proved originating from diagonal sulci by Stereo-electroencephalography (SEEG). All the 5 patients with detailed medical history, head Magnetic resonance (MRI), the Positron emission computered tomography (PET-CT) and psychological evaluation, habitual seizures were recorded by Video-electroencephalography (VEEG) and SEEG, we review the intermittent VEEG and ictal VEEG, analyzing the symptoms of seizures. Results 5 patients were divided into 2 groups by SEEG, group 1 including 3 patients with seizures arising from the bottom of DS, group 2 including 2 patients with seizures arising from the surface of DS, all the tow groups with seizures characterized by both having tonic and complex motors, tonic seizures were prominent in seizures from left DS, and tonic seizures may absent in seizures from right DS. Intermittent discharges with group1 were diffused, and intermittent discharges with group 2 were focal, but both brain areas of frontal and temporal were infected. Ictal EEG findings were consistent with the characteristics of neocortical seizures, the onset EEG shows voltage attenuation, seizures from bottom of DS with diffused EEG onset, and seizures from surface of DS with more focal EEG onset, but both frontal and anterior temporal regions were involved. Conclusionthe symptom of seizures arising from DS characterized by tonic and complex motor, can be divided into seizures arising from the bottom of DS and seizures from the surface of DS, with different electrophysiological characters.
ObjectiveTo investigate characteristics of motor semiology of epileptic seizure originated from dorsolateral frontal lobe. MethodsRetrospectively analysis the clinical profiles of patients who were diagnosed dorsolateral frontal lobe epilepsy (FLE) based on stereoelectroencephalography (SEEG) and underwent respective surgeries subsequently. Component of motor semiology in a seizure can be divided into elementary motor (EM, include tonic, versive, clonic, and myoclonic seizures) and complex motor (CM, include automotor, hypermotor, and so on). A Talairach coordinate system was constructed in the sagittal series of MRI images in each case. From the cross point of VAC and the Sylvian Fissure, a line was drawn antero-superiorly, which made an angle of 60° with the AC-PC line, then the frontal lobe could be divided into anterior and posterior portion. The epileptogenic zone, which was defined as ictal onset and early spreading zone in SEEG, was classified into three types, according to the positional relationship of the responding electrodes contacts and the "60° line": the anterior, posterior, and intermediate FLE. The correlation of the components of motor semiology in seizures and the location of the epileptogenic zone was analyzed. ResultsFive cases (26.3%) were verified as anterior FLE, among which there were 2 of EM, one of CM, and 2 of EM+CM. In 7 cases (36.8%) of intermediate FLE, there were one of EM, none of CM, and 6 of EM+CM. In the rest 7 cases of posterior FLE, there were 6 of EM, none of CM, and one of EM+CM. Compared with the cases that the epileptogenic zone involved anterior portion, the posterior FLE is more likely to present EM seizures (85.7%), and less likely to show CM components (P < 0.05). And Compared with the anterior FLE and posterior FLE, the intermediate FLE is more likely to present EM+CM seizures (85.7%)(P < 0.05). ConclusionThe motor seizure semiology of dorsolateral FLE has significant correlation with the localization of the epileptogenic zone. Posterior FLE mainly present a pure elementary motor seizure, and once the epileptogenic zone involved anteriorly beyond the "60° line", the component of complex motor seizure would be seen. Intermediate FLE, as its specialty of transboundary, is more likely to show "comprised semiology" of EM and CM. Construction of the "60° line" with AC-PC coordinate system in the MRI images may play an useful role in semiology analysis in presurgical evaluation of FLE.
ObjectiveTo evaluate the application of stereotactic electrode implantation on precise epileptogenic zone localization. MethodRetrospectively studied 140 patients with drug-resist epilepsy from March 2012 to June 2015, who undergone a procedure of intracranial stereotactic electrode for localized epileptogenic zone. ResultsIn 140 patients who underwent the ROSA navigated implantation of intracranial electrode, 109 are unilateral implantation, 31 are bilateral; 3 patients experienced an intracranial hematoma caused by the implantation. Preserved time of electrodes, on average, 8.4days (range 2~35 days); Obseved clinical seizures, on average, 10.8 times per pt (range 0~98 times); There were no cerebrospinal fluid leak, intracranial hematoma, electrodes fracture or patient death, except 2 pt's scalp infection (1.43%, scalp infection rate); 131 pts' seizure onset area was precisely localized; 71 pts underwent SEEG-guide resections and were followed up for more than 6 months. In the group of 71 resection pts, 56 pts were reached Engel I class, 2 were Engel Ⅱ, 3 was Engel Ⅲ and 10 were Engel IV class. ConclusionTo intractable epilepsy, when non-invasive assessments can't find the epileptogenic foci, intracranial electrode implantation combined with long-term VEEG is an effective method to localize the epileptogenic foci, especially the ROSA navigated stereotactic electrode implantation, which is a micro-invasive, short-time, less-complication, safe-guaranteed, and precise technique.