Intracerebral EEG Artifact Identification Using Convolutional Neural Networks

Nejedlý, Petr; Cimbálník, Jan; Klimeš, Petr; Plešinger, Filip; Halámek, Josef; Kremen, Václav; Viščor, Ivo; Brinkmann, Benjamin H.; Pail, Martin; Brázdil, Milan; Worrell, Gregory A.; Jurák, Pavel

doi:10.1007/s12021-018-9397-6

Cited by 75 publications

(40 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SR-EEG simulation data with Gauss white noise or brain noise showed lower mean square error and higher correlation of sensor information, and they could detect the signal source more clearly than was possible in lowresolution (LR) EEG. Nejedly et al [23] developed a machine learning method using CNN to detect the artifacts of intracranial EEG (iEEG) signals under clinical control conditions, and the performance of this method is compared with that of expert notes. The results show that this method can be used as a general model of iEEG.…”

Section: Introductionmentioning

confidence: 99%

S-EEGNet: Electroencephalogram Signal Classification Based on a Separable Convolution Neural Network With Bilinear Interpolation

Huang

Xue

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As one of the most important research fields in the brain-computer interface (BCI) field, electroencephalogram (EEG) classification has a wide range of application values. However, for the EEG signal, it is difficult for the traditional neural networks to capture the characteristics of the EEG signal more comprehensively from the time and space dimensions, which has a certain effect on the accuracy of EEG classification. To solve this problem, we can improve the accuracy of classification via end-to-end learning of the time and space dimensions of EEG. In this paper, a new type of EEG classification network, the separable EEGNet (S-EEGNet), is proposed based on Hilbert-Huang transform (HHT) and a separable convolutional neural network (CNN) with bilinear interpolation. The EEG signal is transformed into time-frequency representation by HHT, which allows the EEG signal to be better described in the frequency domain. Then, the depthwise and pointwise elements of the network are combined to extract the feature map. The displacement variable is added by the bilinear interpolation method to the convolution layer of the separable CNN, allowing the free deformation of the sampling grid. The deformation depends on the local, dense, and adaptive input characteristics of the EEG data. The network can learn from the time and space dimensions of EEG signals end to end to extract features to improve the accuracy of EEG classification. To show the effectiveness of S-EEGNet, the team used this method to test two different types of EEG public datasets (motor imagery classification and emotion classification). The accuracy of motor imagery classification is 77.9%, and the accuracy of emotion classification is 89.91%, and 88.31%, respectively. The experimental results showed that the classification accuracy of S-EEGNet improved by 3.6%, 1.15%, and 1.33%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

S-EEGNet: Electroencephalogram Signal Classification Based on a Separable Convolution Neural Network With Bilinear Interpolation

Huang

Xue

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNNs) have demonstrated usefulness in a wide variety of industrial and scientific fields, including image recognition 11 , speech recognition 12 , biological signal processing and reinforcement learning 13 . CNNs have proven to be superior to traditional signal processing techniques in ECG and polysomnography classification during several challenges 14,15 and have been used in variety of EEG processing tasks 16 , for example iEEG noise detection 17 , epileptic seizure detection 18 and seizure prediction 19 .…”

Section: Introductionmentioning

confidence: 99%

“…In previous work 17 we developed a CNN method for differentiation of iEEG signals between artifact (machine acquisition artifacts and muscle artifacts), physiological activity and pathological epileptiform activity. The technique allowed large-scale data processing of wide bandwidth iEEG recordings (0.01–900 Hz; sampling frequency 5 kHz) with hundreds of channels spanning multiple days, with datasets reaching hundreds of gigabytes.…”

Section: Introductionmentioning

confidence: 99%

“…Here we extended our previously described approach 17 and developed and validated a Convolutional-LSTM neural network architecture, which enables partial interpretation of the CNN results using classification heatmaps. This allows for a visual inspection and correlation of the raw iEEG with the data segments driving the classification of the network, and extends our ability to interpret the CNN results, which was not possible with the previous method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Nejedlý

Kremen

Sladky

et al. 2019

Sci Rep

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…Meanwhile, complexity [ 43 ], dynamically identifying relevant EEG channels [ 44 ], and EEG fractal and spectral analysis [ 45 ] have aroused the interest of researchers. Moreover, removal of movement artifacts, ICA theory, and signal processing methods for EEG signals are recent hot topics [ 46 , 47 , 48 , 49 , 50 , 51 ]. These studies provided a solid foundation for the EEG signal applications and have resulted in a great amount of significant and challenging subjects in life sciences.…”

Section: Introductionmentioning

confidence: 99%

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

Sun

2019

Entropy

View full text Add to dashboard Cite

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.Entropy 2019, 21, 849 2 of 18 algorithm; thus, complexity can be analyzed in a multiple scale sense. After this, many different multiscale complexity algorithms such as the multiscale PE (MPE) algorithm [27], the multiscale SampEn algorithm [28], the multiscale permutation Rényi entropy [29], and the multivariate multiscale entropy [30] were designed. Among those methods, the PE algorithm and MPE algorithm have a fast estimation speed and are gaining more and more academic attention. Therefore, this article will concentrate on the PE algorithm.In 2002, Bandt and Pompe [23] proposed the PE algorithm based on the patterns deduced from constructed vectors. However, it was indicated in many literature works that the PE algorithm has some drawbacks that cannot always measure complexity effectively. For instance, Zunino et al. [31] figured out that the Bandt-Pompe method for processing equal values could lead to erroneous conclusions. Until now, how to improve the PE algorithm is still an open project. At present, several improved PE algorithms have been proposed. Bian et al. [32] modified the PE algorithm by mapping the equal value onto the same symbol (rank), and the modified PE (mPE) algorithm was designed. Fadlallah et al. [33] proposed the weighted PE (WPE) algorithm, and EEG signals were analyzed to verify its effectiveness. Azami et al. [34] indicated that PE does not consider the average of the amplitude values and equal amplitude values and designed the amplitude-aware permutation entropy (AAPE). Chen et al. [35]proposed the improved PE (IPE) algorithm by introducing a symbolic process and combining some advantages of previous modifications of PE. As a result, IPE has more patterns and better robustness for noise-polluted time series. Those algorithms have better measuring results when comparing with the original PE algorithm. However, they do not consider the relationship between different patterns since they actually treat the vectors as independent units. Currently, appro...

show abstract

Intracerebral EEG Artifact Identification Using Convolutional Neural Networks

Cited by 75 publications

References 33 publications

S-EEGNet: Electroencephalogram Signal Classification Based on a Separable Convolution Neural Network With Bilinear Interpolation

S-EEGNet: Electroencephalogram Signal Classification Based on a Separable Convolution Neural Network With Bilinear Interpolation

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

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

Contact Info

Product

Resources

About