In clinical practice, EEGs are assessed visually. For practical reasons, recordings often need to be performed with a reduced number of electrodes and artifacts make assessment difficult. To circumvent these obstacles, different interpolation techniques can be utilized. These techniques usually perform better for higher electrode densities and values interpolated at areas far from electrodes can be unreliable. Using a method that learns the statistical distribution of the cortical electrical fields and predicts values may yield better results. Generative networks based on convolutional layers were trained to upsample from 4 or 14 channels or to dynamically restore single missing channels to recreate 21-channel EEGs. 5,144 h of data from 1,385 subjects of the Temple University Hospital EEG database were used for training and evaluating the networks. The results were compared to spherical spline interpolation. Several statistical measures were used as well as a visual evaluation by board certified clinical neurophysiologists. Overall, the generative networks performed significantly better. There was no difference between real and network generated data in the number of examples assessed as artificial by experienced EEG interpreters whereas for data generated by interpolation, the number was significantly higher. In addition, network performance improved with increasing number of included subjects, with the greatest effect seen in the range 5-100 subjects. Using neural networks to restore or upsample EEG signals is a viable alternative to spherical spline interpolation.
T-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation, and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data are usually first transformed into a set of features, but it is not known which features are optimal. The principle of t-SNE was used to train convolutional neural network (CNN) encoders to learn to produce both a high- and a low-dimensional representation, eliminating the need for feature engineering. To evaluate the method, the Temple University EEG Corpus was used to create three datasets with distinct EEG characters: (1) wakefulness and sleep; (2) interictal epileptiform discharges; and (3) seizure activity. The CNN encoders produced low-dimensional representations of the datasets with a structure that conformed well to the EEG characters and generalized to new data. Compared to parametric t-SNE for either a short-time Fourier transform or wavelet representation of the datasets, the developed CNN encoders performed equally well in separating categories, as assessed by support vector machines. The CNN encoders generally produced a higher degree of clustering, both visually and in the number of clusters detected by k-means clustering. The developed principle is promising and could be further developed to create general tools for exploring relations in EEG data.
Background: In clinical practice, EEGs are assessed visually. For practical reasons, recordings often need to be performed with a reduced number of electrodes and artifacts make assessment difficult. To circumvent these obstacles, different interpolation techniques can be utilized. These techniques usually perform better for higher electrode densities and values interpolated at areas far from electrodes can be unreliable. Using a method that learns the statistical distribution of the cortical electrical fields and predicts values may yield better results. New Method: Generative networks based on convolutional layers were trained to upsample from 4 or 14 channels or to dynamically restore single missing channels to recreate 21 channel EEGs. 5,144 hours of data from 1,385 subjects of the Temple University Hospital EEG database were used for training and evaluating the networks. Comparison with Existing Method: The results were compared to spherical spline interpolation. Several statistical measures were used as well as a visual evaluation by board certified clinical neurophysiologists. Overall, the generative networks performed significantly better. There was no difference between real and network generated data in the number of examples assessed as artificial by experienced EEG interpreters whereas for data generated by interpolation, the number was significantly higher. In addition, network performance improved with increasing number of included subjects, with the greatest effect seen in the range 5 – 100 subjects. Conclusions: Using neural networks to restore or upsample EEG signals is a viable alternative to interpolation methods.
10 May 2021 in International Journal of Neurology and Neurotherapy
Trans-spinal Direct Current Stimulation (tsDCS) can alleviate pain perception in humans through plastic processes. Brain Derived Neurotrophic Factor (BDNF) has been shown to influence a large number of physiological processes including those underpinning neural plasticity. A common polymorphism of BDNF (val66met), reduces the efficiency of plastic processes. We studied the effect of this BDNF polymorphism on the signalling and perception of thermal pain and to what degree these can be influenced by tsDCS in young healthy adults.
Background t-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data is usually first transformed into a set of features, but it is not known which features are optimal. New method The principle of t-SNE was used to train convolutional neural network (CNN) encoders to learn to produce both a high- and a low-dimensional representation, eliminating the need for feature engineering. A simple neighbor distribution based on ranked distances was used for the high-dimensional representation instead of the traditional normal distribution. To evaluate the method, the Temple University EEG Corpus was used to create three datasets with distinct EEG characters: 1) wakefulness and sleep, 2) interictal epileptiform discharges, and 3) seizure activity. Results The CNN encoders for the three datasets produced low-dimensional representations of the datasets with a global and local structure that conformed well to the EEG characters and generalized to new data. Comparison to existing methods Compared to parametric t-SNE for either a short-time Fourier transforms or wavelet representation of the datasets, the developed CNN encoders performed equally well but generally produced a higher degree of clustering. Conclusions The developed principle is promising and could be further developed to create general tools for exploring relations in EEG data, e.g., visual summaries of recordings, and trends for continuous EEG monitoring. It might also be used to generate features for other types of machine learning.