scholarly journals ConvDip: A convolutional neural network for better M/EEG Source Imaging

2020 ◽  
Author(s):  
Lukas Hecker ◽  
Rebekka Rupprecht ◽  
Ludger Tebartz van Elst ◽  
Juergen Kornmeier
Keyword(s):  
Neural Network ◽  
Inverse Problem ◽  
Convolutional Neural Network ◽  
Brain Activity ◽  
Clinical Diagnostics ◽  
Dipole Model ◽  
Source Imaging ◽  
Eeg Source Imaging ◽  
Eeg Data ◽  
Inverse Solutions

AbstractEEG and MEG are well-established non-invasive methods in neuroscientific research and clinical diagnostics. Both methods provide a high temporal but low spatial resolution of brain activity. In order to gain insight about the spatial dynamics of the M/EEG one has to solve the inverse problem, which means that more than one configuration of neural sources can evoke one and the same distribution of EEG activity on the scalp. Artificial neural networks have been previously used successfully to find either one or two dipoles sources. These approaches, however, have never solved the inverse problem in a distributed dipole model with more than two dipole sources. We present ConvDip, a novel convolutional neural network (CNN) architecture that solves the EEG inverse problem in a distributed dipole model based on simulated EEG data. We show that (1) ConvDip learned to produce inverse solutions from a single time point of EEG data and (2) outperforms state-of-the-art methods (eLORETA and LCMV beamforming) on all focused performance measures. (3) It is more flexible when dealing with varying number of sources, produces less ghost sources and misses less real sources than the comparison methods. (4) It produces plausible inverse solutions for real-world EEG recordings and needs less than 40 ms for a single forward pass. Our results qualify ConvDip as an efficient and easy-to-apply novel method for source localization in EEG and MEG data, with high relevance for clinical applications, e.g. in epileptology and real time applications.

scholarly journals ConvDip: A Convolutional Neural Network for Better EEG Source Imaging

2021 ◽  
Vol 15 ◽  
Author(s):  
Lukas Hecker ◽  
Rebekka Rupprecht ◽  
Ludger Tebartz Van Elst ◽  
Jürgen Kornmeier
Keyword(s):  
Neural Network ◽  
Inverse Problem ◽  
Convolutional Neural Network ◽  
Clinical Diagnostics ◽  
Dipole Model ◽  
Eeg Activity ◽  
Eeg Source Imaging ◽  
Eeg Data ◽  
Inverse Solutions ◽  
Dipole Sources

The electroencephalography (EEG) is a well-established non-invasive method in neuroscientific research and clinical diagnostics. It provides a high temporal but low spatial resolution of brain activity. To gain insight about the spatial dynamics of the EEG, one has to solve the inverse problem, i.e., finding the neural sources that give rise to the recorded EEG activity. The inverse problem is ill-posed, which means that more than one configuration of neural sources can evoke one and the same distribution of EEG activity on the scalp. Artificial neural networks have been previously used successfully to find either one or two dipole sources. These approaches, however, have never solved the inverse problem in a distributed dipole model with more than two dipole sources. We present ConvDip, a novel convolutional neural network (CNN) architecture, that solves the EEG inverse problem in a distributed dipole model based on simulated EEG data. We show that (1) ConvDip learned to produce inverse solutions from a single time point of EEG data and (2) outperforms state-of-the-art methods on all focused performance measures. (3) It is more flexible when dealing with varying number of sources, produces less ghost sources and misses less real sources than the comparison methods. It produces plausible inverse solutions for real EEG recordings from human participants. (4) The trained network needs <40 ms for a single prediction. Our results qualify ConvDip as an efficient and easy-to-apply novel method for source localization in EEG data, with high relevance for clinical applications, e.g., in epileptology and real-time applications.

scholarly journals Part-of-Speech Classification from Magnetoencephalography Data Using 1-Dimensional Convolutional Neural Network

2020 ◽  
Author(s):  
Alessandro Lopopolo ◽  
Antal van den Bosch
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Mental State ◽  
Human Subjects ◽  
Brain Activity ◽  
Neural Decoding ◽  
Significant Progress ◽  
Part Of Speech ◽  
Syntactic Information ◽  
Speech Classification

Neural decoding of speech and language refers to the extraction of information regarding the stimulus and the mental state of subjects from recordings of their brain activity while performing linguistic tasks. Recent years have seen significant progress in the decoding of speech from cortical activity. This study instead focuses on decoding linguistic information. We present a deep parallel temporal convolutional neural network (1DCNN) trained on part-of-speech (PoS) classification from magnetoencephalography (MEG) data collected during natural language reading. The network is trained on data from 15 human subjects separately, and yields above-chance accuracies on test data for all of them. The level of PoS was targeted because it offers a clean linguistic benchmark level that represents syntactic information and abstracts away from semantic or conceptual representations.

scholarly journals A Novel Convolutional Neural Network Classification Approach of Motor-Imagery EEG Recording Based on Deep Learning

2021 ◽  
Vol 11 (21) ◽  
pp. 9948
Author(s):  
Amira Echtioui ◽  
Ayoub Mlaouah ◽  
Wassim Zouch ◽  
Mohamed Ghorbel ◽  
Chokri Mhiri ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Signal To Noise Ratio ◽  
Eeg Signals ◽  
Learning Techniques ◽  
Eeg Data ◽  
Spatial And Temporal Characteristics

Recently, Electroencephalography (EEG) motor imagery (MI) signals have received increasing attention because it became possible to use these signals to encode a person’s intention to perform an action. Researchers have used MI signals to help people with partial or total paralysis, control devices such as exoskeletons, wheelchairs, prostheses, and even independent driving. Therefore, classifying the motor imagery tasks of these signals is important for a Brain-Computer Interface (BCI) system. Classifying the MI tasks from EEG signals is difficult to offer a good decoder due to the dynamic nature of the signal, its low signal-to-noise ratio, complexity, and dependence on the sensor positions. In this paper, we investigate five multilayer methods for classifying MI tasks: proposed methods based on Artificial Neural Network, Convolutional Neural Network 1 (CNN1), CNN2, CNN1 with CNN2 merged, and the modified CNN1 with CNN2 merged. These proposed methods use different spatial and temporal characteristics extracted from raw EEG data. We demonstrate that our proposed CNN1-based method outperforms state-of-the-art machine/deep learning techniques for EEG classification by an accuracy value of 68.77% and use spatial and frequency characteristics on the BCI Competition IV-2a dataset, which includes nine subjects performing four MI tasks (left/right hand, feet, and tongue). The experimental results demonstrate the feasibility of this proposed method for the classification of MI-EEG signals and can be applied successfully to BCI systems where the amount of data is large due to daily recording.

scholarly journals Convolutional Neural Network Transfer Learning Applied to the Affective Auditory P300-Based BCI

2020 ◽  
Vol 32 (4) ◽  
pp. 731-737
Author(s):  
Akinari Onishi ◽  
◽  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Training Data ◽  
Learning Method ◽  
Eeg Signals ◽  
Recording Time ◽  
Auditory P300 ◽  
Eeg Data ◽  
Time Required

Brain-computer interface (BCI) enables us to interact with the external world via electroencephalography (EEG) signals. Recently, deep learning methods have been applied to the BCI to reduce the time required for recording training data. However, more evidence is required due to lack of comparison. To reveal more evidence, this study proposed a deep learning method named time-wise convolutional neural network (TWCNN), which was applied to a BCI dataset. In the evaluation, EEG data from a subject was classified utilizing previously recorded EEG data from other subjects. As a result, TWCNN showed the highest accuracy, which was significantly higher than the typically used classifier. The results suggest that the deep learning method may be useful to reduce the recording time of training data.

scholarly journals EEG Dipole Source Localization using Deep Neural Network

2022 ◽  
Vol 16 ◽  
pp. 132-140
Author(s):  
Zeng Hui ◽  
Li Ying ◽  
Wang Lingyue ◽  
Yin Ning ◽  
Yang Shuo
Keyword(s):  
Neural Network ◽  
Inverse Problem ◽  
Relative Error ◽  
Source Localization ◽  
Deep Neural Network ◽  
Absolute Error ◽  
Dipole Source ◽  
Head Model ◽  
Eeg Data ◽  
Eeg Inverse Problem

Electroencephalography (EEG) inverse problem is a typical inverse problem, in which the electrical activity within the brain is reconstructed based on EEG data collected from the scalp electrodes. In this paper, the four-layer concentric head model is used for simulation firstly, four deep neural network models including a multilayer perceptron (MLP) model and three convolutional neural networks (CNNs) are adopted to solve EEG inverse problem based on equal current dipole (ECD) model. In the simulations, 100,000 samples are generated randomly, of which 60% are used for network training and 20% are used for cross-validation. Eventually, the generalization performance of the model using the optimal function is measured by the errors in the rest 20% testing set. The experimental results show that the absolute error, relative error, mean positioning error and standard deviation of the four models are extremely low. The CNN with 6 convolutional layers and 3 pooling layers (CNN-3) is the best model. Its absolute error is about 0.015, its relative error is about 0.005, and its dipole position error is 0.040±0.029 cm. Furthermore, we use CNN-3 for source localization of the real EEG data in Working Memory. The results are in accord with physiological experience. The deep neural network method in our study needs fewer calculation parameters, takes less time, and has better positioning results.

scholarly journals Localizing Brain Activity from Multiple Distinct Sources via EEG

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
George Dassios ◽  
Michael Doschoris ◽  
Konstantia Satrazemi
Keyword(s):  
Inverse Problem ◽  
Surface Potential ◽  
Brain Activity ◽  
Sufficient Conditions ◽  
Measured Data ◽  
Single Dipole ◽  
Eeg Data ◽  
Necessary And Sufficient ◽  
Spherical Conductor ◽  
The Brain

An important question arousing in the framework of electroencephalography (EEG) is the possibility to recognize, by means of a recorded surface potential, the number of activated areas in the brain. In the present paper, employing a homogeneous spherical conductor serving as an approximation of the brain, we provide a criterion which determines whether the measured surface potential is evoked by a single or multiple localized neuronal excitations. We show that the uniqueness of the inverse problem for a single dipole is closely connected with attaining certain relations connecting the measured data. Further, we present the necessary and sufficient conditions which decide whether the collected data originates from a single dipole or from numerous dipoles. In the case where the EEG data arouses from multiple parallel dipoles, an isolation of the source is, in general, not possible.

scholarly journals Learning Regional Attention Convolutional Neural Network for Motion Intention Recognition Based on EEG Data

2020 ◽  
Author(s):  
Zhijie Fang ◽  
Weiqun Wang ◽  
Shixin Ren ◽  
Jiaxing Wang ◽  
Weiguo Shi ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Decoding Algorithms ◽  
Time Frequency ◽  
Intention Recognition ◽  
Temporal Features ◽  
Eeg Data ◽  
Benchmark Datasets ◽  
Critical Regions ◽  
Motion Intention

Recent deep learning-based Brain-Computer Interface (BCI) decoding algorithms mainly focus on spatial-temporal features, while failing to explicitly explore spectral information which is one of the most important cues for BCI. In this paper, we propose a novel regional attention convolutional neural network (RACNN) to take full advantage of spectral-spatial-temporal features for EEG motion intention recognition. Time-frequency based analysis is adopted to reveal spectral-temporal features in terms of neural oscillations of primary sensorimotor. The basic idea of RACNN is to identify the activated area of the primary sensorimotor adaptively. The RACNN aggregates a varied number of spectral-temporal features produced by a backbone convolutional neural network into a compact fixed-length representation. Inspired by the neuroscience findings that functional asymmetry of the cerebral hemisphere, we propose a region biased loss to encourage high attention weights for the most critical regions. Extensive evaluations on two benchmark datasets and real-world BCI dataset show that our approach significantly outperforms previous methods.

scholarly journals Posed Inverse Problem Rectification Using Novel Deep Convolutional Neural Network

2020 ◽  
Vol 2 (3) ◽  
pp. 121-127
Author(s):  
Dr. Vijayakumar T.
Keyword(s):  
Neural Network ◽  
Inverse Problem ◽  
Convolutional Neural Network ◽  
Normal Operator ◽  
Computational Cost ◽  
Iterative Algorithms ◽  
Deep Convolutional Neural Network ◽  
High Definition ◽  
Direct Inversion ◽  
Adjoint Operators

The proposed paper addresses the inverse problems using a novel deep convolutional neural network (CNN). Over the years, regularized iterative algorithms have been observed to be the standard approach to address this issue. Though these methodologies give an excellent output, they still impose challenges such as difficulty of hyper parameter selection, increasing computational cost for adjoint operators and forward operators. It has been observed that when the normal operator of the forward model is seen to be a convolution, unrolled iterative methods take up the CNN form. In view of this observation we have proposed a methodology which uses CNN after direct inversion to find the solution for convolutional inverse problem. In the first step the physical model of the system is analyzed using direct inversion. However, this leads to artifacts which are then removed using a combination of residual learning and multi-resolution decomposition in CNN. The results show that the performance of the proposed work outperforms other algorithm and requires a maximum of 1 second to reconstruct an image of high definition.

Sign in / Sign up

Export Citation Format

Share Document