ConvDip: A convolutional neural network for better EEG Source Imaging

Abstract

EEG 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.

Advances in Electrical Source Imaging: A Review of the Current Approaches, Applications and Challenges

“…This architecture is able to model the spatio-temporal information provided by training the network to perceive the correlation between the location of the source and the EEG signals without needing a priori constrictions, normally provided manually by more conventional methods. In a similar manner, ConvDip, a convolutional neural network (CNN), has demonstrated a lower normalized mean squared error in ESI solutions compared to that of exact LORETA (eLORETA) and beamformers for a single source, utilizing a shallow CNN with one convolutional layer and two fully connected layers [11]. Compared to the LSTM approach, ConvDip was trained with single time-instances on simulated data but with multiple sources.…”

“…However, owing to recent advances which incorporate novel methodologies as well as the introduction of machine learning approaches in solving the inverse problem [10,11], the required time and the computational resources for the solution have been significantly reduced. Furthermore, sophisticated algorithms have diminished the localization error efficiently, estimating the location and activation of the different cortical regions [12].…”

Source localization using recursively applied and projected MUSIC with flexible extent estimation

“…A novel class of inverse solvers arose in the past decade that utilize the recent advances in machine learning, predominantly artificial neural networks (ANNs) to solve M/EEG inverse problems. These approaches require training an ANN to produce a source estimate based on simulated pairs of source and M/EEG activity and achieve high accuracy compared to many conventional methods (Cui et al, 2019 ; Hecker et al, 2020 , 2022 ; Pantazis and Adler, 2021 ). ANNs are prone to biases in the training data, wherefore their application is yet limited.…”

MEG Source Localization via Deep Learning

“…Cui et al (2019) [ 33 ] used long-short term memory networks (LSTM) to identify the location and time course of a single source; Ding et. al (2019) [ 34 ] used an LSTM network to refine dynamic statistical parametric mapping solutions; and Hecker et al (2020) [ 35 ] used feedforward neural networks to construct distributed cortical solutions. These studies are limited by the number of dipoles, or aim to address the ill-posed nature of distributed solutions.…”