Abstract
AbstractObjectiveTo use a recurrent neural network (RNN) to reconstruct neural activity responsible for generating noninvasively measured electromagnetic signals.ApproachOutput weights of an RNN were fixed as the lead field matrix from volumetric source space computed using the boundary element method with co-registered structural magnetic resonance images and magnetoencephalography (MEG). Initially, the network was trained to minimize mean-squared-error loss between its outputs and MEG signals, causing activations in the penultimate layer to converge towards putative neural source activations. Subsequently, L1 regularization was applied to the final hidden layer, and the model was fine-tuned, causing it to favour more focused activations. Estimated source signals were then obtained from the outputs of the last hidden layer. We developed and validated this approach with simulations before applying it to real MEG data, comparing performance with three existing methods: beamformers, minimum-norm estimate, and dynamical statistical parametric mapping.Main resultsThe proposed method had higher output signal-to-noise ratios than the others and comparable correlation and error between estimated and simulated sources. Reconstructed MEG signals were also equal or superior to the other methods in terms of their similarity to ground-truth. When applied to MEG data recorded during an auditory roving oddball experiment, source signals estimated with the RNN were generally consistent with expectations from the literature and qualitatively smoother and more reasonable-looking than estimates from the other methods.SignificanceThis work builds on recent developments of RNNs for modelling event-related neural responses by incorporating biophysical constraints from the forward model, thus taking a significant step towards greater biological realism and introducing the possibility of exploring how input manipulations may influence localized neural activity.
Publisher
Cold Spring Harbor Laboratory