Classification and Analysis of a Large MEG Dataset using Convolutional Neural Networks

Abstract

Convolutional neural networks were used to classify and analyse a large magnetoencephalography (MEG) dataset. Networks were trained to classify between active and baseline intervals recorded during cued button pressing. There were two primary objectives for this study: (1) develop networks that can effectively classify MEG data, and (2) identify the important data features that inform classification. Networks with a simple architecture were trained using sensor and source-localised data. Networks trained with sensor data were also trained using varying amounts of data. The important features within the data were identified by applying different visualisation techniques to trained networks. An ensemble of networks trained using sensor data performed best (average test accuracy 0.974 +/- 0.001). It was determined that a dataset containing on the order of hundreds of participants was required for this particular network and task. Visualisation maps highlighted features known to occur during neuromagnetic recordings of cued button pressing.