Generalizing Brain Decoding Across Subjects with Deep Learning

05/27/2022
by   Richard Csaky, et al.
1

Decoding experimental variables from brain imaging data is gaining popularity, with applications in brain-computer interfaces and the study of neural representations. Decoding is typically subject-specific and does not generalise well over subjects. Here, we investigate ways to achieve cross-subject decoding. We used magnetoencephalography (MEG) data where 15 subjects viewed 118 different images, with 30 examples per image. Training on the entire 1s window following the presentation of each image, we experimented with an adaptation of the WaveNet architecture for classification. We also investigated the use of subject embedding to aid learning of subject variability in the group model. We show that deep learning and subject embedding are crucial to closing the performance gap between subject and group-level models. Importantly group models outperform subject models when tested on an unseen subject with little available data. The potential of such group modelling is even higher with bigger datasets. Furthermore, we demonstrate the use of permutation feature importance to gain insight into the spatio-temporal and spectral information encoded in the models, enabling better physiological interpretation. All experimental code is available at https://github.com/ricsinaruto/MEG-group-decode.

READ FULL TEXT

page 13

page 14

research
04/16/2014

MEG Decoding Across Subjects

Brain decoding is a data analysis paradigm for neuroimaging experiments ...
research
07/02/2020

Deep brain state classification of MEG data

Neuroimaging techniques have shown to be useful when studying the brain'...
research
06/19/2023

A Lightweight Causal Model for Interpretable Subject-level Prediction

Recent years have seen a growing interest in methods for predicting a va...
research
02/07/2022

Inter-subject Contrastive Learning for Subject Adaptive EEG-based Visual Recognition

This paper tackles the problem of subject adaptive EEG-based visual reco...
research
06/08/2021

Subject-Independent Brain-Computer Interface for Decoding High-Level Visual Imagery Tasks

Brain-computer interface (BCI) is used for communication between humans ...
research
06/06/2018

Data-driven Probabilistic Atlases Capture Whole-brain Individual Variation

Probabilistic atlases provide essential spatial contextual information f...
research
11/08/2019

Cross-subject Decoding of Eye Movement Goals from Local Field Potentials

Objective. We consider the cross-subject decoding problem from local fie...

Please sign up or login with your details

Forgot password? Click here to reset