Learning Personal Representations from fMRIby Predicting Neurofeedback Performance

TL;DR

This paper introduces a deep learning approach to derive personal brain representations from fMRI data that enhance neurofeedback performance and predict psychiatric traits more effectively than traditional methods.

Contribution

A novel self-supervised recurrent neural network model learns individual-specific brain representations from fMRI data, improving neurofeedback prediction and psychiatric trait estimation.

Findings

Representation improves next-frame fMRI prediction.

Personal representations outperform clinical data in trait prediction.

Method demonstrates effectiveness in self neuromodulation tasks.

Abstract

We present a deep neural network method for learning a personal representation for individuals that are performing a self neuromodulation task, guided by functional MRI (fMRI). This neurofeedback task (watch vs. regulate) provides the subjects with a continuous feedback contingent on down regulation of their Amygdala signal and the learning algorithm focuses on this region's time-course of activity. The representation is learned by a self-supervised recurrent neural network, that predicts the Amygdala activity in the next fMRI frame given recent fMRI frames and is conditioned on the learned individual representation. It is shown that the individuals' representation improves the next-frame prediction considerably. Moreover, this personal representation, learned solely from fMRI images, yields good performance in linear prediction of psychiatric traits, which is better than performing such a prediction based on clinical data and personality tests. Our code is attached as supplementary and the data would be shared subject to ethical approvals.