A Convolutional Autoencoder for Multi-Subject fMRI Data Aggregation

TL;DR

This paper introduces a convolutional autoencoder approach for aggregating multi-subject fMRI data, effectively preserving spatial locality and outperforming traditional methods in brain imaging analysis.

Contribution

It proposes a novel multi-view convolutional autoencoder that combines factor models with searchlight analysis for improved multi-subject fMRI data aggregation.

Findings

The autoencoder preserves spatial locality better than existing methods.

It achieves comparable or superior performance to standard searchlight and shared response models.

The system design addresses computational challenges in training the autoencoder.

Abstract

Finding the most effective way to aggregate multi-subject fMRI data is a long-standing and challenging problem. It is of increasing interest in contemporary fMRI studies of human cognition due to the scarcity of data per subject and the variability of brain anatomy and functional response across subjects. Recent work on latent factor models shows promising results in this task but this approach does not preserve spatial locality in the brain. We examine two ways to combine the ideas of a factor model and a searchlight based analysis to aggregate multi-subject fMRI data while preserving spatial locality. We first do this directly by combining a recent factor method known as a shared response model with searchlight analysis. Then we design a multi-view convolutional autoencoder for the same task. Both approaches preserve spatial locality and have competitive or better performance compared with standard searchlight analysis and the shared response model applied across the whole brain. We also report a system design to handle the computational challenge of training the convolutional autoencoder.