A Convolutional Autoencoder for Multi-Subject fMRI Data Aggregation [article]

Po-Hsuan Chen, Xia Zhu, Hejia Zhang, Javier S. Turek, Janice Chen, Theodore L. Willke, Uri Hasson, Peter J. Ramadge
2016 arXiv   pre-print
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
more » ... 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.
arXiv:1608.04846v1 fatcat:2227k6htenavtf7wlfhhfhu6g4