A generic framework for embedding human brain function with temporally correlated autoencoder

Learning an effective and compact representation of human brain function from high-dimensional fMRI data is crucial for studying the brain's functional organization. Traditional representation methods such as independent component analysis (ICA) and sparse dictionary learning (SDL) mainly rely on matrix decomposition which represents the brain function as spatial brain networks and the corresponding temporal patterns. The correspondence of those brain networks across individuals are built by viewing them as one-hot vectors and then performing the matching. However, those one-hot vectors do not encode the regularity and/or variability of different brains very well, and thus are limited in effectively representing the functional brain activities across individuals and among different time points. To address this problem, in this paper, we formulate the human brain functional representation as an embedding problem, and propose a novel embedding framework based on the Transformer model to encode the brain function in a compact, stereotyped and comparable latent space where the brain activities are represented as dense embedding vectors. We evaluate the proposed embedding framework on the publicly available Human Connectome Project (HCP) task fMRI dataset. The experiments on brain state prediction task indicate the effectiveness and generalizability of the learned embedding. We also explore the interpretability of the learned embedding from both spatial and temporal perspective. In general, our approach provides novel insights on representing the regularity and variability of human brain function in a general, comparable, and stereotyped latent space.

Automated summary

In this study, a novel embedding framework based on the Transformer model is proposed to represent human brain function from high-dimensional fMRI data. The framework encodes brain activities as dense embedding vectors in a compact, stereotyped, and comparable latent space. The results show the effectiveness and generalizability of the learned embedding for brain state prediction tasks and provide new insights into representing the regularity and variability of human brain function.