Unsupervised deep learning for individualized brain functional network identification

TL;DR

This paper introduces an unsupervised deep learning approach using CNNs to identify individual-specific brain functional networks from resting-state fMRI data, enabling fast and personalized brain analysis.

Contribution

It presents a novel end-to-end deep learning framework combining CNNs and brain decomposition models for personalized brain network identification.

Findings

Successfully identified individual-specific FNs consistent with known networks.

FNs were informative for predicting brain age.

Method demonstrated robustness on large rsfMRI datasets.

Abstract

A novel unsupervised deep learning method is developed to identify individual-specific large scale brain functional networks (FNs) from resting-state fMRI (rsfMRI) in an end-to-end learning fashion. Our method leverages deep Encoder-Decoder networks and conventional brain decomposition models to identify individual-specific FNs in an unsupervised learning framework and facilitate fast inference for new individuals with one forward pass of the deep network. Particularly, convolutional neural networks (CNNs) with an Encoder-Decoder architecture are adopted to identify individual-specific FNs from rsfMRI data by optimizing their data fitting and sparsity regularization terms that are commonly used in brain decomposition models. Moreover, a time-invariant representation learning module is designed to learn features invariant to temporal orders of time points of rsfMRI data. The proposed method has been validated based on a large rsfMRI dataset and experimental results have demonstrated that our method could obtain individual-specific FNs which are consistent with well-established FNs and are informative for predicting brain age, indicating that the individual-specific FNs identified truly captured the underlying variability of individualized functional neuroanatomy.