Group Linear non-Gaussian Component Analysis with Applications to Neuroimaging

TL;DR

This paper introduces a group LNGCA method for neuroimaging that improves feature detection in fMRI data by capturing low-variance components and shared group signals, outperforming traditional ICA in accuracy.

Contribution

The paper proposes a novel group LNGCA model with a parametric resampling test for component number estimation, enhancing neuroimaging analysis over existing ICA methods.

Findings

Higher accuracy in component estimation compared to group ICA

Identification of different temporal engagement levels in autism spectrum disorder

Effective extraction of shared and subject-specific brain networks

Abstract

Independent component analysis (ICA) is an unsupervised learning method popular in functional magnetic resonance imaging (fMRI). Group ICA has been used to search for biomarkers in neurological disorders including autism spectrum disorder and dementia. However, current methods use a principal component analysis (PCA) step that may remove low-variance features. Linear non-Gaussian component analysis (LNGCA) enables simultaneous dimension reduction and feature estimation including low-variance features in single-subject fMRI. We present a group LNGCA model to extract group components shared by more than one subject and subject-specific components. To determine the total number of components in each subject, we propose a parametric resampling test that samples spatially correlated Gaussian noise to match the spatial dependence observed in data. In simulations, our estimated group components achieve higher accuracy compared to group ICA. We apply our method to a resting-state fMRI study on autism spectrum disorder in 342 children (252 typically developing, 90 with autism), where the group signals include resting-state networks. We find examples of group components that appear to exhibit different levels of temporal engagement in autism versus typically developing children, as revealed using group LNGCA. This novel approach to matrix decomposition is a promising direction for feature detection in neuroimaging.