A group model for stable multi-subject ICA on fMRI datasets

TL;DR

This paper introduces a hierarchical group ICA model for multi-subject fMRI data, enhancing the reproducibility and stability of identified brain networks for better inter-group comparisons.

Contribution

It proposes CanICA, a novel estimation procedure combining probabilistic dimension reduction, canonical correlation analysis, and ICA for improved multi-subject fMRI analysis.

Findings

CanICA yields more reproducible group-level features.

The method outperforms existing multi-subject ICA techniques.

Results validated on resting-state and localizer datasets.

Abstract

Spatial Independent Component Analysis (ICA) is an increasingly used data-driven method to analyze functional Magnetic Resonance Imaging (fMRI) data. To date, it has been used to extract sets of mutually correlated brain regions without prior information on the time course of these regions. Some of these sets of regions, interpreted as functional networks, have recently been used to provide markers of brain diseases and open the road to paradigm-free population comparisons. Such group studies raise the question of modeling subject variability within ICA: how can the patterns representative of a group be modeled and estimated via ICA for reliable inter-group comparisons? In this paper, we propose a hierarchical model for patterns in multi-subject fMRI datasets, akin to mixed-effect group models used in linear-model-based analysis. We introduce an estimation procedure, CanICA (Canonical ICA), based on i) probabilistic dimension reduction of the individual data, ii) canonical correlation analysis to identify a data subspace common to the group iii) ICA-based pattern extraction. In addition, we introduce a procedure based on cross-validation to quantify the stability of ICA patterns at the level of the group. We compare our method with state-of-the-art multi-subject fMRI ICA methods and show that the features extracted using our procedure are more reproducible at the group level on two datasets of 12 healthy controls: a resting-state and a functional localizer study.