Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension

TL;DR

This paper introduces an independent component-based encoding framework for fMRI data during story listening, improving interpretability and robustness by dissociating neural signals from noise and enabling network-level analysis.

Contribution

The study presents a novel IC-based encoding approach that enhances the analysis of brain activity by separating stimulus-driven signals from noise, accommodating individual variability.

Findings

Identified ICs with high predictivity across subjects.

ICs corresponded to known cognitive networks like auditory and language.

Noise components showed poor predictive performance, confirming model validity.

Abstract

Encoding models provide a powerful framework for linking continuous stimulus features to neural activity; however, traditional voxelwise approaches are limited by measurement noise, inter-subject variability, and redundancy arising from spatially correlated voxels encoding overlapping neural signals. Here, we propose an independent component (IC)-based encoding framework that dissociates stimulus-driven and noise-driven signals in fMRI data. We decompose continuous fMRI data from naturalistic story listening into ICs using one subset of the data, and train encoding models on independent data to predict IC time series from large language model representations of linguistic input. Across subjects, a subset of ICs exhibited consistently high predictivity. These ICs were spatially and temporally consistent across subjects and included cognitive networks known to respond during story listening (auditory and language). Auditory component time series were strongly correlated with acoustic stimulus features, highlighting the interpretability of identified component time series. Components identified as noise or motion-related artifacts by ICA-AROMA showed uniformly poor predictive performance, confirming that highly predicted components reflect genuine stimulus-related neural signals rather than confounds. Overall, IC-based encoding models enable analyses at the level of functional networks, accommodating the variability in network locations across individuals and providing interpretable results that are easy to compare across subjects.