Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension
This work addresses the problem of noise and inter-subject variability in fMRI encoding models, offering a method to analyze functional networks rather than individual voxels, but it is an incremental improvement over existing voxelwise approaches.
The authors propose an independent component (IC)-based encoding framework for fMRI data during story comprehension, which dissociates stimulus-driven from noise-driven signals. They show that a subset of ICs (e.g., auditory and language networks) exhibit high predictivity from language model features, while noise components show poor performance, enabling interpretable network-level analysis.
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.