Fast shared response model for fMRI data

TL;DR

The paper introduces FastSRM, an efficient algorithm for large-scale fMRI data analysis that significantly reduces computational resources while maintaining accuracy, enabling new insights into brain activity related to age during naturalistic stimuli.

Contribution

FastSRM is a novel, faster, and more memory-efficient algorithm for shared response modeling in fMRI data, suitable for large datasets.

Findings

FastSRM matches original SRM performance.

FastSRM is about 5x faster.

FastSRM uses 20-40x less memory.

Abstract

The shared response model provides a simple but effective framework to analyse fMRI data of subjects exposed to naturalistic stimuli. However when the number of subjects or runs is large, fitting the model requires a large amount of memory and computational power, which limits its use in practice. In this work, we introduce the FastSRM algorithm that relies on an intermediate atlas-based representation. It provides considerable speed-up in time and memory usage, hence it allows easy and fast large-scale analysis of naturalistic-stimulus fMRI data. Using four different datasets, we show that our method matches the performance of the original SRM algorithm while being about 5x faster and 20x to 40x more memory efficient. Based on this contribution, we use FastSRM to predict age from movie watching data on the CamCAN sample. Besides delivering accurate predictions (mean absolute error of 7.5 years), FastSRM extracts topographic patterns that are predictive of age, demonstrating that brain activity during free perception reflects age.