Compressed Online Dictionary Learning for Fast fMRI Decomposition

TL;DR

This paper introduces a fast, scalable method for resting-state fMRI data decomposition by reducing temporal dimensions prior to dictionary learning, maintaining reliability while improving computational efficiency.

Contribution

It proposes a novel time-reduction approach for dictionary learning in fMRI analysis, enhancing scalability without sacrificing result quality.

Findings

Time-reduction maintains decomposition reliability.

Significant improvement in computational scalability.

Method effective on large datasets.

Abstract

We present a method for fast resting-state fMRI spatial decomposi-tions of very large datasets, based on the reduction of the temporal dimension before applying dictionary learning on concatenated individual records from groups of subjects. Introducing a measure of correspondence between spatial decompositions of rest fMRI, we demonstrates that time-reduced dictionary learning produces result as reliable as non-reduced decompositions. We also show that this reduction significantly improves computational scalability.