Identifying functional networks via sparse coding of whole brain FMRI signals

There have been several recent studies that used sparse representation for fMRI signal analysis and activation detection based on the assumption that each voxel's fMRI signal is linearly composed of sparse components. However, it has been rarely explored whether/how sparse representation of fMRI signals can be used to infer functional networks. To fill this gap, this paper presents a novel, alternative methodology of identifying multiple functional networks via sparse representation of whole-brain task-based fMRI signals. Our basic idea is that all fMRI signals within the whole brain of one subject are aggregated into a big data matrix, which is then factorized into an over-complete dictionary basis matrix and a reference weight matrix via an effective online dictionary learning algorithm. Our experimental results have shown that this novel methodology can uncover multiple functional networks that can be characterized and interpreted in spatial, temporal and frequency domains based on current brain science knowledge. Importantly, these well-characterized functional network components are quite reproducible in different brains. In general, our methods offer a novel, effective and unified solution to multiple fMRI data analysis tasks including activation detection, de-activation detection, and functional network identification. We envision that our novel methods will lay down a solid foundation of deeper understanding of the brain's functions in the future.