Scalable Group Level Probabilistic Sparse Factor Analysis
This work addresses the need for probabilistic methods in fMRI analysis for neuroscience researchers, but it is incremental as it builds on existing factor analysis techniques with added sparsity and noise modeling.
The authors tackled the lack of probabilistic formulations in neural representation extraction from fMRI data by proposing a scalable group-level probabilistic sparse factor analysis (psFA) model, which resulted in sparse components similar to group independent component analysis and reduced noise in activation-related areas.
Many data-driven approaches exist to extract neural representations of functional magnetic resonance imaging (fMRI) data, but most of them lack a proper probabilistic formulation. We propose a group level scalable probabilistic sparse factor analysis (psFA) allowing spatially sparse maps, component pruning using automatic relevance determination (ARD) and subject specific heteroscedastic spatial noise modeling. For task-based and resting state fMRI, we show that the sparsity constraint gives rise to components similar to those obtained by group independent component analysis. The noise modeling shows that noise is reduced in areas typically associated with activation by the experimental design. The psFA model identifies sparse components and the probabilistic setting provides a natural way to handle parameter uncertainties. The variational Bayesian framework easily extends to more complex noise models than the presently considered.