spacer

spacer

spacer

spacer

Archetypal Analysis for Modeling Multisubject fMRI Data

2016

Abstract—Functional magnetic resonance imaging (fMRI) is widely used to measure brain function during various cognitive states. However, it remains a challenge to obtain low-rank models of functional networks in fMRI that have interpretable latent fea- tures and generalize across groups of subjects, due to significant in- tersubject variability in the signal structure and noise. Group-level modeling is typically performed using component decompositions such as independent component analysis (ICA), which represent data as a linear combination of latent brain patterns, or using clus- tering models, where data are assumed to be generated by a set of “prototype” time series. Archetypal analysis (AA) provides a promising alternative, combining the advantages of component- model flexibility with highly interpretable latent “archetypes” (similar to cluster-model prototypes). To date, AA has not been applied to group-level fMRI; a major limitation is that it does not generalize to multi-subject datasets, which may have significant variations in blood oxygenation-level-dependent signal and het- eroscedastic noise. We develop multi-subject AA (MS-AA), which accounts for group-level data by assuming that archetypal tempo- ral profiles have a common latent generator across subjects, ensur- ing that the temporal components are derived from a consistent set of brain regions. In addition, the model accounts for noise het- eroscedasticity by modeling subject- and voxel-specific noise vari- ance. This provides a novel approach to group-level modeling and an alternative to preexisting methods that account for inter-subject variability by extracting individual maps as a postprocessing step (e.g., dual-regression ICA), or assuming spatial dependency of maps across subjects (e.g., independent vector analysis). MS-AA shows robust performance when modelling archetypes for a mo- tor task experiment. The procedure extracts a “seed map” across subjects, used to provide brain parcellations with subject-specific temporal profiles. Our approach thus decomposes multisubject fMRI data into distinct interpretable component archetypes that may help to model both consistent group-level measures of fMRI data and individual variability.