A hierarchy of cognitive brain networks revealed by multivariate performance metrics

To evaluate discriminant models in fMRI data we introduce the pseudo-Receiver Operating Characteristic plot defined by subsampled, spit-half measures of prediction (P) versus spatial pattern reproducibility (R). We illustrate (P, R) plots using denoised fMRI data with 10%-100% of the components from a 1^st-level principal component analysis (PCA). An LD model is then regularized in split-half subsamples with 2^nd-level PCAs that retain Q PCs from the largest to smaller variance. We show that the resulting Z-scored, LD spatial maps with monotonically increasing P and Q reflect regionally-dependent hierarchies of underlying brain-networks adapted to meet particular task demands.