Logan Grosenick, Brad Klingenberg, Kiefer Katovich, Brian Knutson, Jonathan E. Taylor (2013).
NeuroImage
Logan Grosenick, Brad Klingenberg, Kiefer Katovich, Brian Knutson, Jonathan E. Taylor (2013).
NeuroImage
GraphNet is a family of interpretable machine-learning models for whole-brain fMRI that produce sparse, spatially structured predictions, avoiding the instability and dense, hard-to-read solutions of off-the-shelf methods.
Multivariate machine learning methods are increasingly used to analyze neuroimaging data, often replacing more traditional "mass univariate" techniques that fit data one voxel at a time. In the functional magnetic resonance imaging (fMRI) literature, this has led to broad application of "off-the-shelf" classification and regression methods. These generic approaches allow investigators to use ready-made algorithms to accurately decode perceptual, cognitive, or behavioral states from distributed patterns of neural activity. However, when applied to correlated whole-brain fMRI data these methods suffer from coefficient instability, are sensitive to outliers, and yield dense solutions that are hard to interpret without arbitrary thresholding. Here, we develop variants of the Graph-constrained Elastic-Net (GraphNet), a fast, whole-brain regression and classification method developed for spatially and temporally correlated data that automatically yields interpretable coefficient maps (Grosenick et al., 2009b). GraphNet methods yield sparse but structured solutions by combining structured graph constraints (based on knowledge about coefficient smoothness or connectivity) with a global sparsity-inducing prior that automatically selects important variables. Because GraphNet methods can efficiently fit regression or classification models to whole-brain, multiple time-point data sets and enhance classification accuracy relative to volume-of-interest (VOI) approaches, they eliminate the need for inherently biased VOI analyses and allow whole-brain fitting without the multiple comparison problems that plague mass univariate and roaming VOI ("searchlight") methods. …
Logan Grosenick, Brad Klingenberg, Kiefer Katovich, Brian Knutson, Jonathan E. Taylor (2013). Interpretable whole-brain prediction analysis with GraphNet. NeuroImage. https://doi.org/10.1016/j.neuroimage.2012.12.062