GLMdenoise improves multivariate pattern analysis of fMRI data

• Published in: NeuroImage (Orlando, Fla.) Vol. 183; pp. 606 - 616
• Main Authors: Charest, Ian, Kriegeskorte, Nikolaus, Kay, Kendrick N.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2018; Elsevier Limited; Academic Press
• Subjects: Accuracy; Activity patterns; Adult; BOLD fMRI; Brain research; Cerebral Cortex - diagnostic imaging; Cerebral Cortex - physiology; Classification; Correlated noise; Cross-validation; Data processing; Datasets; Decoding; Denoising; Experiments; Functional magnetic resonance imaging; Functional Neuroimaging - methods; General linear model; Humans; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Magnetic Resonance Imaging - methods; Measurement techniques; Medical imaging; Multivariate Analysis; Multivariate pattern analysis; Neurosciences; Noise; Pattern Recognition, Automated; Physiology; Principal components analysis; Psychomotor Performance - physiology; Representational similarity analysis; Visual Perception - physiology; Multivariate pattern analysis; Cross-validation; Classification; Correlated noise; Representational similarity analysis; General linear model; Decoding; BOLD fMRI; Denoising
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2018.08.064

GLMdenoise is a denoising technique for task-based fMRI. In GLMdenoise, estimates of spatially correlated noise (which may be physiological, instrumental, motion-related, or neural in origin) are derived from the data and incorporated as nuisance regressors in a general linear model (GLM) analysis. We previously showed that GLMdenoise outperforms a variety of other denoising techniques in terms of cross-validation accuracy of GLM estimates (Kay et al., 2013a). However, the practical impact of denoising for experimental studies remains unclear. Here we examine whether and to what extent GLMdenoise improves sensitivity in the context of multivariate pattern analysis of fMRI data. On a large number of participants (31 participants across 4 experiments; 3 T, gradient-echo, spatial resolution 2–3.75 mm, temporal resolution 1.3–2 s, number of conditions 32–75), we perform representational similarity analysis (Kriegeskorte et al., 2008a) as well as pattern classification (Haxby et al., 2001). We find that GLMdenoise substantially improves replicability of representational dissimilarity matrices (RDMs) across independent splits of each participant's dataset (average RDM replicability increases from r = 0.46 to r = 0.61). Additionally, we find that GLMdenoise substantially improves pairwise classification accuracy (average classification accuracy increases from 79% correct to 84% correct). We show that GLMdenoise often improves and never degrades performance for individual participants and that GLMdenoise also improves across-participant consistency. We conclude that GLMdenoise is a useful tool that can be routinely used to maximize the amount of information extracted from fMRI activity patterns. •GLMdenoise improves pattern classification of fMRI data.•GLMdenoise improves representational similarity analyses (RSA) of fMRI data.•GLMdenoise improves consistency of RSA results within and across subjects.•GLMdenoise improves brain-behavior correlation.•GLMdenoise outperforms classical approaches in denoising fMRI data for MVPA.