Fast Gaussian Naïve Bayes for searchlight classification analysis

• Published in: NeuroImage (Orlando, Fla.) Vol. 163; pp. 471 - 479
• Main Authors: Ontivero-Ortega, Marlis, Lage-Castellanos, Agustin, Valente, Giancarlo, Goebel, Rainer, Valdes-Sosa, Mitchell
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.12.2017; Elsevier Limited
• Subjects: Bayes Theorem; Bayesian analysis; Binomial distribution; Brain - physiology; Brain mapping; Brain Mapping - methods; Classification; Computational neuroscience; Functional magnetic resonance imaging; Gaussian Naïve Bayes; Humans; Magnetic Resonance Imaging - methods; Pattern Recognition, Automated - methods; Permutation tests; Searchlight MVPA; Studies; Support Vector Machine; Systematic review; Gaussian Naïve Bayes; Permutation tests; Support vector machine; Searchlight MVPA
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2017.09.001

The searchlight technique is a variant of multivariate pattern analysis (MVPA) that examines neural activity across large sets of small regions, exhaustively covering the whole brain. This usually involves application of classifier algorithms across all searchlights, which entails large computational costs especially when testing the statistical significance of the accuracies with permutation methods. In this article, a new implementation of the Gaussian Naive Bayes classifier is presented (henceforth massive-GNB). This approach allows classification in all searchlights simultaneously, and is faster than previously published searchlight GNB implementations, as well as other more complex classifiers including support vector machines (SVM). To ensure that the gain in speed for GNB would be useful in searchlight analysis, we compared the accuracies of massive-GNB and SVM in detecting the lateral occipital complex (LOC) in an fMRI localizer experiment (26 subjects). Moreover, this region as defined in a meta-analysis of many activation studies was used as a gold standard to compare error rates for both classifiers. In individual searchlights, SVM was somewhat more accurate than massive-GNB and more selective in detecting the meta-analytic LOC. However, with multiple comparison correction at the cluster-level the two classifiers performed equivalently. Thus for cluster-level analysis, massive-GNB produces an accuracy similar to more sophisticated classifiers but with a substantial gain in speed. Massive-GNB (available as a public Matlab toolbox) could facilitate the more widespread use of searchlight analysis. •A fast version of GNB (massive-GNB) was developed for searchlight MVPA.•A great gain of speed was evinced compared to previous GNB versions and SVM.•Massive-GNB expedites permutation tests in the searchlight context.•In real fMRI data, GNB had a similar accuracy to SVM at a cluster-level analysis.•These results facilitate more widespread usage of searchlight MVPA.