A validation of a multi-spatialscale method for multivariate pattern analysis

• Published in: 2014 International Workshop on Pattern Recognition in Neuroimaging pp. 1 - 4
• Main Authors: Bulthe, Jessica, van den Hurk, Job, Daniels, Nicky, De Smedt, Bert, Op de Beeck, Hans P.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2014
• Subjects: Accuracy; Biology; Decoding; fMRI; Kernel; MVPA; Noise; Pattern analysis; ROI-based analysis; Searchlight; Support vector machines
• DOI: 10.1109/PRNI.2014.6858513

Most fMRI studies using Multi-Voxel Pattern Analysis (MVPA) restrict these analyses to merely one spatial scale. However, recently [1] used a multi-spatial scale method combining three levels of MVPA analysis on fMRI data from 16 subjects who performed a number comparison task: whole-brain MVPA, Regions Of Interest (ROI) based MVPA, and a small radius searchlight. The results of [1] clearly demonstrated the necessity of incorporating different spatial scales in MVPA analysis to draw conclusions on how the neural representations of the effects are distributed across the brain. We tested the validity of the method used in this empirical study by using three simulated fMRI datasets. Both simulated data and the real data [1] confirmed the relevance of analyzing data with MVPA on different spatial scales.