An Evolutionary Approach to Multivariate Feature Selection for FMRI Pattern Analysis

Multivariate pattern recognition has recently gained in popularity as an alternative to univariate fMRI analyis, although the exceedingly high spatial dimensionality has proven problematic. Addressing this issue, we have explored the effectiveness of evolutionary algorithms in determining a limited number of voxels that, in combination, optimally discriminate between single volumes of fMRI. Using a simple multiple linear regression classifier in conjunction with as few as five evolutionarily selected voxels, a subject mean single trial binary prediction rate of 74.3% was achieved on data generated by tactile stimulation of the arm compared to rest. On the same data, feature selection based on statistical parametric mapping resulted in 63.8% correct classification. Our evolutionary feature selection approach thus illustrates how, using appropriate multivariate feature selection, surprising amounts of information can be extracted from very few voxels in single volumes of fMRI. Moreover, the resulting voxel discrimination relevance maps (VDRMs) showed considerable overlap with traditional statistical activation maps, providing a model-free alternative to statistical voxel activation