A hybrid SVM-GLM approach for fMRI data analysis.

The hypothesis-driven fMRI data analysis methods, represented by the conventional general linear model (GLM), have a strictly defined statistical framework for assessing regionally specific activations but require prior brain response modeling that is usually hard to be accurate. On the contrary, exploratory methods, like the support vector machine (SVM), are independent of prior hemodynamic response function (HRF), but generally lack a statistical inference framework. To take the advantages of both kinds of methods, this paper presents a composite approach through combining conventional GLM with SVM. This hybrid SVM-GLM concept is to use the power of SVM to obtain a data-derived reference function and enter it into the conventional GLM for statistical inference. The data-derived reference function was extracted from the SVM classifier using a new temporal profile extraction method. In simulations with synthetic fMRI data, SVM-GLM demonstrated a better sensitivity and specificity performance for detecting the synthetic activations, as compared to the conventional GLM. With real fMRI data, SVM-GLM showed better sensitivity than regular GLM for detecting the sensorimotor activations.