Diffuse Outlier Time Series Detection Technique for Functional Magnetic Resonance Imaging

We propose a new support vector machine (SVM) based method that improves the time series classification in magnetic resonance imaging (fMRI). We exploit the robust anisotropic diffusion (RAD) technique to increase the classification performance of the one class support vector machine by taking into account the hypothesis of spatial relationship between active voxels. The proposed method was called Diffuse One Class Support Vector Machine (DOCSVM). DOCSVM method treats activated voxels as outliers and applies one class support vector machine to generate an activation map and RAD to include the neighborhood hypothesis, improving the classification and reducing the iteration steps with respect to RADSPM. We give a brief review of the main methods, present receiver operating characteristic (ROC) results and conclude suggesting further research alternatives.