RESTING STATE 7T FMRI INDEPENDENT COMPONENT ANALYSIS WITH NONLINEAR DIMENSIONALITY REDUCTION

Independent component analysis can be applied to fMRI to investigate connectivity maps over the whole brain. Usually, ICA is performed after dimensionality reduction using singular value decomposition. Ultra-high field 7T magnetic resonance imaging (MRI) offers potentially unprecedented spatial resolution of functional activity within the human brain through increased signal and contrast to noise ratios over traditional 1.5T and 3T MRI scanners. However, the effects physiological and imaging artifacts are also greatly increased. The outliers and distortions in 7T fMRI may influence the performance of principal component analysis which only retains the linear properties. Herein, we explored some nonlinear dimensionality reduction methods as a preprocessing step of ICA. The resulting independent components are different for each dimensionality reduction method but how to define a better one needs further validation. Index Terms — 7T fMRI, Resting State fMRI