Method and apparatus for processing medical image signal

The present invention relates to a method for analyzing fMRI data by using independent component analysis (ICA) and dual-regression analysis (DR) and estimating personal brain function activation patterns with high accuracy. A method for processing a medical image signal and a device thereof apply temporal-concatenation independent concatenation analysis (TC-GICA) and repeated dual-regression analysis considering spatial sparseness to the fMRI data obtained from a plurality of objects.