In the paper dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) measurements are used for estimation of brain perfusion parameters: cerebral blood flow (CBF), cerebral blood volume (CBV ) and mean transit time (MTT). The three-compartmental model is proposed. Two approaches to the model identification of MRI data are presented and compared. The difference between the two approaches consists in the method the model microparameters are identified. For both the approaches the perfusion parameters are calculated on the base of the calculated model microparameters. Then parametric images of CBF , CBV and MTT and of model microparameters are created and compared.