Dynamic susceptibility contrast magnetic resonance imaging (DSC-MRI) derived relative cerebral blood volume (rCBV) is a valuable diagnosis biomarker. However, the injection of gadolinium-based contrast agent (GBCA) in DSC-MRI acquisition is prone to cause adverse effects. In this study, a rCBV generation method was proposed based on deep neural network and intravoxel incoherent motion magnetic resonance imaging (IVIM-MRI) data. Consistency analysis shows that the rCBV maps generated from our proposed method are of high consistency with the realistic ones, implying that the proposed method has the potential to obtain DSC-MRI derived rCBV maps without GBCA injection.
This abstract and the presentation materials are available to members only; a login is required.