A novel radial basis Bayesian regularization deep neural network for the Maxwell nanofluid applied on the Buongiorno model

The diagnosis of many neurologic diseases benefits from the ability to quantitatively assess iron in the brain. Paramagnetic iron modifies the magnetic susceptibility causing magnetic field inhomogeneity in MRI. The local field can be mapped using the MR signal phase, which is discarded in a typical image reconstruction. The calculation of the susceptibility from the measured magnetic field is an ill-posed inverse problem. In this work, a bayesian regularization approach that adds spatial priors from the MR magnitude image is formulated for susceptibility imaging. Priors include background regions of known zero susceptibility and edge information from the magnitude image. Simulation and phantom validation experiments demonstrated accurate susceptibility maps free of artifacts. The ability to characterize iron content in brain hemorrhage was demonstrated on patients with cavernous hemangioma. Additionally, multiple structures within the brain can be clearly visualized and characterized. The technique introduces a new quantitative contrast in MRI that is directly linked to iron in the brain. Copyright (c) 2009 Wiley-Liss, Inc.