QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field

Quantitative susceptibility mapping (QSM) is a powerful MRI technique that has shown great potential in quantifying tissue susceptibility in numerous neurological disorders. However, the intrinsic ill-posed dipole inversion problem greatly affects the accuracy of the susceptibility map. We proposed QSMGAN: a 3D deep convolutional neural network approach based on improved U-Net with increased phase receptive field and further refined the network using the WGAN-GP training strategy. Our method could generate accurate and realistic QSM from single orientation phase maps efficiently and performed significantly better than traditional non-learning-based dipole inversion algorithms.