QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field
This work addresses accuracy issues in QSM for neurological disorder diagnosis, representing an incremental improvement over existing deep learning methods.
The authors tackled the ill-posed dipole inversion problem in quantitative susceptibility mapping (QSM) for MRI by proposing QSMGAN, a 3D generative adversarial network with increased receptive field, which generates accurate QSM maps from single orientation phase maps and performs significantly better than traditional non-learning-based algorithms, as verified on unseen brain tumor patients with radiation-induced cerebral microbleeds.
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 propose QSMGAN: a 3D deep convolutional neural network approach based on a 3D U-Net architecture with increased receptive field of the input phase compared to the output and further refined the network using the WGAN with gradient penalty training strategy. Our method generates accurate QSM maps from single orientation phase maps efficiently and performs significantly better than traditional non-learning-based dipole inversion algorithms. The generalization capability was verified by applying the algorithm to an unseen pathology--brain tumor patients with radiation-induced cerebral microbleeds.