QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with increased receptive field
Yicheng Chen,
Angela Jakary,
Sivakami Avadiappan,
Christopher P. Hess,
Janine M. Lupo
Affiliations
Yicheng Chen
From the UCSF/UC Berkeley Graduate Program in Bioengineering, University of California, San Francisco and Berkeley, CA, USA; From the Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
Angela Jakary
From the Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
Sivakami Avadiappan
From the Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
Christopher P. Hess
From the Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA
Janine M. Lupo
From the UCSF/UC Berkeley Graduate Program in Bioengineering, University of California, San Francisco and Berkeley, CA, USA; From the Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA; Corresponding author. Byers Hall UCSF, Box 2532, 1700 4th Street, Suite 303D, San Francisco, CA, 94158-2330, USA.
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.
