Abstract #4655

Dual-domain Generative Adversarial Model for Accelerated MRI Reconstruction

Guanhua Wang^1,2, Enhao Gong^2,3, Suchandrima Banerjee⁴, Karen Ying⁵, Greg Zaharchuk⁶, and John Pauly²

¹Biomedical Engineering, Tsinghua University, Beijing, China, ²Electrical Engineering, Stanford University, Stanford, CA, United States, ³Subtle Medical, Menlo Park, CA, United States, ⁴Global Applied Science Laboratory, GE Healthcare, Menlo Park, CA, United States, ⁵Engineering Physics, Tsinghua University, Beijing, China, ⁶Radiology, Stanford University, Stanford, CA, United States

Previous CS frameworks based on Deep Learning like GANCS have demonstrated improved quality and efficiency. To further improve the restoration of the high-frequency details and the suppression of aliasing artifacts, a data-driven regularization is explicitly added on the k-space, in the form of an adversarial loss (GAN). In this work, the cross-domain generative adversarial model is trained and evaluated on diverse datasets and show decent generalization ability. For both quantitative comparison and visual inspection, the proposed method achieves better reconstruction than previous networks.

This abstract and the presentation materials are available to members only; a login is required.

Join Here