0225

View Abstract / View Presentation

Deep Low-rank plus Sparse Network for Dynamic MR Imaging

Wenqi Huang^1,2, Ziwen Ke^1,2, Zhuo-Xu Cui¹, Jing Cheng^2,3, Zhilang Qiu^2,3, Sen Jia³, Yanjie Zhu³, and Dong Liang^1,3
¹Research Center for Medical AI, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, ²Shenzhen College of Advanced Technology, University of Chinese Academy of Sciences, Shenzhen, China, ³Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

We propose a model-based low-rank plus sparse network (L+S-Net) for dynamic MR reconstruction. A learned singular value thresholding was introduced to explore the deep low rank prior. Experiment results show that it can improve the reconstruction both qualitatively and quantitatively.

Fig. 1. The proposed sparse plus low-rank network (L+S-Net) for dynamic MRI. The L+S-Net is defined by the iterative procedures of Eq.(5). The three layers correspond to the three modules in L+S-Net, which are named as low-rank prior layer, sparse prior layer and data consistency layer respectively. The convolution block in sparse prior layer is shown at the left bottom. The correction term in data consistency layer is shown at the right bottom.

Fig. 3. The reconstruction results of the different methods (L+S, MoDL and L+S-Net) at 12-fold acceleration using multi-coil data. The first row shows, from left to right, the ground truth, the reconstruction result of these methods. The second row shows the enlarged view of their respective heart regions framed by a yellow box. The third row shows the error map (display ranges [0, 0.07]). The y-t image (extraction of the 92th slice along the y and temporal dimensions) and the error of y-t image are also given for each signal to show the reconstruction performance in the temporal dimension.