Zhongsen Li1, Hanyu Wei1, Chuyu Liu1, Yichen Zheng1, Shuo Chen1, and Rui Li1
1Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China
1Center for Biomedical Imaging Research, Department of Biomedical Engineering, Tsinghua University, Beijing, China
We integrated classical “partial separable” model with "variational network”. The proposed PS-VN architecture is able to reconstruct over 4 thousand image frames in approximately 10 seconds with comparable accuracy with baseline method.
Figure 1. A schematic illustration of the proposed PS-VN reconstruction pipeline. (a). The part of solving spatial basis images U in classical PS model is substituted by a variational network. (b). An unrolled layer of PS-VN consists of a data fidelity block and a regularization block. The parameters are tuned by backpropagation during network training. (c). PS-VN recovers the corrupted spatial basis images U. AHb is used to be the initial value U(0) as the input of VN. The reconstructed images can be obtained by multiplying spatial basis U with temporal basis V.
Table 1. Summary statistics of different reconstruction methods. The metrics are averaged over 4200 time frames on the test set. Generally, PS reconstruction show the best nRMSE, PSNR and SSIM; however, it takes around 10 min to reconstruct a single slice. The addition of TV constraints into PS model reduced the reconstruction time to less than 4 min, while at the cost of decrease in PSNR and SSIM. PS-VN produce higher PSNR and SSIM than PS+TV method, and consumes only around 10 seconds.