Fast MRI Reconstruction via Boosting Filter Diversity of Deep Cascading Networks

Wen-Hao Zheng, Xiao-Xin Li, Haigen Hu, Qianwei Zhou, Qihui Wang

Abstract: Deep Cascading Networks (DCNs) are very popular for fast MRI reconstruction. However, DCNs still have limited generalization ability on highly undersampled MRI data. One main reason is that the training data is not well used. A promising solution is to boost the filter diversity of DCNs to well fit the rich features in the training data. This can be achieved by reducing the repetition level of the undersampled input images via using the pixel unshuffle (PU) operator. As different input images and different subnets of DCNs require different PU-scales, we propose a novel PU-Scale Estimation (PUSE) method to automatically infer optimal PU-scales. By incorporating PUSE into DCNs, we construct a new Multi-PU-Scale Diversity based (MSDiv+) architecture for DCNs. To boost training convergence, we further propose to generate mini-batches by mixing data samples with different optimal PU-scales. Experiments on the fastMRI dataset demonstrate the effectiveness of our method.