Fast MRI Reconstruction via Boosting Filter Diversity of Deep Cascading Networks.
IEEE International Conference on Bioinformatics and Biomedicine(2023)
摘要
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.
更多查看译文
关键词
MRI Reconstruction,pixel unshuffle,filter diversity,deep cascading networks
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要