A plethora of deep-neural-networks (DNN) based methods were proposed over the past few years to address the challenging ill-posed inverse problem of MRI reconstruction from undersampled "k-space" (Fourier domain) data. However, instability against variations in the acquisition process and the anatomical distribution, indicates a poor generalization of the relevant physical models by the DNN architectures compared to their classical counterparts. The poor generalization effectively precludes DNN applicability for undersampled MRI reconstruction in the clinical setting. We improve the generalization capacity of DNN methods for undersampled MRI reconstruction by introducing a physically-primed DNN architecture and training approach. Our architecture encodes the undersampling mask in addition to the observed data in the model architecture and employs an appropriate training approach that uses data generated with various undersampling masks to encourage the model to generalize the undersampled MRI reconstruction problem. We demonstrated the added-value of our approach through extensive experimentation with the publicly available Fast-MRI dataset. Our physically-primed approach achieved an enhanced generalization capacity which resulted in significantly improved robustness against variations in the acquisition process and in the anatomical distribution, especially in pathological regions, compared to both vanilla DNN methods and DNN trained with undersampling mask augmentation. Trained models and code to replicate our experiments will become available for research purposes upon acceptance.

通过引入基于物理原理的DNN架构和训练方法来提高DNN方法在MRI重建中的泛化能力，该方法通过采用不同的欠采样蒙版产生的数据来鼓励模型推广MRI重建问题，在Fast-MRI数据集上的实验结果表明，我们的方法在解决MRI重建中的艰难问题方面比传统方法有更好的应用前景。

面向广义欠采样MRI重建的物理深度神经网络