Data-driven approaches recently achieved remarkable success in magnetic resonance imaging (MRI) reconstruction, but integration into clinical routine remains challenging due to a lack of generalizability and interpretability. In this paper, we address these challenges in a unified framework based on generative image priors. We propose a novel deep neural network based regularizer which is trained in an unsupervised setting on reference magnitude images only. After training, the regularizer encodes higher-level domain statistics which we demonstrate by synthesizing images without data. Embedding the trained model in a classical variational approach yields high-quality reconstructions irrespective of the sub-sampling pattern. In addition, the model shows stable behavior even if the test data deviate significantly from the training data. Furthermore, a probabilistic interpretation provides a distribution of reconstructions and hence allows uncertainty quantification. To reconstruct parallel MRI, we propose a fast algorithm to jointly estimate the image and the sensitivity maps. The results demonstrate competitive performance, on par with state-of-the-art end-to-end deep learning methods, while preserving the flexibility with respect to sub-sampling patterns and allowing for uncertainty quantification.

翻译：数据驱动方法近年来在磁共振成像（MRI）重建领域取得了显著成功，但由于缺乏泛化性和可解释性，其融入临床常规仍面临挑战。本文提出一个基于生成图像先验的统一框架来应对这些挑战。我们设计了一种新型深度神经网络正则化器，该正则化器在无监督设置下仅基于参考幅度图像进行训练。训练完成后，该正则化器能够编码高层次领域统计信息——这一点通过无数据条件下的图像合成实验得以验证。将训练好的模型嵌入经典变分方法中，无论采用何种欠采样模式，均可获得高质量重建结果。此外，即使测试数据与训练数据存在显著偏差，该模型仍能保持稳定表现。基于概率解释框架，该方法可提供重建结果的分布信息，从而支持不确定性量化。为进行并行MRI重建，我们提出了一种联合估计图像与灵敏度图的快速算法。实验结果表明，该方法在保持欠采样模式灵活性的同时，能够实现与最先进端到端深度学习方法相媲美的竞争性性能，并支持不确定性量化。