Stable Deep MRI Reconstruction using Generative Priors
This work addresses the problem of reliable and flexible MRI reconstruction for clinical applications, though it is incremental as it builds on existing variational and generative approaches.
The paper tackles the challenges of generalizability and interpretability in MRI reconstruction by proposing a generative deep neural network regularizer trained on reference images, which yields high-quality reconstructions independent of sub-sampling patterns and allows for uncertainty quantification, achieving competitive performance comparable to state-of-the-art methods.
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 a generative 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 when confronted with out-of-distribution data in the form of contrast variation. 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.