Stable Deep MRI Reconstruction using Generative Priors

TL;DR

This paper introduces a generative prior-based deep learning framework for MRI reconstruction that improves generalizability, interpretability, and uncertainty quantification, achieving state-of-the-art results across various sampling patterns.

Contribution

It presents a novel deep neural regularizer trained on reference images, integrated into a classical variational approach for flexible, high-quality MRI reconstruction.

Findings

Achieves high-quality reconstructions across different sampling patterns

Demonstrates stability with out-of-distribution contrast variations

Provides uncertainty quantification through a probabilistic interpretation

Abstract

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.