Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase Augmentation

TL;DR

This paper introduces a method to create robust generative priors from magnitude-only MRI images by augmenting with phase information, significantly improving reconstruction quality over traditional regularization methods.

Contribution

The authors propose a phase augmentation workflow to train generative priors from magnitude-only images, enhancing MRI reconstruction performance and robustness.

Findings

Priors trained on complex images outperform magnitude-only trained priors.

Larger training datasets lead to more robust priors.

Generative priors outperform L1-wavelet regularization in high undersampling scenarios.

Abstract

Purpose: In this work, we present a workflow to construct generic and robust generative image priors from magnitude-only images. The priors can then be used for regularization in reconstruction to improve image quality. Methods: The workflow begins with the preparation of training datasets from magnitude-only MR images. This dataset is then augmented with phase information and used to train generative priors of complex images. Finally, trained priors are evaluated using both linear and nonlinear reconstruction for compressed sensing parallel imaging with various undersampling schemes. Results: The results of our experiments demonstrate that priors trained on complex images outperform priors trained only on magnitude images. Additionally, a prior trained on a larger dataset exhibits higher robustness. Finally, we show that the generative priors are superior to L1 -wavelet regularization for compressed sensing parallel imaging with high undersampling. Conclusion: These findings stress the importance of incorporating phase information and leveraging large datasets to raise the performance and reliability of the generative priors for MRI reconstruction. Phase augmentation makes it possible to use existing image databases for training.