Robust Compressed Sensing MRI with Deep Generative PriorsDownload PDF

Published: 09 Nov 2021, Last Modified: 08 Sept 2024NeurIPS 2021 PosterReaders: Everyone
Keywords: Compressed sensing, generative priors, MRI reconstruction, Langevin dynamics, Inverse problems
Abstract: The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems. However, to date this framework has been empirically successful only on certain datasets (for example, human faces and MNIST digits), and it is known to perform poorly on out-of-distribution samples. In this paper, we present the first successful application of the CSGM framework on clinical MRI data. We train a generative prior on brain scans from the fastMRI dataset, and show that posterior sampling via Langevin dynamics achieves high quality reconstructions. Furthermore, our experiments and theory show that posterior sampling is robust to changes in the ground-truth distribution and measurement process. Our code and models are available at: \url{https://github.com/utcsilab/csgm-mri-langevin}.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
TL;DR: Posterior sampling of score-based models is robust for compressed sensing multi-coil MRI
Supplementary Material: pdf
Code: https://github.com/utcsilab/csgm-mri-langevin
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](https://www.catalyzex.com/paper/robust-compressed-sensing-mri-with-deep/code)
27 Replies

Loading