SMRD: SURE-Based Robust MRI Reconstruction with Diffusion Models

Our repository has moved to https://github.com/NVlabs/SMRD. Please follow the link to access our code. This repository implements two papers for diffusion model based MRI reconstruction:

1. SMRD: SURE-Based Robust MRI Reconstruction with Diffusion Models. MICCAI 2023 (https://link.springer.com/chapter/10.1007/978-3-031-43898-1_20)

2. Regularization by Denoising Diffusion Process for MRI Reconstruction. MIDL 2023 (https://openreview.net/forum?id=M1V498MXelq)

About

If you use this repository for your work, please consider citing the following work:

@inproceedings{ozturkler2023smrd,
  title         = {{SMRD}: SURE-based Robust {MRI} Reconstruction with Diffusion Models},
  author        = {Batu Ozturkler and Chao Liu and Benjamin Eckart and Morteza Mardani and Jiaming Song and Jan Kautz},
  booktitle     = {International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI)},
  pages         = {199--209},
  year          = {2023},
  organization  = {Springer}
}

@inproceedings{
ozturkler2023regularization,
title={Regularization by Denoising Diffusion Process for {MRI} Reconstruction},
author={Batu Ozturkler and Morteza Mardani and Arash Vahdat and Jan Kautz and John M. Pauly},
booktitle={Medical Imaging with Deep Learning, short paper track},
year={2023},
url={https://openreview.net/forum?id=M1V498MXelq}
}

Contact

For questions or comments, contact ozt@stanford.edu.