SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models

TL;DR

SMRD introduces a SURE-based method for robust MRI reconstruction with diffusion models, enabling automatic hyperparameter tuning during testing to improve image quality and robustness across various conditions.

Contribution

It is the first to incorporate SURE into diffusion model sampling for automatic hyperparameter tuning in MRI reconstruction.

Findings

Outperforms baselines across noise levels, acceleration factors, and anatomies.

Achieves up to 6 dB PSNR improvement under measurement noise.

Demonstrates enhanced robustness during testing without validation tuning.

Abstract

Diffusion models have recently gained popularity for accelerated MRI reconstruction due to their high sample quality. They can effectively serve as rich data priors while incorporating the forward model flexibly at inference time, and they have been shown to be more robust than unrolled methods under distribution shifts. However, diffusion models require careful tuning of inference hyperparameters on a validation set and are still sensitive to distribution shifts during testing. To address these challenges, we introduce SURE-based MRI Reconstruction with Diffusion models (SMRD), a method that performs test-time hyperparameter tuning to enhance robustness during testing. SMRD uses Stein's Unbiased Risk Estimator (SURE) to estimate the mean squared error of the reconstruction during testing. SURE is then used to automatically tune the inference hyperparameters and to set an early stopping criterion without the need for validation tuning. To the best of our knowledge, SMRD is the first to incorporate SURE into the sampling stage of diffusion models for automatic hyperparameter selection. SMRD outperforms diffusion model baselines on various measurement noise levels, acceleration factors, and anatomies, achieving a PSNR improvement of up to 6 dB under measurement noise. The code is publicly available at https://github.com/NVlabs/SMRD .