mlsanityData to 7 Oct 2026

SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models

arXiv 2310.01799 ↗First posted 3 Oct 2023eess.IV cs.CVcited by 15

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

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 .

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 24 of its 44 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

24 of 44 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  2. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstruction12 Jul
  3. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction5 Mar
  4. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  5. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 19

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  6. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  7. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  8. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  9. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  10. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  11. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  12. 2021Zero-Shot Self-Supervised Learning for MRI Reconstructioncited by 53
7 more
  1. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  2. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
  3. 2023GSURE-Based Diffusion Model Training with Corrupted Datacited by 40
  4. 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
  5. 2017Deep Generative Adversarial Networks for Compressed Sensing Automates MRIcited by 15
  6. 2020ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithmscited by 13
  7. 2022GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstructioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 5; 2026: 1.

15 papers.

Sort:

By area:

  1. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  2. 2024Slice-Consistent 3D Volumetric Brain CT-to-MRI Translation with 2D Brownian Bridge Diffusion Modelcited by 16
  3. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  4. 2024When Diffusion MRI Meets Diffusion Model: A Novel Deep Generative Model for Diffusion MRI Generationcited by 6
  5. 2024MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion modelcited by 3
  6. 2024Score-based Generative Priors Guided Model-driven Network for MRI Reconstructioncited by 3
  7. 2024MCU-Net: A Multi-prior Collaborative Deep Unfolding Network with Gates-controlled Spatial Attention for Accelerated MR Image Reconstructioncited by 2
  8. 2024Sub-DM:Subspace Diffusion Model with Orthogonal Decomposition for MRI Reconstructioncited by 2
  9. 2025A Comprehensive Survey on Magnetic Resonance Image Reconstructioncited by 1
  10. 2025From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstructioncited by 1
  11. 2024MS-Glance: Bio-Insipred Non-semantic Context Vectors and their Applications in Supervising Image Reconstructioncited by 0
  12. 2024LDPM: Towards undersampled MRI reconstruction with MR-VAE and Latent Diffusion Priorcited by 0
3 more
  1. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstructioncited by 0
  2. 2025Predicting before Reconstruction: A generative prior framework for MRI accelerationcited by 0
  3. 2026Principled Design of Diffusion-based Optimizers for Inverse Problemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  2. 2024On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
  3. 2024Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction
  4. 2026Likelihood-Separable Diffusion Inference for Multi-Image MRI Super-Resolution
  5. 2024Resolution-Robust 3D MRI Reconstruction with 2D Diffusion Priors: Diverse-Resolution Training Outperforms Interpolation
  6. 2025Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm
  7. 2023Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
  8. 2026ReDiff: Reliability-Guided Diffusion for Trustworthy Ultra-Low-Field to High-Field MRI Synthesis