mlsanityData to 7 Oct 2026

Robust multi-coil MRI reconstruction via self-supervised denoising

arXiv 2411.12919 ↗First posted 19 Nov 2024eess.IV cs.AI cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We study the effect of incorporating self-supervised denoising as a pre-processing step for training deep learning (DL) based reconstruction methods on data corrupted by Gaussian noise. K-space data employed for training are typically multi-coil and inherently noisy. Although DL-based reconstruction methods trained on fully sampled data can enable high reconstruction quality, obtaining large, noise-free datasets is impractical. We leverage Generalized Stein's Unbiased Risk Estimate (GSURE) for denoising. We evaluate two DL-based reconstruction methods: Diffusion Probabilistic Models (DPMs) and Model-Based Deep Learning (MoDL). We evaluate the impact of denoising on the performance of these DL-based methods in solving accelerated multi-coil magnetic resonance imaging (MRI) reconstruction. The experiments were carried out on T2-weighted brain and fat-suppressed proton-density knee scans. We observed that self-supervised denoising enhances the quality and efficiency of MRI reconstructions across various scenarios. Specifically, employing denoised images rather than noisy counterparts when training DL networks results in lower normalized root mean squared error (NRMSE), higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) across different SNR levels, including 32dB, 22dB, and 12dB for T2-weighted brain data, and 24dB, 14dB, and 4dB for fat-suppressed knee data. Overall, we showed that denoising is an essential pre-processing technique capable of improving the efficacy of DL-based MRI reconstruction methods under diverse conditions. By refining the quality of input data, denoising enables training more effective DL networks, potentially bypassing the need for noise-free reference MRI scans.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 49 of its 80 references that are in the map. First posted on arXiv 19 Nov 2024.

Builds on

49 of 80 references.

References · 49

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  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. 2022Denoising Diffusion Restoration Modelscited by 951
  8. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  9. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  10. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraintscited by 501
  11. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  12. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
37 more
  1. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  2. 2021Score-based diffusion models for accelerated MRIcited by 308
  3. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  4. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  5. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  6. 2022Diffusion models as plug-and-play priorscited by 230
  7. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 126
  8. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  9. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  10. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  11. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  12. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  13. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59
  14. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Modelscited by 50
  15. 2018Unsupervised Learning with Stein's Unbiased Risk Estimatorcited by 47
  16. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Modelscited by 46
  17. 2024Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Datacited by 44
  18. 2018Training Deep Learning Based Denoisers without Ground Truth Datacited by 43
  19. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
  20. 2017MR image reconstruction using deep density priorscited by 37
  21. 2024Denoising: A Powerful Building-Block for Imaging, Inverse Problems, and Machine Learningcited by 35
  22. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Datacited by 32
  23. 2022A theoretical framework for self-supervised MR image reconstruction using sub-sampling via variable density Noisier2Noisecited by 29
  24. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 28
  25. 2022Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstructioncited by 23
  26. 2019Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Datacited by 17
  27. 2024UNSURE: self-supervised learning with Unknown Noise level and Stein's Unbiased Risk Estimatecited by 16
  28. 2024Stochastic Deep Restoration Priors for Imaging Inverse Problemscited by 14
  29. 2020ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithmscited by 13
  30. 2021A review and experimental evaluation of deep learning methods for MRI reconstructioncited by 13
  31. 2019Unsupervised Deep Basis Pursuit: Learning inverse problems without ground-truth datacited by 10
  32. 2022Clean self-supervised MRI reconstruction from noisy, sub-sampled training data with Robust SSDUcited by 10
  33. 2022SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstructioncited by 10
  34. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRIcited by 9
  35. 2019Self-supervised learning of inverse problem solvers in medical imagingcited by 8
  36. 2021Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI datacited by 5
  37. 2024Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomycited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurementscited by 3
  2. 2025Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstructioncited by 0
  3. 2025Extendable Generalization Self-Supervised Diffusion for Low-Dose CT Reconstructioncited by 0
  4. 2026Evaluating the Safety of Deep Learning-Based Brain MRI Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
  2. 2022MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion
  3. 2025Unsupervised Accelerated MRI Reconstruction via Ground-Truth-Free Flow Matching
  4. 2024Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction
  5. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  6. 2024On Instabilities of Unsupervised Denoising Diffusion Models in Magnetic Resonance Imaging Reconstruction
  7. 2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
  8. 2025DiffDenoise: Self-Supervised Medical Image Denoising with Conditional Diffusion Models