mlsanityData to 13 Oct 2026

Self-Supervised MRI Reconstruction with Unrolled Diffusion Models

arXiv 2306.16654 ↗First posted 29 Jun 2023eess.IV cs.CVcited by 37

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Magnetic Resonance Imaging (MRI) produces excellent soft tissue contrast, albeit it is an inherently slow imaging modality. Promising deep learning methods have recently been proposed to reconstruct accelerated MRI scans. However, existing methods still suffer from various limitations regarding image fidelity, contextual sensitivity, and reliance on fully-sampled acquisitions for model training. To comprehensively address these limitations, we propose a novel self-supervised deep reconstruction model, named Self-Supervised Diffusion Reconstruction (SSDiffRecon). SSDiffRecon expresses a conditional diffusion process as an unrolled architecture that interleaves cross-attention transformers for reverse diffusion steps with data-consistency blocks for physics-driven processing. Unlike recent diffusion methods for MRI reconstruction, a self-supervision strategy is adopted to train SSDiffRecon using only undersampled k-space data. Comprehensive experiments on public brain MR datasets demonstrates the superiority of SSDiffRecon against state-of-the-art supervised, and self-supervised baselines in terms of reconstruction speed and quality. Implementation will be available at https://github.com/yilmazkorkmaz1/SSDiffRecon.

Key facts. Cited by 37 papers in the map (data through 13 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 17 of its 40 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

17 of 40 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstruction2 Sep
  2. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstruction12 Jul
  3. 2022Towards performant and reliable undersampled MR reconstruction via diffusion model sampling8 Mar
  4. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction5 Mar

Other references · 13

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,751
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,585
  4. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 386
  5. 2017Image reconstruction by domain transform manifold learningcited by 231
  6. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  7. 2021Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learningcited by 78
  8. 2017A Deep Cascade of Convolutional Neural Networks for MR Image Reconstructioncited by 74
  9. 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
  10. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  11. 2021Over-and-Under Complete Convolutional RNN for MRI Reconstructioncited by 29
  12. 2022On learning adaptive acquisition policies for undersampled multi-coil MRI reconstructioncited by 14
1 more
  1. 2022Rethinking the optimization process for self-supervised model-driven MRI reconstructioncited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 5; 2024: 15; 2025: 12; 2026: 5.

37 papers.

Sort:

By area:

  1. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  2. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  3. 2024Self-Consistent Recursive Diffusion Bridge for Medical Image Translationcited by 26
  4. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  5. 2024A study of why we need to reassess full reference image quality assessment with medical imagescited by 17
  6. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstructioncited by 13
  7. 2024DenoMamba: A fused state-space model for low-dose CT denoisingcited by 11
  8. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRIcited by 9
  9. 2023Fast Controllable Diffusion Models for Undersampled MRI Reconstructioncited by 8
  10. 2024Physics-Driven Autoregressive State Space Models for Medical Image Reconstructioncited by 7
  11. 2024Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Modelscited by 5
  12. 2023Score-based Diffusion Models With Self-supervised Learning For Accelerated 3D Multi-contrast Cardiac Magnetic Resonance Imagingcited by 4
25 more
  1. 2023Joint Supervised and Self-supervised Learning for MRI Reconstructioncited by 4
  2. 2025Generative Autoregressive Transformers for Model-Agnostic Federated MRI Reconstructioncited by 4
  3. 2024MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion modelcited by 3
  4. 2024Score-based Generative Priors Guided Model-driven Network for MRI Reconstructioncited by 3
  5. 2024Denoising Diffusion Probabilistic Models for Magnetic Resonance Fingerprintingcited by 3
  6. 2025PhaseGen: A Diffusion-Based Approach for Complex-Valued MRI Data Generationcited by 3
  7. 2025Diff-Unfolding: A Model-Based Score Learning Framework for Inverse Problemscited by 3
  8. 2024Robust Simultaneous Multislice MRI Reconstruction Using Slice-Wise Learned Generative Diffusion Priorscited by 2
  9. 2025Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Modelscited by 2
  10. 2025Physics informed guided diffusion for accelerated multi-parametric MRI reconstructioncited by 2
  11. 2024DuDoUniNeXt: Dual-domain unified hybrid model for single and multi-contrast undersampled MRI reconstructioncited by 1
  12. 2025Re-Visible Dual-Domain Self-Supervised Deep Unfolding Network for MRI Reconstructioncited by 1
  13. 2025A Comprehensive Survey on Magnetic Resonance Image Reconstructioncited by 1
  14. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  15. 2024Real-time cardiac cine MRI -- A comparison of a diffusion probabilistic model with alternative state-of-the-art image reconstruction techniques for undersampled spiral acquisitionscited by 0
  16. 2024MS-Glance: Bio-Insipred Non-semantic Context Vectors and their Applications in Supervising Image Reconstructioncited by 0
  17. 2025Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integrationcited by 0
  18. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstructioncited by 0
  19. 2025Diffusion-Assisted Frequency Attention Model for Whole-body Low-field MRI Reconstructioncited by 0
  20. 2025Predicting before Reconstruction: A generative prior framework for MRI accelerationcited by 0
  21. 2026Accelerating Stroke MRI with Diffusion Probabilistic Models through Large-Scale Pre-training and Target-Specific Fine-Tuningcited by 0
  22. 2026Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstructioncited by 0
  23. 2026CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropoutcited by 0
  24. 2026DD-INR: Dynamics-Driven Implicit Neural Representation for Accelerated Whole-Brain Functional MRI Reconstructioncited by 0
  25. 2026Evaluating the Safety of Deep Learning-Based Brain MRI Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Self-supervised Diffusion Bridge for MRI Reconstruction
  2. 2024Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction
  3. 2024Robust multi-coil MRI reconstruction via self-supervised denoising
  4. 2024TC-DiffRecon: Texture coordination MRI reconstruction method based on diffusion model and modified MF-UNet method
  5. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  6. 2023Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise
  7. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models
  8. 2026Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models