mlsanityData to 14 Oct 2026

Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise

arXiv 2311.10162 ↗First posted 16 Nov 2023eess.IV cs.CV cs.LGcited by 4

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Deep learning-based MRI reconstruction models have achieved superior performance these days. Most recently, diffusion models have shown remarkable performance in image generation, in-painting, super-resolution, image editing and more. As a generalized diffusion model, cold diffusion further broadens the scope and considers models built around arbitrary image transformations such as blurring, down-sampling, etc. In this paper, we propose a k-space cold diffusion model that performs image degradation and restoration in k-space without the need for Gaussian noise. We provide comparisons with multiple deep learning-based MRI reconstruction models and perform tests on a well-known large open-source MRI dataset. Our results show that this novel way of performing degradation can generate high-quality reconstruction images for accelerated MRI.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 28 of its 33 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

28 of 33 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Survey14 Nov
  2. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction5 Mar
  3. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Models15 Nov
  4. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  9. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  10. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  11. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  12. 2021Variational Diffusion Modelscited by 1,153
12 more
  1. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  2. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 342
  3. 2022Cold Diffusion: Inverting Arbitrary Image Transforms Without Noisecited by 276
  4. 2021Deblurring via Stochastic Refinementcited by 249
  5. 2023Efficient Diffusion Training via Min-SNR Weighting Strategycited by 246
  6. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 202
  7. 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
  8. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  9. 2022Few-Shot Diffusion Modelscited by 38
  10. 2019Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstructioncited by 12
  11. 2018A Hybrid Frequency-domain/Image-domain Deep Network for Magnetic Resonance Image Reconstructioncited by 11
  12. 2020Machine Learning in Magnetic Resonance Imaging: Image Reconstructioncited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024Accelerating MRI with Longitudinally-informed Latent Posterior Samplingcited by 1
  2. 2025Few-Shot Deployment of Pretrained MRI Transformers in Brain Imaging Taskscited by 1
  3. 2026High-dimensional Embedding Prior for Noisy K-space Domain MRIReconstructioncited by 0
  4. 2026Dense Temporal Contrast Synthesis via Conditioned Latent Transportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
  2. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?
  3. 2025Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Models
  4. 2023Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstruction
  5. 2024Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
  6. 2023Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification
  7. 2022High-Frequency Space Diffusion Models for Accelerated MRI
  8. 2025Unsupervised Accelerated MRI Reconstruction via Ground-Truth-Free Flow Matching