mlsanityData to 7 Oct 2026

Adaptive Diffusion Priors for Accelerated MRI Reconstruction

arXiv 2207.05876 ↗First posted 12 Jul 2022eess.IV cs.CVcited by 117

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator, they can show poor generalization across variable operators. Unconditional models instead learn generative image priors decoupled from the operator to improve reliability against domain shifts related to the imaging operator. Recent diffusion models are particularly promising given their high sample fidelity. Nevertheless, inference with a static image prior can perform suboptimally. Here we propose the first adaptive diffusion prior for MRI reconstruction, AdaDiff, to improve performance and reliability against domain shifts. AdaDiff leverages an efficient diffusion prior trained via adversarial mapping over large reverse diffusion steps. A two-phase reconstruction is executed following training: a rapid-diffusion phase that produces an initial reconstruction with the trained prior, and an adaptation phase that further refines the result by updating the prior to minimize data-consistency loss. Demonstrations on multi-contrast brain MRI clearly indicate that AdaDiff outperforms competing conditional and unconditional methods under domain shifts, and achieves superior or on par within-domain performance.

Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 61 of its 101 references that are in the map. First posted on arXiv 12 Jul 2022.

Builds on

61 of 101 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Towards performant and reliable undersampled MR reconstruction via diffusion model sampling8 Mar
  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 · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  9. 2017Deep Image Priorcited by 1,097
  10. 2018Which Training Methods for GANs do actually Converge?cited by 672
  11. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  12. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
38 more
  1. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
  2. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  3. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  4. 2017Learned Primal-dual Reconstructioncited by 251
  5. 2017Image reconstruction by domain transform manifold learningcited by 231
  6. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  7. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
  8. 2018Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networkscited by 131
  9. 2017Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstructioncited by 105
  10. 2017Deep learning for undersampled MRI reconstructioncited by 91
  11. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  12. 2021Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformerscited by 76
  13. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  14. 2017A Deep Cascade of Convolutional Neural Networks for MR Image Reconstructioncited by 74
  15. 2019Time-Dependent Deep Image Prior for Dynamic MRIcited by 70
  16. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  17. 2018Deep Residual Learning for Accelerated MRI using Magnitude and Phase Networkscited by 53
  18. 2022ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformercited by 52
  19. 2017A Transfer-Learning Approach for Accelerated MRI using Deep Neural Networkscited by 43
  20. 2017Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problemscited by 40
  21. 2017MR image reconstruction using deep density priorscited by 37
  22. 2022Federated Learning of Generative Image Priors for MRI Reconstructioncited by 33
  23. 2021Over-and-Under Complete Convolutional RNN for MRI Reconstructioncited by 29
  24. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 28
  25. 2020Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGANcited by 28
  26. 2018DIMENSION: Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Trainingcited by 26
  27. 2018Quantitative Susceptibility Mapping using Deep Neural Network: QSMnetcited by 24
  28. 2020Unsupervised MRI Reconstruction with Generative Adversarial Networkscited by 24
  29. 2019Model Learning: Primal Dual Networks for Fast MR imagingcited by 22
  30. 2021TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imagingcited by 18
  31. 2021Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Networkcited by 16
  32. 2021Universal Undersampled MRI Reconstructioncited by 15
  33. 2019Wasserstein GANs for MR Imaging: from Paired to Unpaired Trainingcited by 14
  34. 2020Neural Network-based Reconstruction in Compressed Sensing MRI Without Fully-sampled Training Datacited by 14
  35. 2018Complex Fully Convolutional Neural Networks for MR Image Reconstructioncited by 12
  36. 2019Joint multi-contrast Variational Network reconstruction (jVN) with application to rapid 2D and 3D imagingcited by 11
  37. 2021DONet: Dual-Octave Network for Fast MR Image Reconstructioncited by 9
  38. 2021Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Imagescited by 8

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 33; 2024: 44; 2025: 25; 2026: 9.

117 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  3. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 191
  4. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  5. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  6. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 72
  7. 2023Generative AI for Medical Imaging: extending the MONAI Frameworkcited by 68
  8. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  9. 2022High-Frequency Space Diffusion Models for Accelerated MRIcited by 41
  10. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Modelscited by 37
  11. 2024Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generationcited by 33
  12. 2024Rethinking Diffusion Model for Multi-Contrast MRI Super-Resolutioncited by 29
38 more
  1. 2024Self-Consistent Recursive Diffusion Bridge for Medical Image Translationcited by 26
  2. 2024I2I-Mamba: Multi-modal medical image synthesis via selective state space modelingcited by 26
  3. 2022One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesiscited by 22
  4. 2023Diffusion Modeling with Domain-conditioned Prior Guidance for Accelerated MRI and qMRI Reconstructioncited by 20
  5. 2023Investigating Data Memorization in 3D Latent Diffusion Models for Medical Image Synthesiscited by 19
  6. 2025RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priorscited by 17
  7. 2023Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Actioncited by 15
  8. 2023MRI Reconstruction with Side Information using Diffusion Modelscited by 15
  9. 2023SMRD: SURE-based Robust MRI Reconstruction with Diffusion Modelscited by 15
  10. 2023DreaMR: Diffusion-driven Counterfactual Explanation for Functional MRIcited by 14
  11. 2023Correlated and Multi-frequency Diffusion Modeling for Highly Under-sampled MRI Reconstructioncited by 14
  12. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstructioncited by 13
  13. 2023SPIRiT-Diffusion: Self-Consistency Driven Diffusion Model for Accelerated MRIcited by 12
  14. 2023DDPET-3D: Dose-aware Diffusion Model for 3D Ultra Low-dose PET Imagingcited by 12
  15. 2025Metrics that matter: Evaluating image quality metrics for medical image generationcited by 12
  16. 2023CDiffMR: Can We Replace the Gaussian Noise with K-Space Undersampling for Fast MRI?cited by 11
  17. 2024DenoMamba: A fused state-space model for low-dose CT denoisingcited by 11
  18. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRIcited by 9
  19. 2024Unconditional Latent Diffusion Models Memorize Patient Imaging Data: Implications for Openly Sharing Synthetic Datacited by 9
  20. 2024Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstructioncited by 9
  21. 2024LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyondcited by 9
  22. 2023Fast Inference in Denoising Diffusion Models via MMD Finetuningcited by 8
  23. 2023Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Modelscited by 8
  24. 2025TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced Efficiencycited by 8
  25. 2022Content-Based Medical Image Retrieval with Opponent Class Adaptive Margin Losscited by 7
  26. 2023Annealed Score-Based Diffusion Model for MR Motion Artifact Reductioncited by 7
  27. 2023MCMC-Correction of Score-Based Diffusion Models for Model Compositioncited by 7
  28. 2024MambaRecon: MRI Reconstruction with Structured State Space Modelscited by 7
  29. 2024A Unified Model for Compressed Sensing MRI Across Undersampling Patternscited by 7
  30. 2024Physics-Driven Autoregressive State Space Models for Medical Image Reconstructioncited by 7
  31. 2023HydraViT: Adaptive Multi-Branch Transformer for Multi-Label Disease Classification from Chest X-ray Imagescited by 6
  32. 2023CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Modelcited by 6
  33. 2024Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRIcited by 6
  34. 2024TC-DiffRecon: Texture coordination MRI reconstruction method based on diffusion model and modified MF-UNet methodcited by 5
  35. 2024Dose-aware Diffusion Model for 3D PET Image Denoising: Multi-institutional Validation with Reader Study and Real Low-dose Datacited by 5
  36. 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolationscited by 5
  37. 2024Highly Accelerated MRI via Implicit Neural Representation Guided Posterior Sampling of Diffusion Modelscited by 5
  38. 2024Physics-Inspired Generative Models in Medical Imaging: A Reviewcited by 5

50 most cited of 117 All 117 (JSON)

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. 2025Deep generative priors for 3D brain analysis
  3. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
  4. 2025MDPG: Multi-domain Diffusion Prior Guidance for MRI Reconstruction
  5. 2022ADIR: Adaptive Diffusion for Image Reconstruction
  6. 2023Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise
  7. 2023CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis
  8. 2025Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images