mlsanityData to 14 Oct 2026

Patch-Based Diffusion for Data-Efficient, Radiologist-Preferred MRI Reconstruction

arXiv 2509.21531 ↗First posted 25 Sep 2025eess.IV cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Magnetic resonance imaging (MRI) requires long acquisition times, raising costs, reducing accessibility, and making scans more susceptible to motion artifacts. Diffusion probabilistic models that learn data-driven priors can potentially assist in reducing acquisition time. However, they typically require large training datasets that can be prohibitively expensive to collect. Patch-based diffusion models have shown promise in learning effective data-driven priors over small real-valued datasets, but have not yet demonstrated clinical value in MRI. We extend the Patch-based Diffusion Inverse Solver (PaDIS) to complex-valued, multi-coil MRI reconstruction, and compare it against a state-of-the-art whole-image diffusion baseline (FastMRI-EDM) for 7x undersampled MRI reconstruction on the FastMRI brain dataset. We show that PaDIS-MRI models trained on small datasets of as few as 25 k-space images outperform FastMRI-EDM on image quality metrics (PSNR, SSIM, NRMSE), pixel-level uncertainty, cross-contrast generalization, and robustness to severe k-space undersampling. In a blinded study with three radiologists, PaDIS-MRI reconstructions were chosen as diagnostically superior in 91.7% of cases, compared to baselines (i) FastMRI-EDM and (ii) classical convex reconstruction with wavelet sparsity. These findings highlight the potential of patch-based diffusion priors for high-fidelity MRI reconstruction in data-scarce clinical settings where diagnostic confidence matters.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 16 of its 24 references that are in the map. First posted on arXiv 25 Sep 2025.

Builds on

16 of 24 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images25 Jan
  2. 2023A Survey of Emerging Applications of Diffusion Probabilistic Models in MRI19 Nov
  3. 2023Patched Diffusion Models for Unsupervised Anomaly Detection in Brain MRI7 Mar
  4. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 12

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  2. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  4. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  5. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  6. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 286
  7. 2023Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Modelscited by 133
  8. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
  9. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Datacited by 32
  10. 2024Learning Image Priors through Patch-based Diffusion Models for Solving Inverse Problemscited by 20
  11. 2024Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problemscited by 8
  12. 2024Robust multi-coil MRI reconstruction via self-supervised denoisingcited by 4

Built on by

Not cited yet.

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. 2023Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models
  3. 2024LDPM: Towards undersampled MRI reconstruction with MR-VAE and Latent Diffusion Prior
  4. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction
  5. 2024Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction
  6. 2025Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
  7. 2024MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion model
  8. 2022High-Frequency Space Diffusion Models for Accelerated MRI