mlsanityData to 7 Oct 2026

A Self-supervised Diffusion Bridge for MRI Reconstruction

arXiv 2501.03430 ↗First posted 6 Jan 2025eess.IV cs.CVcited by 2

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Diffusion bridges (DBs) are a class of diffusion models that enable faster sampling by interpolating between two paired image distributions. Training traditional DBs for image reconstruction requires high-quality reference images, which limits their applicability to settings where such references are unavailable. We propose SelfDB as a novel self-supervised method for training DBs directly on available noisy measurements without any high-quality reference images. SelfDB formulates the diffusion process by further sub-sampling the available measurements two additional times and training a neural network to reverse the corresponding degradation process by using the available measurements as the training targets. We validate SelfDB on compressed sensing MRI, showing its superior performance compared to the denoising diffusion models.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 12 of its 18 references that are in the map. First posted on arXiv 6 Jan 2025.

Builds on

12 of 18 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution24 Mar
  2. 2022DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction22 Nov

Other references · 10

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  4. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  5. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  6. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  7. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  8. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  9. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  10. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problemscited by 65

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025A Comprehensive Survey on Magnetic Resonance Image Reconstructioncited by 1
  2. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Self-Consistent Nested Diffusion Bridge for Accelerated MRI Reconstruction
  2. 2023Learning Fourier-Constrained Diffusion Bridges for MRI Reconstruction
  3. 2022Self-Score: Self-Supervised Learning on Score-Based Models for MRI Reconstruction
  4. 2020Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning
  5. 2023DDM2: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models
  6. 2023Self-Supervised MRI Reconstruction with Unrolled Diffusion Models
  7. 2025Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining
  8. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data