MRI super-resolution in ten sampling steps using a diffusion bridge model

• URL: http://arxiv.org/abs/2608.08819v1
• Date: Sun, 09 Aug 2026 17:09:21 GMT
• Title: MRI super-resolution in ten sampling steps using a diffusion bridge model
• Abstract summary: Diffusion-based super-resolution reconstructs high-resolution (HR) images from low-resolution (LR) inputs.<n>We developed an efficient diffusion framework that reconstructs HR MRI directly from LR data.<n>We evaluated SR-DBM on ultra-high-field 7T brain T1 MP2RAGE maps and pelvic T2-weighted prostate images.
• Score: 36.87358869523498
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Objective. MRI provides excellent soft-tissue contrast, but long acquisition times can cause patient discomfort and lead to motion artifacts, forcing a trade-off between spatial resolution and scan time. Diffusion-based super-resolution (SR) reconstructs high-resolution (HR) images from low-resolution (LR) inputs, but typically needs many sampling steps and initializes from a Gaussian prior ill-suited to image restoration. We developed an efficient diffusion framework that reconstructs HR MRI directly from LR data. Approach. We propose super-resolution diffusion bridge model (SR-DBM), a super-resolution diffusion bridge model that casts SR as a stochastic transport between the LR and HR image distributions. Through a Doob's h-transform of a mean-reverting stochastic differential equation, SR-DBM pins the process to the paired HR and LR images at its endpoints, initializing reconstruction from the measured anatomy rather than from Gaussian noise. The HR image is recovered by a deterministic reverse trajectory in which a network predicts the clean image at each of only ten sampling steps. We evaluated SR-DBM on ultra-high-field 7T brain T1 MP2RAGE maps and pelvic T2-weighted prostate images against nine comparison methods using PSNR, SSIM, GMSD, and LPIPS. Main results. SR-DBM attained the highest PSNR and SSIM and the lowest GMSD on both datasets (brain: 27.66+-1.52 dB, 0.96+-0.02, 7.96+-1.86$; prostate: 27.87+-2.29 dB, 0.80+-0.05, 8.38+- 1.44), with statistically significant gains over every comparison method (two-sided Wilcoxon signed-rank test with Holm correction, p<0.05). The strongest baseline, SR-EMamba, ranked second. Qualitatively, SR-DBM produced the smallest residual errors and best preserved fine structures and lesions.

Related papers

• Likelihood-Separable Diffusion Inference for Multi-Image MRI Super-Resolution [3.3307176205207383]
  We generalize diffusion-based inverse single-image problem solvers for multi-image super-resolution (MISR) MRI.<n>We show that the DPS likelihood correction allows an exactly-separable gradient decomposition across independently acquired measurements.<n>Our results achieve state-of-the-art super-resolution of anisotropic MRI volumes and, critically, enable reconstruction of near-isotropic anatomy from routine 2D multi-slice acquisitions.
  arXiv  Detail & Related papers  (2026-01-20T14:53:20Z)
• MRI super-resolution reconstruction using efficient diffusion probabilistic model with residual shifting [3.9576638237437183]
  This study introduces a residual error-shifting mechanism that drastically reduces sampling steps while preserving critical anatomical details.<n>We propose a novel diffusion-based SR framework called Res-SRDiff, which integrates residual error shifting into the forward diffusion process.
  arXiv  Detail & Related papers  (2025-03-03T14:15:08Z)
• Rapid Whole Brain Motion-robust Mesoscale In-vivo MR Imaging using Multi-scale Implicit Neural Representation [6.894117592271847]
  This study proposes Rotating-view super-resolution (ROVER)-MRI, an unsupervised framework based on multi-scale implicit neural representations (INR)<n>ROVER-MRI employs coordinate-based neural networks to implicitly and continuously encode image structures at multiple spatial scales.<n> validation on ex-vivo monkey brain data and multiple in-vivo human datasets demonstrates substantially improved reconstruction performance.
  arXiv  Detail & Related papers  (2025-02-12T18:48:12Z)
• Optimizing Sampling Patterns for Compressed Sensing MRI with Diffusion Generative Models [75.52575380824051]
  We present a learning method to optimize sub-sampling patterns for compressed sensing multi-coil MRI. We use a single-step reconstruction based on the posterior mean estimate given by the diffusion model and the MRI measurement process. Our method requires as few as five training images to learn effective sampling patterns.
  arXiv  Detail & Related papers  (2023-06-05T22:09:06Z)
• Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction [68.80715727288514]
  We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix. In this paper, we propose a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction.
  arXiv  Detail & Related papers  (2022-09-15T03:58:30Z)
• Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN [9.599347633285635]
  We present a medical AttentIon Denoising Super Resolution Generative Adversarial Network (AID-SRGAN) for diographic image super-resolution. To the best of our knowledge, this is the first composite degradation model proposed for radiographic images. Our proposed method achieves $31.90$ of PSNR with a scale factor of $4 times$, which is $7.05 %$ higher than that obtained by recent work.
  arXiv  Detail & Related papers  (2022-08-05T06:54:44Z)
• Towards Lightweight Super-Resolution with Dual Regression Learning [58.98801753555746]
  Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks. The SR problem is typically an ill-posed problem and existing methods would come with several limitations. We propose a dual regression learning scheme to reduce the space of possible SR mappings.
  arXiv  Detail & Related papers  (2022-07-16T12:46:10Z)
• Sinogram upsampling using Primal-Dual UNet for undersampled CT and radial MRI reconstruction [0.4199844472131921]
  The Primal-Dual network is a deep learning based method for reconstructing sparsely-sampled CT data. This paper introduces Primal-Dual UNet, which improves the Primal-Dual network in terms of accuracy and reconstruction speed.
  arXiv  Detail & Related papers  (2021-12-26T19:31:34Z)
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution [65.25508348574974]
  We go below the MRI acceleration factors reported by all published papers that reference the original fastMRI challenge. We consider powerful deep learning based image enhancement methods to compensate for the underresolved images. The quality of the reconstructed images surpasses that of the other methods, yielding an MSE of 0.00114, a PSNR of 29.6 dB, and an SSIM of 0.956 at x16 acceleration factor.
  arXiv  Detail & Related papers  (2021-03-04T10:45:01Z)
• Perception Consistency Ultrasound Image Super-resolution via Self-supervised CycleGAN [63.49373689654419]
  We propose a new perception consistency ultrasound image super-resolution (SR) method based on self-supervision and cycle generative adversarial network (CycleGAN) We first generate the HR fathers and the LR sons of the test ultrasound LR image through image enhancement. We then make full use of the cycle loss of LR-SR-LR and HR-LR-SR and the adversarial characteristics of the discriminator to promote the generator to produce better perceptually consistent SR results.
  arXiv  Detail & Related papers  (2020-12-28T08:24:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.