mlsanityData to 7 Oct 2026

Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models

arXiv 2605.01185 ↗First posted 2 May 2026cs.CVcited by 0

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Accelerated magnetic resonance imaging (MRI) enabled by the training of deep learning (DL)-based image recon. models requires large and diverse raw k-space datasets. In most clinical MRI applications, due to storage and patient privacy concerns, raw k-space data is discarded and magnitude-only images are the only component saved. Consequently, a large portion of the DL-based MRI recon. literature has either relied on small training datasets or has used one of the few available open-source k-space datasets. At the same time, the growing number of anonymized magnitude-only image registries/databases motivates the development of techniques that can use them as training datasets for generalizable DL-based recon. models. Here we propose to address this challenge by employing a generative approach based on conditional score-based diffusion models (SBDMs): given a magnitude-only MR image, it synthesizes a phase map (in the image domain) that realistically corresponds to the magnitude-only image. We evaluate its generative capabilities in a downstream DL-based recon. task whereby a large k-space dataset is generated by combining the SBDM-synthesized phase-maps and the corresponding magnitude-only images, and this k-space dataset is then used to train a DL model for accelerated MRI recon. We compare the performance of the resulting DL model versus those trained according to (a) a naive approach that uses smooth phase, (b) a k-space training dataset generated using synthesized phase maps derived from a generative adversarial network, and (c) the ground truth k-space data. Our results suggest that the DL model trained from SBDM-synthesized k-space data outperforms the other approaches in terms of quantitative metrics as well as qualitatively observed recon. fidelity, i.e., whether the reconstructed images include erroneous or hallucinated features that could adversely impact diagnostic accuracy.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 23 of its 33 references that are in the map. First posted on arXiv 2 May 2026.

Builds on

23 of 33 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models5 Jun
  2. 2023CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis24 Mar
  3. 2022Diffusion Probabilistic Models beat GANs on Medical Images14 Dec
  4. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models19 Nov
  5. 2022Brain Imaging Generation with Latent Diffusion Models15 Sep
  6. 2021Score-based diffusion models for accelerated MRI8 Oct

Other references · 17

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  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. 2022Generative Adversarial Networkscited by 5,603
  8. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  9. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  11. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  12. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
5 more
  1. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  2. 2019Seeing What a GAN Cannot Generatecited by 148
  3. 2022Studying Bias in GANs through the Lens of Racecited by 31
  4. 2023One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstructioncited by 14
  5. 2018Simulating single-coil MRI from the responses of multiple coilscited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025PhaseGen: A Diffusion-Based Approach for Complex-Valued MRI Data Generation
  2. 2023Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise
  3. 2025Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
  4. 2026Structural MRI Synthesis for Alzheimer's Disease via Conditional Diffusion on Anatomical Masks
  5. 2023Conditional Diffusion Models for Semantic 3D Brain MRI Synthesis
  6. 2022Accelerated Motion Correction with Deep Generative Diffusion Models
  7. 2024Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI
  8. 2025Dual-domain Multi-path Self-supervised Diffusion Model for Accelerated MRI Reconstruction