mlsanityData to 14 Oct 2026

FgC2F-UDiff: Frequency-guided and Coarse-to-fine Unified Diffusion Model for Multi-modality Missing MRI Synthesis

arXiv 2501.03526 ↗First posted 7 Jan 2025eess.IV cs.CV cs.LGcited by 3

On the map: Diffusion models → Medical imaging and segmentation

Abstract (arXiv)

Multi-modality magnetic resonance imaging (MRI) is essential for the diagnosis and treatment of brain tumors. However, missing modalities are commonly observed due to limitations in scan time, scan corruption, artifacts, motion, and contrast agent intolerance. Synthesis of missing MRI has been a means to address the limitations of modality insufficiency in clinical practice and research. However, there are still some challenges, such as poor generalization, inaccurate non-linear mapping, and slow processing speeds. To address the aforementioned issues, we propose a novel unified synthesis model, the Frequency-guided and Coarse-to-fine Unified Diffusion Model (FgC2F-UDiff), designed for multiple inputs and outputs. Specifically, the Coarse-to-fine Unified Network (CUN) fully exploits the iterative denoising properties of diffusion models, from global to detail, by dividing the denoising process into two stages, coarse and fine, to enhance the fidelity of synthesized images. Secondly, the Frequency-guided Collaborative Strategy (FCS) harnesses appropriate frequency information as prior knowledge to guide the learning of a unified, highly non-linear mapping. Thirdly, the Specific-acceleration Hybrid Mechanism (SHM) integrates specific mechanisms to accelerate the diffusion model and enhance the feasibility of many-to-many synthesis. Extensive experimental evaluations have demonstrated that our proposed FgC2F-UDiff model achieves superior performance on two datasets, validated through a comprehensive assessment that includes both qualitative observations and quantitative metrics, such as PSNR SSIM, LPIPS, and FID.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 29 of its 69 references that are in the map. First posted on arXiv 7 Jan 2025.

Builds on

29 of 69 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis24 Mar
  2. 2021Diffusion Models for Implicit Image Segmentation Ensembles6 Dec

Other references · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  7. 2022Diffusion Models in Vision: A Surveycited by 1,015
  8. 2021The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classificationcited by 518
  9. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  10. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  11. 2021ResViT: Residual vision transformers for multi-modal medical image synthesiscited by 177
  12. 2019Seeing What a GAN Cannot Generatecited by 148
15 more
  1. 2019Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Networkcited by 98
  2. 2020Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesiscited by 86
  3. 2022Conversion Between CT and MRI Images Using Diffusion and Score-Matching Modelscited by 69
  4. 2020Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusioncited by 68
  5. 2023Unified Multi-Modal Image Synthesis for Missing Modality Imputationcited by 40
  6. 2019mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesiscited by 34
  7. 2020Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recoverycited by 14
  8. 2018PIMMS: Permutation Invariant Multi-Modal Segmentationcited by 9
  9. 2023Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRIcited by 9
  10. 2021A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translationcited by 8
  11. 2023LFSRDiff: Light Field Image Super-Resolution via Diffusion Modelscited by 5
  12. 2024Mix-Domain Contrastive Learning for Unpaired H&E-to-IHC Stain Translationcited by 5
  13. 2022United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRIcited by 4
  14. 2023Disentangled Representation Learning for Controllable Person Image Generationcited by 4
  15. 2024Multi-Layer Dense Attention Decoder for Polyp Segmentationcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025How Far Are We from Generating Missing Modalities with Foundation Models?cited by 1
  2. 2025T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosiscited by 1
  3. 2025Pyramid Hierarchical Masked Diffusion Model for Imaging Synthesiscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Cycle-guided Denoising Diffusion Probability Model for 3D Cross-modality MRI Synthesis
  2. 2025AMM-Diff: Adaptive Multi-Modality Diffusion Network for Missing Modality Imputation
  3. 2026Frequency Error-Guided Under-sampling Optimization for Multi-Contrast MRI Reconstruction
  4. 2025SLaM-DiMM: Shared Latent Modeling for Diffusion Based Missing Modality Synthesis in MRI
  5. 2025D2Diff : A Dual Domain Diffusion Model for Accurate Multi-Contrast MRI Synthesis
  6. 2026WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis
  7. 2026VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation
  8. 2026Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation