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

arXiv: https://arxiv.org/abs/2501.03526 · HTML: https://mlsanity.com/paper/2501.03526/

## 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.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 29 of 29)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [Diffusion Models for Implicit Image Segmentation Ensembles](https://mlsanity.com/paper/2112.03145/) (2021)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network](https://mlsanity.com/paper/1904.12200/) (2019)
- [Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis](https://mlsanity.com/paper/2002.05000/) (2020)
- [Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models](https://mlsanity.com/paper/2209.12104/) (2022)
- [Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion](https://mlsanity.com/paper/2002.09708/) (2020)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [Unified Multi-Modal Image Synthesis for Missing Modality Imputation](https://mlsanity.com/paper/2304.05340/) (2023)
- [mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis](https://mlsanity.com/paper/1909.11504/) (2019)
- [Progressively Volumetrized Deep Generative Models for Data-Efficient Contextual Learning of MR Image Recovery](https://mlsanity.com/paper/2011.13913/) (2020)
- [PIMMS: Permutation Invariant Multi-Modal Segmentation](https://mlsanity.com/paper/1807.06537/) (2018)
- [Edge-aware Multi-task Network for Integrating Quantification Segmentation and Uncertainty Prediction of Liver Tumor on Multi-modality Non-contrast MRI](https://mlsanity.com/paper/2307.01798/) (2023)
- [A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation](https://mlsanity.com/paper/2110.10837/) (2021)
- [LFSRDiff: Light Field Image Super-Resolution via Diffusion Models](https://mlsanity.com/paper/2311.16517/) (2023)
- [Mix-Domain Contrastive Learning for Unpaired H&E-to-IHC Stain Translation](https://mlsanity.com/paper/2406.11799/) (2024)
- [United adversarial learning for liver tumor segmentation and detection of multi-modality non-contrast MRI](https://mlsanity.com/paper/2201.02629/) (2022)
- [Disentangled Representation Learning for Controllable Person Image Generation](https://mlsanity.com/paper/2312.05798/) (2023)
- [Multi-Layer Dense Attention Decoder for Polyp Segmentation](https://mlsanity.com/paper/2403.18180/) (2024)

## Built on by (most cited first, 3 of 3)

- [How Far Are We from Generating Missing Modalities with Foundation Models?](https://mlsanity.com/paper/2506.03530/) (2025)
- [T-CACE: A Time-Conditioned Autoregressive Contrast Enhancement Multi-Task Framework for Contrast-Free Liver MRI Synthesis, Segmentation, and Diagnosis](https://mlsanity.com/paper/2508.09919/) (2025)
- [Pyramid Hierarchical Masked Diffusion Model for Imaging Synthesis](https://mlsanity.com/paper/2507.16579/) (2025)

## 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.