# Pyramid Hierarchical Masked Diffusion Model for Imaging Synthesis

arXiv: https://arxiv.org/abs/2507.16579 · HTML: https://mlsanity.com/paper/2507.16579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 25 of its 42 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [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)
- [Generative Moment Matching Networks](https://mlsanity.com/paper/1502.02761/) (2015)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis](https://mlsanity.com/paper/1612.07919/) (2016)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Missing MRI Pulse Sequence Synthesis using Multi-Modal Generative Adversarial Network](https://mlsanity.com/paper/1904.12200/) (2019)
- [Diffusion Probabilistic Models beat GANs on Medical Images](https://mlsanity.com/paper/2212.07501/) (2022)
- [Diffusion Models as Masked Autoencoders](https://mlsanity.com/paper/2304.03283/) (2023)
- [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)
- [VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers](https://mlsanity.com/paper/2104.06757/) (2021)
- [GANBERT: Generative Adversarial Networks with Bidirectional Encoder Representations from Transformers for MRI to PET synthesis](https://mlsanity.com/paper/2008.04393/) (2020)
- [PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer](https://mlsanity.com/paper/2105.13993/) (2021)
- [Six-channel Image Representation for Cross-domain Object Detection](https://mlsanity.com/paper/2101.00561/) (2021)
- [FgC2F-UDiff: Frequency-guided and Coarse-to-fine Unified Diffusion Model for Multi-modality Missing MRI Synthesis](https://mlsanity.com/paper/2501.03526/) (2025)

## Abstract (arXiv)

Medical image synthesis plays a crucial role in clinical workflows, addressing the common issue of missing imaging modalities due to factors such as extended scan times, scan corruption, artifacts, patient motion, and intolerance to contrast agents. The paper presents a novel image synthesis network, the Pyramid Hierarchical Masked Diffusion Model (PHMDiff), which employs a multi-scale hierarchical approach for more detailed control over synthesizing high-quality images across different resolutions and layers. Specifically, this model utilizes randomly multi-scale high-proportion masks to speed up diffusion model training, and balances detail fidelity and overall structure. The integration of a Transformer-based Diffusion model process incorporates cross-granularity regularization, modeling the mutual information consistency across each granularity's latent spaces, thereby enhancing pixel-level perceptual accuracy. Comprehensive experiments on two challenging datasets demonstrate that PHMDiff achieves superior performance in both the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), highlighting its capability to produce high-quality synthesized images with excellent structural integrity. Ablation studies further confirm the contributions of each component. Furthermore, the PHMDiff model, a multi-scale image synthesis framework across and within medical imaging modalities, shows significant advantages over other methods. The source code is available at https://github.com/xiaojiao929/PHMDiff