# Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis

arXiv: https://arxiv.org/abs/2406.03002 · HTML: https://mlsanity.com/paper/2406.03002/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Placed in

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

## Builds on (most cited first, 28 of 28)

- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Generating Images with Sparse Representations](https://mlsanity.com/paper/2103.03841/) (2021)
- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [Seeing What a GAN Cannot Generate](https://mlsanity.com/paper/1910.11626/) (2019)
- [Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers](https://mlsanity.com/paper/2401.11605/) (2024)
- [CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI Synthesis](https://mlsanity.com/paper/2303.14081/) (2023)
- [DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-Resolution](https://mlsanity.com/paper/2303.13933/) (2023)
- [A Closer Look at the Optimization Landscapes of Generative Adversarial Networks](https://mlsanity.com/paper/1906.04848/) (2019)
- [Multi-modal learning for predicting the genotype of glioma](https://mlsanity.com/paper/2203.10852/) (2022)
- [Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI](https://mlsanity.com/paper/2106.13188/) (2021)
- [BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification](https://mlsanity.com/paper/2103.08494/) (2021)
- [Atlas-powered deep learning (ADL) -- application to diffusion weighted MRI](https://mlsanity.com/paper/2205.03210/) (2022)

## Built on by (most cited first, 8 of 8)

- [Artificial Intelligence for Biomedical Video Generation](https://mlsanity.com/paper/2411.07619/) (2024)
- [Schr"odinger Diffusion Driven Signal Recovery in 3T BOLD fMRI Using Unmatched 7T Observations](https://mlsanity.com/paper/2504.01004/) (2025)
- [Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRI](https://mlsanity.com/paper/2509.07020/) (2025)
- [USB: Unified Synthetic Brain Framework for Bidirectional Pathology-Healthy Generation and Editing](https://mlsanity.com/paper/2512.00269/) (2025)
- [Joint Modelling Histology and Molecular Markers for Cancer Classification](https://mlsanity.com/paper/2502.07979/) (2025)
- [GM-LDM: Latent Diffusion Model for Brain Biomarker Identification through Functional Data-Driven Gray Matter Synthesis](https://mlsanity.com/paper/2506.12719/) (2025)
- [HaDM-ST: Histology-Assisted Differential Modeling for Spatial Transcriptomics Generation](https://mlsanity.com/paper/2508.07225/) (2025)
- [FOD-Diff: 3D Multi-Channel Patch Diffusion Model for Fiber Orientation Distribution](https://mlsanity.com/paper/2512.16075/) (2025)

## Abstract (arXiv)

Diffusion MRI (dMRI) is an important neuroimaging technique with high acquisition costs. Deep learning approaches have been used to enhance dMRI and predict diffusion biomarkers through undersampled dMRI. To generate more comprehensive raw dMRI, generative adversarial network based methods are proposed to include b-values and b-vectors as conditions, but they are limited by unstable training and less desirable diversity. The emerging diffusion model (DM) promises to improve generative performance. However, it remains challenging to include essential information in conditioning DM for more relevant generation, i.e., the physical principles of dMRI and white matter tract structures. In this study, we propose a physics-guided diffusion model to generate high-quality dMRI. Our model introduces the physical principles of dMRI in the noise evolution in the diffusion process and introduce a query-based conditional mapping within the difussion model. In addition, to enhance the anatomical fine detials of the generation, we introduce the XTRACT atlas as prior of white matter tracts by adopting an adapter technique. Our experiment results show that our method outperforms other state-of-the-art methods and has the potential to advance dMRI enhancement.