# Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation

arXiv: https://arxiv.org/abs/2407.05428 · HTML: https://mlsanity.com/paper/2407.05428/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 24 references that are in the map.
- First posted on arXiv 7 Jul 2024.

## Builds on (most cited first, 16 of 16)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Understanding Diffusion Models: A Unified Perspective](https://mlsanity.com/paper/2208.11970/) (2022)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [Semantic Image Synthesis via Diffusion Models](https://mlsanity.com/paper/2207.00050/) (2022)
- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation](https://mlsanity.com/paper/2305.05424/) (2023)
- [Tracked 3D Ultrasound and Deep Neural Network-based Thyroid Segmentation reduce Interobserver Variability in Thyroid Volumetry](https://mlsanity.com/paper/2108.10118/) (2021)
- [MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization](https://mlsanity.com/paper/2303.12649/) (2023)
- [Rethinking Ultrasound Augmentation: A Physics-Inspired Approach](https://mlsanity.com/paper/2105.02188/) (2021)
- [Multi-Level Global Context Cross Consistency Model for Semi-Supervised Ultrasound Image Segmentation with Diffusion Model](https://mlsanity.com/paper/2305.09447/) (2023)
- [CACTUSS: Common Anatomical CT-US Space for US examinations](https://mlsanity.com/paper/2207.08619/) (2022)
- [Deep Ultrasound Denoising Without Clean Data](https://mlsanity.com/paper/2201.02604/) (2022)
- [Ultrasound Speckle Suppression and Denoising using MRI-derived Normalizing Flow Priors](https://mlsanity.com/paper/2112.13110/) (2021)
- [LOTUS: Learning to Optimize Task-based US representations](https://mlsanity.com/paper/2307.16021/) (2023)

## Built on by (most cited first, 10 of 10)

- [Ultrasound Image Generation using Latent Diffusion Models](https://mlsanity.com/paper/2502.08580/) (2025)
- [Denoising Plane Wave Ultrasound Images Using Diffusion Probabilistic Models](https://mlsanity.com/paper/2408.10987/) (2024)
- [Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images](https://mlsanity.com/paper/2411.04004/) (2024)
- [High Volume Rate 3D Ultrasound Reconstruction with Diffusion Models](https://mlsanity.com/paper/2505.22090/) (2025)
- [Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoising](https://mlsanity.com/paper/2506.21499/) (2025)
- [Physical foundations for trustworthy medical imaging: a review for artificial intelligence researchers](https://mlsanity.com/paper/2505.02843/) (2025)
- [AWDiff: An a trous wavelet diffusion model for lung ultrasound image synthesis](https://mlsanity.com/paper/2603.03125/) (2026)
- [Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis](https://mlsanity.com/paper/2607.11655/) (2026)
- [One Model, Two Worlds: Bidirectional Sonar-Optical Translation](https://mlsanity.com/paper/2609.06253/) (2026)
- [Abdominal Ultrasound Simulation from Semantic Labels using Paired Label-to-Physics-Based Image Translation](https://mlsanity.com/paper/2610.08849/) (2026)

## Abstract (arXiv)

Deep learning (DL) methods typically require large datasets to effectively learn data distributions. However, in the medical field, data is often limited in quantity, and acquiring labeled data can be costly. To mitigate this data scarcity, data augmentation techniques are commonly employed. Among these techniques, generative models play a pivotal role in expanding datasets. However, when it comes to ultrasound (US) imaging, the authenticity of generated data often diminishes due to the oversight of ultrasound physics. We propose a novel approach to improve the quality of generated US images by introducing a physics-based diffusion model that is specifically designed for this image modality. The proposed model incorporates an US-specific scheduler scheme that mimics the natural behavior of sound wave propagation in ultrasound imaging. Our analysis demonstrates how the proposed method aids in modeling the attenuation dynamics in US imaging. We present both qualitative and quantitative results based on standard generative model metrics, showing that our proposed method results in overall more plausible images. Our code is available at https://github.com/marinadominguez/diffusion-for-us-images