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

TL;DR

This paper introduces a physics-inspired diffusion model tailored for ultrasound image generation, enhancing the realism of synthetic US images by mimicking sound wave propagation physics, which benefits data augmentation in medical imaging.

Contribution

The paper presents a novel ultrasound-specific diffusion model with a physics-based scheduler that improves the authenticity of generated US images, addressing limitations of prior generative approaches.

Findings

Generated images are more plausible and realistic.

Quantitative metrics show improved quality over baseline models.

The model effectively captures sound wave attenuation dynamics.

Abstract

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