UltraG-Ray: Physics-Based Gaussian Ray Casting for Novel Ultrasound View Synthesis

TL;DR

UltraG-Ray introduces a physics-based Gaussian ray casting method for ultrasound view synthesis, improving realism by explicitly modeling tissue effects and view-dependent attenuation.

Contribution

It proposes a learnable 3D Gaussian scene representation combined with a physics-based ray casting scheme for more realistic ultrasound image synthesis.

Findings

Achieves up to 15% increase in MS-SSIM over state-of-the-art methods.

Captures view-dependent attenuation effects naturally.

Produces more realistic B-mode ultrasound images.

Abstract

Novel view synthesis (NVS) in ultrasound has gained attention as a technique for generating anatomically plausible views beyond the acquired frames, offering new capabilities for training clinicians or data augmentation. However, current methods struggle with complex tissue and view-dependent acoustic effects. Physics-based NVS aims to address these limitations by including the ultrasound image formation process into the simulation. Recent approaches combine a learnable implicit scene representation with an ultrasound-specific rendering module, yet a substantial gap between simulation and reality remains. In this work, we introduce UltraG-Ray, a novel ultrasound scene representation based on a learnable 3D Gaussian field, coupled to an efficient physics-based module for B-mode synthesis. We explicitly encode ultrasound-specific parameters, such as attenuation and reflection, into a Gaussian-based spatial representation and realize image synthesis within a novel ray casting scheme. In contrast to previous methods, this approach naturally captures view-dependent attenuation effects, thereby enabling the generation of physically informed B-mode images with increased realism. We compare our method to state-of-the-art and observe consistent gains in image quality metrics (up to 15% increase on MS-SSIM), demonstrating clear improvement in terms of realism of the synthesized ultrasound images.