UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes

2025-05-08

AI Summary

Ultrasound imaging is safe, cost-effective, and real-time, yet its 2D interpretation is highly operator-dependent, leading to high diagnostic variability and poor standardization. Existing 2D-to-3D reconstruction methods suffer from excessive computational cost, high memory consumption, and neglect of ultrasound physics. This paper proposes the first ultrasound-physics-aware Gaussian rasterization framework: it explicitly models intersections between the transducer plane and acoustic wavefronts; introduces GPU-efficient analytical raster boundary formulations and numerically stable covariance parameterization; and integrates ultrasound-specific Gaussian splatting, acoustically aligned 3D transducer modeling, and CUDA-accelerated rasterization. On a single GPU, our method achieves state-of-the-art reconstruction quality in just five minutes, attaining an SSIM of 0.99 within twenty minutes. Clinical blind evaluation confirms it delivers the most anatomically faithful and diagnostically reliable reconstructions to date.

Technology Category

• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Data transparency and provenance
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Ultrasound imaging is widely used due to its safety, affordability, and real-time capabilities, but its 2D interpretation is highly operator-dependent, leading to variability and increased cognitive demand. 2D-to-3D reconstruction mitigates these challenges by providing standardized volumetric views, yet existing methods are often computationally expensive, memory-intensive, or incompatible with ultrasound physics. We introduce UltraGauss: the first ultrasound-specific Gaussian Splatting framework, extending view synthesis techniques to ultrasound wave propagation. Unlike conventional perspective-based splatting, UltraGauss models probe-plane intersections in 3D, aligning with acoustic image formation. We derive an efficient rasterization boundary formulation for GPU parallelization and introduce a numerically stable covariance parametrization, improving computational efficiency and reconstruction accuracy. On real clinical ultrasound data, UltraGauss achieves state-of-the-art reconstructions in 5 minutes, and reaching 0.99 SSIM within 20 minutes on a single GPU. A survey of expert clinicians confirms UltraGauss' reconstructions are the most realistic among competing methods. Our CUDA implementation will be released upon publication.

Problem

• 2D ultrasound interpretation is operator-dependent and variable
• Existing 3D reconstruction methods are computationally expensive
• Current techniques often ignore ultrasound physics principles

Innovation

• Ultrasound-specific Gaussian Splatting framework
• Efficient GPU-parallelized rasterization boundary formulation
• Numerically stable covariance parametrization for accuracy