Shadow Reduction in Ultrasound Imaging Using Differentiable Simulation and Radiance Field Decomposition

2026-09-24

AI Summary

This study addresses the problem of acoustic shadows caused by highly attenuating tissues, such as bone, which obscure critical anatomical structures in ultrasound imaging. To overcome this limitation, this work proposes RFlash, a physics-informed post-processing framework that leverages differentiable radiance fields to decompose images into attenuation and scattering maps, adaptively re-rendering them to eliminate acoustic shadows. Notably, this approach requires no hardware modifications, avoids the hallucination artifacts common in generative models, and is compatible with standard 2D/3D scanning data acquired across multiple probe types. Evaluated on datasets including fetal brain imaging, RFlash significantly outperforms classical correction methods, reducing prediction errors by 40% while effectively enhancing both bone shadow segmentation accuracy and physical consistency.

Abstract

Acoustic shadows from bone and other highly attenuating tissues obscure clinically important structures in ultrasound. In fetal brain imaging, skull-induced artefacts disproportionately degrade the hemisphere closer to the transducer (proximal), limiting symmetric assessment of the two hemispheres. Existing correction methods require raw scanner data, impose restrictive assumptions on tissue properties, or rely on generative models that may hallucinate anatomy. We present RFlash, a physics-informed post-processing method that decomposes beamformed ultrasound images into explicit attenuation and scatter-intensity maps using a differentiable radiance-field formulation of image formation. Attenuation-adaptive re-rendering then removes the dependence of the signal at each depth on the intervening tissue, equivalent to virtually advancing the transducer into the tissue. Across 1,261 3D fetal brain volumes, 143 real 2D curvilinear abdominal scans, and 1,200 simulated 2D linear-probe liver scans, RFlash reduces shadow-related intensity differences more effectively than classical Hughes-Duck attenuation correction. For a gestational-age model trained on the distal hemisphere (further from the transducer) and applied to the proximal hemisphere, prediction error decreases by 5.1 days (40%) relative to the original images. The estimated attenuation maps also yield shadow-confidence maps that improve random-forest bone-shadow segmentation over the image alone and receive greater SHAP importance than an existing neural confidence-map baseline, suggesting greater physical consistency. RFlash requires neither hardware modification nor access to raw scanner data and supports 2D and 3D acquisitions with linear and curvilinear probes, making it widely applicable allowing clinicians to use our method on their already acquired scanners and images.

Problem

• Ultrasound imaging
• Acoustic shadow reduction
• Fetal brain imaging
• Shadow artifacts
• Attenuation

Innovation

• Differentiable Simulation
• Radiance Field Decomposition
• Ultrasound Shadow Reduction
• Physics-Informed Post-Processing
• Attenuation Map