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

arXiv: https://arxiv.org/abs/2609.29373 · HTML: https://mlsanity.com/paper/2609.29373/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 56 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 12 of 12)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [TensoRF: Tensorial Radiance Fields](https://mlsanity.com/paper/2203.09517/) (2022)
- [Ultra-NeRF: Neural Radiance Fields for Ultrasound Imaging](https://mlsanity.com/paper/2301.10520/) (2023)
- [UltraGauss: Ultrafast Gaussian Reconstruction of 3D Ultrasound Volumes](https://mlsanity.com/paper/2505.05643/) (2025)
- [RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans](https://mlsanity.com/paper/2404.10766/) (2024)
- [NeRF-US: Removing Ultrasound Imaging Artifacts from Neural Radiance Fields in the Wild](https://mlsanity.com/paper/2408.10258/) (2024)
- [UltraRay: Introducing Full-Path Ray Tracing in Physics-Based Ultrasound Simulation](https://mlsanity.com/paper/2501.05828/) (2025)
- [UlRe-NeRF: 3D Ultrasound Imaging through Neural Rendering with Ultrasound Reflection Direction Parameterization](https://mlsanity.com/paper/2408.00860/) (2024)
- [Shadow Detection for Ultrasound Images Using Unlabeled Data and Synthetic Shadows](https://mlsanity.com/paper/1908.01439/) (2019)
- [DiffUS: Differentiable Ultrasound Rendering from Volumetric Imaging](https://mlsanity.com/paper/2508.06768/) (2025)

## Abstract (arXiv)

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.