# Rethinking Ultrasound Augmentation: A Physics-Inspired Approach

arXiv: https://arxiv.org/abs/2105.02188 · HTML: https://mlsanity.com/paper/2105.02188/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 22 references that are in the map.
- First posted on arXiv 5 May 2021.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Deep learning in ultrasound imaging](https://mlsanity.com/paper/1907.02994/) (2019)
- [Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13321/) (2020)
- [Simultaneous Segmentation and Classification of Bone Surfaces from Ultrasound Using a Multi-feature Guided CNN](https://mlsanity.com/paper/1806.09766/) (2018)
- [Force-Ultrasound Fusion: Bringing Spine Robotic-US to the Next "Level"](https://mlsanity.com/paper/2002.11404/) (2020)

## Built on by (most cited first, 15 of 15)

- [MI-SegNet: Mutual Information-Based US Segmentation for Unseen Domain Generalization](https://mlsanity.com/paper/2303.12649/) (2023)
- [Physiology-based simulation of the retinal vasculature enables annotation-free segmentation of OCT angiographs](https://mlsanity.com/paper/2207.11102/) (2022)
- [Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation](https://mlsanity.com/paper/2407.05428/) (2024)
- [Self-Supervised Learning with Limited Labeled Data for Prostate Cancer Detection in High Frequency Ultrasound](https://mlsanity.com/paper/2211.00527/) (2022)
- [Revisiting Data Augmentation for Ultrasound Images](https://mlsanity.com/paper/2501.13193/) (2025)
- [Conditional Generative Data Augmentation for Clinical Audio Datasets](https://mlsanity.com/paper/2203.11570/) (2022)
- [PINNs for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2408.01026/) (2024)
- [Investigating Pulse-Echo Sound Speed Estimation in Breast Ultrasound with Deep Learning](https://mlsanity.com/paper/2302.03064/) (2023)
- [LOTUS: Learning to Optimize Task-based US representations](https://mlsanity.com/paper/2307.16021/) (2023)
- [A novel open-source ultrasound dataset with deep learning benchmarks for spinal cord injury localization and anatomical segmentation](https://mlsanity.com/paper/2409.16441/) (2024)
- [Towards Real-time Intrahepatic Vessel Identification in Intraoperative Ultrasound-Guided Liver Surgery](https://mlsanity.com/paper/2410.03420/) (2024)
- [Artificial Intelligence for Biomedical Video Generation](https://mlsanity.com/paper/2411.07619/) (2024)
- [Physically Consistent Image Augmentation for Deep Learning in Mueller Matrix Polarimetry](https://mlsanity.com/paper/2411.07918/) (2024)
- [Improved Techniques for the Conditional Generative Augmentation of Clinical Audio Data](https://mlsanity.com/paper/2211.02874/) (2022)
- [FALCON: Few-Shot Adversarial Learning for Cross-Domain Medical Image Segmentation](https://mlsanity.com/paper/2601.01687/) (2026)

## Abstract (arXiv)

Medical Ultrasound (US), despite its wide use, is characterized by artifacts and operator dependency. Those attributes hinder the gathering and utilization of US datasets for the training of Deep Neural Networks used for Computer-Assisted Intervention Systems. Data augmentation is commonly used to enhance model generalization and performance. However, common data augmentation techniques, such as affine transformations do not align with the physics of US and, when used carelessly can lead to unrealistic US images. To this end, we propose a set of physics-inspired transformations, including deformation, reverb and Signal-to-Noise Ratio, that we apply on US B-mode images for data augmentation. We evaluate our method on a new spine US dataset for the tasks of bone segmentation and classification.