# Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness

arXiv: https://arxiv.org/abs/2202.01208 · HTML: https://mlsanity.com/paper/2202.01208/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 103 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 23 of 23)

- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Deeper Depth Prediction with Fully Convolutional Residual Networks](https://mlsanity.com/paper/1606.00373/) (2016)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [Single-Image Depth Perception in the Wild](https://mlsanity.com/paper/1604.03901/) (2016)
- [An overview of deep learning in medical imaging focusing on MRI](https://mlsanity.com/paper/1811.10052/) (2018)
- [How much data is needed to train a medical image deep learning system to achieve necessary high accuracy?](https://mlsanity.com/paper/1511.06348/) (2015)
- [Deep learning in ultrasound imaging](https://mlsanity.com/paper/1907.02994/) (2019)
- [A Gentle Introduction to Deep Learning in Medical Image Processing](https://mlsanity.com/paper/1810.05401/) (2018)
- [Adaptive and Compressive Beamforming Using Deep Learning for Medical Ultrasound](https://mlsanity.com/paper/1907.10257/) (2019)
- [A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound](https://mlsanity.com/paper/1810.00322/) (2018)
- [Efficient B-mode Ultrasound Image Reconstruction from Sub-sampled RF Data using Deep Learning](https://mlsanity.com/paper/1712.06096/) (2017)
- [High Resolution 3D Ultrasonic Breast Imaging by Time-Domain Full Waveform Inversion](https://mlsanity.com/paper/2102.00755/) (2021)
- [Ultrasound Elasticity Imaging Using Physics-based Models And Learning-based Plug-And-Play Priors](https://mlsanity.com/paper/2103.14096/) (2021)
- [Towards CT-quality Ultrasound Imaging using Deep Learning](https://mlsanity.com/paper/1710.06304/) (2017)
- [Deep Variational Networks with Exponential Weighting for Learning Computed Tomography](https://mlsanity.com/paper/1906.05528/) (2019)
- [Training Variational Networks with Multi-Domain Simulations: Speed-of-Sound Image Reconstruction](https://mlsanity.com/paper/2006.14395/) (2020)
- [Domain Adaptation for Ultrasound Beamforming](https://mlsanity.com/paper/2007.03096/) (2020)
- [Detecting muscle activation using ultrasound speed of sound inversion with deep learning](https://mlsanity.com/paper/1910.09046/) (2019)

## Built on by (most cited first, 3 of 3)

- [Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data](https://mlsanity.com/paper/2312.10271/) (2023)
- [Learning-based sound speed estimation and aberration correction in linear-array photoacoustic imaging](https://mlsanity.com/paper/2306.11034/) (2023)
- [AutoSpeed: A Linked Autoencoder Approach for Pulse-Echo Speed-of-Sound Imaging for Medical Ultrasound](https://mlsanity.com/paper/2207.02392/) (2022)

## Abstract (arXiv)

Ultrasound b-mode imaging is a qualitative approach and diagnostic quality strongly depends on operators' training and experience. Quantitative approaches can provide information about tissue properties; therefore, can be used for identifying various tissue types, e.g., speed-of-sound in the tissue can be used as a biomarker for tissue malignancy, especially in breast imaging. Recent studies showed the possibility of speed-of-sound reconstruction using deep neural networks that are fully trained on simulated data. However, because of the ever-present domain shift between simulated and measured data, the stability and performance of these models in real setups are still under debate. In prior works, for training data generation, tissue structures were modeled as simplified geometrical structures which does not reflect the complexity of the real tissues. In this study, we proposed a new simulation setup for training data generation based on Tomosynthesis images. We combined our approach with the simplified geometrical model and investigated the impacts of training data diversity on the stability and robustness of an existing network architecture. We studied the sensitivity of the trained network to different simulation parameters, e.g., echogenicity, number of scatterers, noise, and geometry. We showed that the network trained with the joint set of data is more stable on out-of-domain simulated data as well as measured phantom data.