WaveFlow - Towards Integration of Ultrasound Processing with Deep Learning
Abstract
The ultimate goal of this work is a real-time processing framework for ultrasound image reconstruction augmented with machine learning. To attain this, we have implemented WaveFlow - a set of ultrasound data acquisition and processing tools for TensorFlow. WaveFlow includes: ultrasound Environments (connection points between the input raw ultrasound data source and TensorFlow) and signal processing Operators (ops) library. Raw data can be processed in real-time using algorithms available both in TensorFlow and WaveFlow. Currently, WaveFlow provides ops for B-mode image reconstruction (beamforming), signal processing and quantitative ultrasound. The ops were implemented both for the CPU and GPU, as well as for built-in automated tests and benchmarks. To demonstrate WaveFlow's performance, ultrasound data were acquired from wire and cyst phantoms and elaborated using selected sequences of the ops. We implemented and evaluated: Delay-and-Sum beamformer, synthetic transmit aperture imaging (STAI), plane-wave imaging (PWI), envelope detection algorithm and dynamic range clipping. The benchmarks were executed on the NVidia Titan X GPU integrated in the USPlatform research scanner (us4us Ltd., Poland). We achieved B-mode image reconstruction frame rates of 55 fps, 17 fps for the STAI and the PWI algorithms, respectively. The results showed the feasibility of real-time ultrasound image reconstruction using WaveFlow operators in the TensorFlow framework. WaveFlow source code can be found at github.com/waveflow-team/waveflow
Cite
@article{arxiv.1811.01566,
title = {WaveFlow - Towards Integration of Ultrasound Processing with Deep Learning},
author = {Piotr Jarosik and Michał Byra and Marcin Lewandowski},
journal= {arXiv preprint arXiv:1811.01566},
year = {2018}
}
Comments
2018 IEEE International Ultrasonics Symposium