Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction

Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image reconstruction

Zhao, Wenzhao (University Heidelberg)
Fan, Yuling (University Heidelberg)
Wang, Hongjian (Donghua University)
Gemmeke, Hartmut (Karlsruhe Institut für Technologie)
van Dongen, K.W.A. (TU Delft ImPhys/Medical Imaging; TU Delft ImPhys/Van Dongen goup)
Hopp, Torsten (Karlsruhe Institut für Technologie)
Hesser, Jürgen (University Heidelberg)

2023

Objective. The image reconstruction of ultrasound computed tomography is computationally expensive with conventional iterative methods. The fully learned direct deep learning reconstruction is promising to speed up image reconstruction significantly. However, for direct reconstruction from measurement data, due to the lack of real labeled data, the neural network is usually trained on a simulation dataset and shows poor performance on real data because of the simulation-to-real gap.Approach. To improve the simulation-to-real generalization of neural networks, a series of strategies are developed including a Fourier-transform-integrated neural network, measurement-domain data augmentation methods, and a self-supervised-learning-based patch-wise preprocessing neural network. Our strategies are evaluated on both the simulation dataset and real measurement datasets from two different prototype machines.Main results. The experimental results show that our deep learning methods help to improve the neural networks' robustness against noise and the generalizability to real measurement data.Significance. Our methods prove that it is possible for neural networks to achieve superior performance to traditional iterative reconstruction algorithms in imaging quality and allow for real-time 2D-image reconstruction. This study helps pave the path for the application of deep learning methods to practical ultrasound tomography image reconstruction based on simulation datasets.

deep learning
Fourier transform
measurement domain
refraction-corrected ultrasound tomography
simulation-to-real generalization

http://resolver.tudelft.nl/uuid:e419a842-d1e5-419b-bafb-fe70974b8605

https://doi.org/10.1088/1361-6560/acaeed

2023-07-27

Physics in Medicine and Biology, 68 (3)

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2023 Wenzhao Zhao, Yuling Fan, Hongjian Wang, Hartmut Gemmeke, K.W.A. van Dongen, Torsten Hopp, Jürgen Hesser