2021
DOI: 10.1007/978-3-030-80432-9_11
|View full text |Cite
|
Sign up to set email alerts
|

Data-Driven Speed-of-Sound Reconstruction for Medical Ultrasound: Impacts of Training Data Format and Imperfections on Convergence

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
1

Relationship

1
7

Authors

Journals

citations
Cited by 8 publications
(5 citation statements)
references
References 19 publications
0
5
0
Order By: Relevance
“…Results on the human neck and calf muscles provided promising indications of SoS variations. Similarly, Jush et al explored a deep neural network for SoS reconstruction for US breast imaging using single plane wave US acquisition [31] and further extended to in-phase and quadrature data as the input [38]. Inspired by the feasibility of retrieving SoS distributions from US channel data with deep neural networks, a learningbased SoS correction method for PA imaging was proposed based on a dual-modal PA/US imaging system.…”
Section: Discussionmentioning
confidence: 99%
“…Results on the human neck and calf muscles provided promising indications of SoS variations. Similarly, Jush et al explored a deep neural network for SoS reconstruction for US breast imaging using single plane wave US acquisition [31] and further extended to in-phase and quadrature data as the input [38]. Inspired by the feasibility of retrieving SoS distributions from US channel data with deep neural networks, a learningbased SoS correction method for PA imaging was proposed based on a dual-modal PA/US imaging system.…”
Section: Discussionmentioning
confidence: 99%
“…Phase Noise Studies showed that phase distortions can a↵ect SoS predictions (Stähli et al, 2020a;Khun Jush et al, 2021). Therefore, we applied uncorrelated phase distortions by shifting the phase of each channel by a random value in the range [ 0.7, 0.7] radian.…”
Section: Number Of Reflective Specklesmentioning
confidence: 99%
“…For SoS reconstruction, acquiring sufficient measured data alongside its corresponding GT for training a deep neural network is challenging because there is no known gold-standard method capable of creating exact GT for reflection data (pulse-echo ultrasound) and there are only a few phantoms available with known heterogeneous SoS. Therefore, for deep learning-based approaches using simulated data for training is a common practice [7,10,11,12,13,14,15,16]. K-Wave toolbox [26] (Version 1.3) is used for the simulation of training data.…”
Section: Datasetmentioning
confidence: 99%
“…Similar techniques are employed for SoS reconstruction from ultrasound echo data. [10,11,12,13,14,15,16] investigated encoder-decoder networks with multiple or single steering angles for SoS reconstruction. In these studies, an encoder-decoder network takes sensor domain data as input and directly reconstructs the SoS map in the output.…”
Section: Introductionmentioning
confidence: 99%