Deep neural networks for non-linear model-based ultrasound reconstruction

H. Almansouri; S. V. Venkatakrishnan; G. T. Buzzard; C. A. Bouman; H. Santos-Villalobos

doi:10.1109/GlobalSIP.2018.8646704

Deep neural networks for non-linear model-based ultrasound reconstruction

H. Almansouri
, S. V. Venkatakrishnan
, G. T. Buzzard
, C. A. Bouman
, H. Santos-Villalobos

Multimodal Sensor Analytics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

10 Scopus citations

Abstract

Ultrasound reflection tomography is widely used to image large complex specimens that are only accessible from a single side, such as well systems and nuclear power plant containment walls. Typical methods for inverting the measurement rely on delay-and-sum algorithms that rapidly produce reconstructions but with significant artifacts. Recently, model-based reconstruction approaches using a linear forward model have been shown to significantly improve image quality compared to the conventional approach. However, even these techniques result in artifacts for complex objects because of the inherent non-linearity of the ultrasound forward model.In this paper, we propose a non-iterative model-based reconstruction method for inverting measurements that are based on non-linear forward models for ultrasound imaging. Our approach involves obtaining an approximate estimate of the reconstruction using a simple linear back-projection and training a deep neural network to refine this to the actual reconstruction. We apply our method to simulated and experimental ultrasound data to demonstrate dramatic improvements in image quality compared to the delay-and-sum approach and the linear model-based reconstruction approach.

Original language	English
Title of host publication	2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	6-10
Number of pages	5
ISBN (Electronic)	9781728112954
DOIs	https://doi.org/10.1109/GlobalSIP.2018.8646704
State	Published - Jul 2 2018
Event	2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Anaheim, United States Duration: Nov 26 2018 → Nov 29 2018

Publication series

Name	2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

Conference

Conference	2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018
Country/Territory	United States
City	Anaheim
Period	11/26/18 → 11/29/18

Funding

This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes.

Access to Document

10.1109/GlobalSIP.2018.8646704

Cite this

Almansouri, H., Venkatakrishnan, S. V., Buzzard, G. T., Bouman, C. A., & Santos-Villalobos, H. (2018). Deep neural networks for non-linear model-based ultrasound reconstruction. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings (pp. 6-10). Article 8646704 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2018.8646704

Almansouri, H. ; Venkatakrishnan, S. V. ; Buzzard, G. T. et al. / Deep neural networks for non-linear model-based ultrasound reconstruction. 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 6-10 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).

@inproceedings{2d19f4c2b0b54efcb698916ebe187fc0,

title = "Deep neural networks for non-linear model-based ultrasound reconstruction",

abstract = "Ultrasound reflection tomography is widely used to image large complex specimens that are only accessible from a single side, such as well systems and nuclear power plant containment walls. Typical methods for inverting the measurement rely on delay-and-sum algorithms that rapidly produce reconstructions but with significant artifacts. Recently, model-based reconstruction approaches using a linear forward model have been shown to significantly improve image quality compared to the conventional approach. However, even these techniques result in artifacts for complex objects because of the inherent non-linearity of the ultrasound forward model.In this paper, we propose a non-iterative model-based reconstruction method for inverting measurements that are based on non-linear forward models for ultrasound imaging. Our approach involves obtaining an approximate estimate of the reconstruction using a simple linear back-projection and training a deep neural network to refine this to the actual reconstruction. We apply our method to simulated and experimental ultrasound data to demonstrate dramatic improvements in image quality compared to the delay-and-sum approach and the linear model-based reconstruction approach.",

author = "H. Almansouri and Venkatakrishnan, \{S. V.\} and Buzzard, \{G. T.\} and Bouman, \{C. A.\} and H. Santos-Villalobos",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 ; Conference date: 26-11-2018 Through 29-11-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/GlobalSIP.2018.8646704",

language = "English",

series = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "6--10",

booktitle = "2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings",

}

Almansouri, H, Venkatakrishnan, SV, Buzzard, GT, Bouman, CA & Santos-Villalobos, H 2018, Deep neural networks for non-linear model-based ultrasound reconstruction. in 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings., 8646704, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 6-10, 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018, Anaheim, United States, 11/26/18. https://doi.org/10.1109/GlobalSIP.2018.8646704

Deep neural networks for non-linear model-based ultrasound reconstruction. / Almansouri, H.; Venkatakrishnan, S. V.; Buzzard, G. T. et al.
2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 6-10 8646704 (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep neural networks for non-linear model-based ultrasound reconstruction

AU - Almansouri, H.

AU - Venkatakrishnan, S. V.

AU - Buzzard, G. T.

AU - Bouman, C. A.

AU - Santos-Villalobos, H.

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Ultrasound reflection tomography is widely used to image large complex specimens that are only accessible from a single side, such as well systems and nuclear power plant containment walls. Typical methods for inverting the measurement rely on delay-and-sum algorithms that rapidly produce reconstructions but with significant artifacts. Recently, model-based reconstruction approaches using a linear forward model have been shown to significantly improve image quality compared to the conventional approach. However, even these techniques result in artifacts for complex objects because of the inherent non-linearity of the ultrasound forward model.In this paper, we propose a non-iterative model-based reconstruction method for inverting measurements that are based on non-linear forward models for ultrasound imaging. Our approach involves obtaining an approximate estimate of the reconstruction using a simple linear back-projection and training a deep neural network to refine this to the actual reconstruction. We apply our method to simulated and experimental ultrasound data to demonstrate dramatic improvements in image quality compared to the delay-and-sum approach and the linear model-based reconstruction approach.

AB - Ultrasound reflection tomography is widely used to image large complex specimens that are only accessible from a single side, such as well systems and nuclear power plant containment walls. Typical methods for inverting the measurement rely on delay-and-sum algorithms that rapidly produce reconstructions but with significant artifacts. Recently, model-based reconstruction approaches using a linear forward model have been shown to significantly improve image quality compared to the conventional approach. However, even these techniques result in artifacts for complex objects because of the inherent non-linearity of the ultrasound forward model.In this paper, we propose a non-iterative model-based reconstruction method for inverting measurements that are based on non-linear forward models for ultrasound imaging. Our approach involves obtaining an approximate estimate of the reconstruction using a simple linear back-projection and training a deep neural network to refine this to the actual reconstruction. We apply our method to simulated and experimental ultrasound data to demonstrate dramatic improvements in image quality compared to the delay-and-sum approach and the linear model-based reconstruction approach.

UR - https://www.scopus.com/pages/publications/85063103142

U2 - 10.1109/GlobalSIP.2018.8646704

DO - 10.1109/GlobalSIP.2018.8646704

M3 - Conference contribution

AN - SCOPUS:85063103142

T3 - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

SP - 6

EP - 10

BT - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018

Y2 - 26 November 2018 through 29 November 2018

ER -

Almansouri H, Venkatakrishnan SV, Buzzard GT, Bouman CA, Santos-Villalobos H. Deep neural networks for non-linear model-based ultrasound reconstruction. In 2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 6-10. 8646704. (2018 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2018 - Proceedings). doi: 10.1109/GlobalSIP.2018.8646704

Deep neural networks for non-linear model-based ultrasound reconstruction

Abstract

Publication series

Conference

Funding

Access to Document

Other files and links

Fingerprint

Cite this