Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction

Shu Wei Huang, Hao Min Cheng, Shien Fong Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Electrical impedance tomography (EIT) is a noninvasive and non-radiative medical imaging technique based on detecting the inhomogeneous electrical properties of the tissue. The inverse problem of EIT is a highly nonlinear ill-posed problem, which is the main reason that affects image quality. Our goal is to solve the EIT inverse problem using the nonlinear mapping properties of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this paper, the adaptive moment estimation (ADAM) optimization method and mean-square-error (MSE) function are used to train an ANN to solve the inverse problem and a CNN to process the ANN image. The networks are trained on datasets of simulated data, and tested on datasets of simulated data and experimental data. Results for time-difference EIT (td-EIT) images are presented using simulated EIT data from EIDORS and experimental EIT data from our EIT systems. The results are used to compare the proposed method with the one-step Gauss-Newton linear method and RBFNN method. The proposed method offers improved resolution (RES), low position error (PE) and excellent artefact removal compared to the existing methods. The experimental results show that our method can improve the RES by 50 to 70 percent and reduce the PE by 60 to 70 percent. The improvements in RES and processing speed are essential for clinical EIT measurement of dynamic physiological processes.

Original languageEnglish (US)
Title of host publication2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1551-1554
Number of pages4
ISBN (Electronic)9781538613115
DOIs
StatePublished - Jul 2019
Event41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 - Berlin, Germany
Duration: Jul 23 2019Jul 27 2019

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
ISSN (Print)1557-170X

Conference

Conference41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019
CountryGermany
CityBerlin
Period7/23/197/27/19

Fingerprint

Acoustic impedance
Computer-Assisted Image Processing
Image reconstruction
Electric Impedance
Tomography
Neural networks
Imaging techniques
Inverse problems
Physiological Phenomena
Medical imaging
Diagnostic Imaging
Mean square error
Artifacts
Image quality
Electric properties
Tissue
Processing

Keywords

  • Artificial neural network
  • Conductivity imaging
  • Electrical impedance tomography
  • Inverse solve

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Huang, S. W., Cheng, H. M., & Lin, S. F. (2019). Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019 (pp. 1551-1554). [8856781] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2019.8856781

Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction. / Huang, Shu Wei; Cheng, Hao Min; Lin, Shien Fong.

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1551-1554 8856781 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Huang, SW, Cheng, HM & Lin, SF 2019, Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019., 8856781, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, Institute of Electrical and Electronics Engineers Inc., pp. 1551-1554, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019, Berlin, Germany, 7/23/19. https://doi.org/10.1109/EMBC.2019.8856781
Huang SW, Cheng HM, Lin SF. Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1551-1554. 8856781. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2019.8856781
Huang, Shu Wei ; Cheng, Hao Min ; Lin, Shien Fong. / Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1551-1554 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{823172bdfbcb445080362a10aeb3b7cb,
title = "Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction",
abstract = "Electrical impedance tomography (EIT) is a noninvasive and non-radiative medical imaging technique based on detecting the inhomogeneous electrical properties of the tissue. The inverse problem of EIT is a highly nonlinear ill-posed problem, which is the main reason that affects image quality. Our goal is to solve the EIT inverse problem using the nonlinear mapping properties of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this paper, the adaptive moment estimation (ADAM) optimization method and mean-square-error (MSE) function are used to train an ANN to solve the inverse problem and a CNN to process the ANN image. The networks are trained on datasets of simulated data, and tested on datasets of simulated data and experimental data. Results for time-difference EIT (td-EIT) images are presented using simulated EIT data from EIDORS and experimental EIT data from our EIT systems. The results are used to compare the proposed method with the one-step Gauss-Newton linear method and RBFNN method. The proposed method offers improved resolution (RES), low position error (PE) and excellent artefact removal compared to the existing methods. The experimental results show that our method can improve the RES by 50 to 70 percent and reduce the PE by 60 to 70 percent. The improvements in RES and processing speed are essential for clinical EIT measurement of dynamic physiological processes.",
keywords = "Artificial neural network, Conductivity imaging, Electrical impedance tomography, Inverse solve",
author = "Huang, {Shu Wei} and Cheng, {Hao Min} and Lin, {Shien Fong}",
year = "2019",
month = "7",
doi = "10.1109/EMBC.2019.8856781",
language = "English (US)",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1551--1554",
booktitle = "2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019",

}

TY - GEN

T1 - Improved Imaging Resolution of Electrical Impedance Tomography Using Artificial Neural Networks for Image Reconstruction

AU - Huang, Shu Wei

AU - Cheng, Hao Min

AU - Lin, Shien Fong

PY - 2019/7

Y1 - 2019/7

N2 - Electrical impedance tomography (EIT) is a noninvasive and non-radiative medical imaging technique based on detecting the inhomogeneous electrical properties of the tissue. The inverse problem of EIT is a highly nonlinear ill-posed problem, which is the main reason that affects image quality. Our goal is to solve the EIT inverse problem using the nonlinear mapping properties of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this paper, the adaptive moment estimation (ADAM) optimization method and mean-square-error (MSE) function are used to train an ANN to solve the inverse problem and a CNN to process the ANN image. The networks are trained on datasets of simulated data, and tested on datasets of simulated data and experimental data. Results for time-difference EIT (td-EIT) images are presented using simulated EIT data from EIDORS and experimental EIT data from our EIT systems. The results are used to compare the proposed method with the one-step Gauss-Newton linear method and RBFNN method. The proposed method offers improved resolution (RES), low position error (PE) and excellent artefact removal compared to the existing methods. The experimental results show that our method can improve the RES by 50 to 70 percent and reduce the PE by 60 to 70 percent. The improvements in RES and processing speed are essential for clinical EIT measurement of dynamic physiological processes.

AB - Electrical impedance tomography (EIT) is a noninvasive and non-radiative medical imaging technique based on detecting the inhomogeneous electrical properties of the tissue. The inverse problem of EIT is a highly nonlinear ill-posed problem, which is the main reason that affects image quality. Our goal is to solve the EIT inverse problem using the nonlinear mapping properties of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this paper, the adaptive moment estimation (ADAM) optimization method and mean-square-error (MSE) function are used to train an ANN to solve the inverse problem and a CNN to process the ANN image. The networks are trained on datasets of simulated data, and tested on datasets of simulated data and experimental data. Results for time-difference EIT (td-EIT) images are presented using simulated EIT data from EIDORS and experimental EIT data from our EIT systems. The results are used to compare the proposed method with the one-step Gauss-Newton linear method and RBFNN method. The proposed method offers improved resolution (RES), low position error (PE) and excellent artefact removal compared to the existing methods. The experimental results show that our method can improve the RES by 50 to 70 percent and reduce the PE by 60 to 70 percent. The improvements in RES and processing speed are essential for clinical EIT measurement of dynamic physiological processes.

KW - Artificial neural network

KW - Conductivity imaging

KW - Electrical impedance tomography

KW - Inverse solve

UR - http://www.scopus.com/inward/record.url?scp=85077871486&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077871486&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2019.8856781

DO - 10.1109/EMBC.2019.8856781

M3 - Conference contribution

C2 - 31946190

AN - SCOPUS:85077871486

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 1551

EP - 1554

BT - 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -