A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks
Electrical impedance tomography (EIT) provides an indirect measure of the physiological state and growth of the maize ear by reconstructing the distribution of electrical impedance. However, the two-dimensional (2D) EIT within the electrode plane finds it challenging to comprehensively represent the...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2024-04-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-1944.pdf |
_version_ | 1797209786718093312 |
---|---|
author | Hai-Ying Zheng Yang Li Nan Wang Yang Xiang Jin-Hang Liu Liu-Deng Zhang Lan Huang Zhong-Yi Wang |
author_facet | Hai-Ying Zheng Yang Li Nan Wang Yang Xiang Jin-Hang Liu Liu-Deng Zhang Lan Huang Zhong-Yi Wang |
author_sort | Hai-Ying Zheng |
collection | DOAJ |
description | Electrical impedance tomography (EIT) provides an indirect measure of the physiological state and growth of the maize ear by reconstructing the distribution of electrical impedance. However, the two-dimensional (2D) EIT within the electrode plane finds it challenging to comprehensively represent the spatial distribution of conductivity of the intact maize ear, including the husk, kernels, and cob. Therefore, an effective method for 3D conductivity reconstruction is necessary. In practical applications, fluctuations in the contact impedance of the maize ear occur, particularly with the increase in the number of grids and computational workload during the reconstruction of 3D spatial conductivity. These fluctuations may accentuate the ill-conditioning and nonlinearity of the EIT. To address these challenges, we introduce RFNetEIT, a novel computational framework specifically tailored for the absolute imaging of the three-dimensional electrical impedance of maize ear. This strategy transforms the reconstruction of 3D electrical conductivity into a regression process. Initially, a feature map is extracted from measured boundary voltage via a data reconstruction module, thereby enhancing the correlation among different dimensions. Subsequently, a nonlinear mapping model of the 3D spatial distribution of the boundary voltage and conductivity is established, utilizing the residual network. The performance of the proposed framework is assessed through numerical simulation experiments, acrylic model experiments, and maize ear experiments. Our experimental results indicate that our method yields superior reconstruction performance in terms of root-mean-square error (RMSE), correlation coefficient (CC), structural similarity index (SSIM), and inverse problem-solving time (IPST). Furthermore, the reconstruction experiments on maize ears demonstrate that the method can effectively reconstruct the 3D conductivity distribution. |
first_indexed | 2024-04-24T10:00:14Z |
format | Article |
id | doaj.art-cfc1ff5beeb64feabda397595d365e48 |
institution | Directory Open Access Journal |
issn | 2376-5992 |
language | English |
last_indexed | 2024-04-24T10:00:14Z |
publishDate | 2024-04-01 |
publisher | PeerJ Inc. |
record_format | Article |
series | PeerJ Computer Science |
spelling | doaj.art-cfc1ff5beeb64feabda397595d365e482024-04-13T15:05:07ZengPeerJ Inc.PeerJ Computer Science2376-59922024-04-0110e194410.7717/peerj-cs.1944A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networksHai-Ying Zheng0Yang Li1Nan Wang2Yang Xiang3Jin-Hang Liu4Liu-Deng Zhang5Lan Huang6Zhong-Yi Wang7College of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaCollege of Information and Electrical Engineering, China Agricultural University, Beijing, ChinaElectrical impedance tomography (EIT) provides an indirect measure of the physiological state and growth of the maize ear by reconstructing the distribution of electrical impedance. However, the two-dimensional (2D) EIT within the electrode plane finds it challenging to comprehensively represent the spatial distribution of conductivity of the intact maize ear, including the husk, kernels, and cob. Therefore, an effective method for 3D conductivity reconstruction is necessary. In practical applications, fluctuations in the contact impedance of the maize ear occur, particularly with the increase in the number of grids and computational workload during the reconstruction of 3D spatial conductivity. These fluctuations may accentuate the ill-conditioning and nonlinearity of the EIT. To address these challenges, we introduce RFNetEIT, a novel computational framework specifically tailored for the absolute imaging of the three-dimensional electrical impedance of maize ear. This strategy transforms the reconstruction of 3D electrical conductivity into a regression process. Initially, a feature map is extracted from measured boundary voltage via a data reconstruction module, thereby enhancing the correlation among different dimensions. Subsequently, a nonlinear mapping model of the 3D spatial distribution of the boundary voltage and conductivity is established, utilizing the residual network. The performance of the proposed framework is assessed through numerical simulation experiments, acrylic model experiments, and maize ear experiments. Our experimental results indicate that our method yields superior reconstruction performance in terms of root-mean-square error (RMSE), correlation coefficient (CC), structural similarity index (SSIM), and inverse problem-solving time (IPST). Furthermore, the reconstruction experiments on maize ears demonstrate that the method can effectively reconstruct the 3D conductivity distribution.https://peerj.com/articles/cs-1944.pdfElectrical impedance tomography (EIT)Maize ear3D conductivity distributionFeature reconfigurationResidual networks |
spellingShingle | Hai-Ying Zheng Yang Li Nan Wang Yang Xiang Jin-Hang Liu Liu-Deng Zhang Lan Huang Zhong-Yi Wang A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks PeerJ Computer Science Electrical impedance tomography (EIT) Maize ear 3D conductivity distribution Feature reconfiguration Residual networks |
title | A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
title_full | A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
title_fullStr | A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
title_full_unstemmed | A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
title_short | A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
title_sort | novel framework for three dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks |
topic | Electrical impedance tomography (EIT) Maize ear 3D conductivity distribution Feature reconfiguration Residual networks |
url | https://peerj.com/articles/cs-1944.pdf |
work_keys_str_mv | AT haiyingzheng anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT yangli anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT nanwang anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT yangxiang anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT jinhangliu anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT liudengzhang anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT lanhuang anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT zhongyiwang anovelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT haiyingzheng novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT yangli novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT nanwang novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT yangxiang novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT jinhangliu novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT liudengzhang novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT lanhuang novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks AT zhongyiwang novelframeworkforthreedimensionalelectricalimpedancetomographyreconstructionofmaizeearviafeaturereconfigurationandresidualnetworks |