Planar array magnetic induction tomography further improvement

Li, Fang; Soleimani, Masoud; Abascal, Juan F P J

doi:10.1108/sr-02-2018-0027

Cited by 4 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The imaging process has two essential stages: one is the forward modeling, and the other is image reconstruction, often termed as the inverse problem [34]. During the test, the time difference (TD) method was adopted to obtain the resistance projection (P), where P equaled the difference of the resistances at different times: one with a homogeneous conductive background and the other with detected samples added into the background [35]. Tap water with a conductivity of σ = 0.018 S/m was taken as the background medium.…”

Section: Conventional Forward Modeling and Image Reconstruction Algorithm Of Ccertmentioning

confidence: 99%

Application of Deep Neural Network to the Reconstruction of Two-Phase Material Imaging by Capacitively Coupled Electrical Resistance Tomography

Chen

Jiang

et al. 2021

Electronics

View full text Add to dashboard Cite

A convolutional neural network (CNN)-based image reconstruction algorithm for two-phase material imaging is presented and verified with experimental data from a capacitively coupled electrical resistance tomography (CCERT) sensor. As a contactless version of electrical resistance tomography (ERT), CCERT has advantages such as no invasion, low cost, no radiation, and rapid response for two-phase material imaging. Besides that, CCERT avoids contact error of ERT by imaging from outside of the pipe. Forward modeling was implemented based on the practical circular array sensor, and the inverse image reconstruction was realized by a CNN-based supervised learning algorithm, as well as the well-known total variation (TV) regularization algorithm for comparison. The 2D, monochrome, 2500-pixel image was divided into 625 clusters, and each cluster was used individually to train its own CNN to solve the 16 classes classification problem. Inherent regularization for the assumption of binary materials enabled us to use a classification algorithm with CNN. The iterative TV regularization algorithm achieved a close state of the two-phase material reconstruction by its sparsity-based assumption. The supervised learning algorithm established the mathematical model that mapped the simulated resistance measurement to the pixel patterns of the clusters. The training process was carried out only using simulated measurement data, but simulated and experimental tests were both conducted to investigate the feasibility of applying a multi-layer CNN for CCERT imaging. The performance of the CNN algorithm on the simulated data is demonstrated, and the comparison between the results created by the TV-based algorithm and the proposed CNN algorithm with the real-world data is also provided.

show abstract

Section: Conventional Forward Modeling and Image Reconstruction Algorithm Of Ccertmentioning

confidence: 99%

Application of Deep Neural Network to the Reconstruction of Two-Phase Material Imaging by Capacitively Coupled Electrical Resistance Tomography

Chen

Jiang

et al. 2021

Electronics

View full text Add to dashboard Cite

show abstract

“…If the conductivity distribution between the transmitter and receiver coils is changed, then the induced voltage at the sensing coils will be perturbed. By observing this perturbation, tomographic system will be established after solving the forward and inverse problems [15].…”

Section: Measurement System In Mitmentioning

confidence: 99%

Feasible Magnetic Induction Tomography for Determining Parkinson’s Disease by Biomarker Imaging

Hussaini,

Subash CB,

MK Md

et al. 2023

J Brain Disord

View full text Add to dashboard Cite

In order to support patients suffering from Parkinson's disease caused by irregular aggregation of alpha-synuclein in the brain, an economically affordable and diagnostically effective modality such as magnetic induction tomographyis proposed to differentiate normal and Parkinson's disease brain tissues based on imaging. MIT technology has been applied in various medical fields due to its advancement in the diagnosis of diseases. It is sensitive to conductivity, permittivity, and permeability of biological tissue. This work focuses on the virtual simulation by COMSOL Multi-physics for the design and development of non-invasive and contactless MIT system that emphasized on 16 channels for Parkinson's disease detection using primary coils to induce electromagnetic fields in the brain tissue and measured the signals at the receivers. The new horizon can be reached by developing tracers that specifically bind alphasynucleinat different places in the brain (cerebellum and hypothalamus). The simulation model comprises sixteen sensor coils, one act as a transmitter and others are receivers at one period with total of 240 data readings generated. The readings of the receivers and 240 data obtained based on sensitivity of matrices calculation are used for the reconstruction of the images of the non-aggregated and aggregated alpha-synuclein using a linear back projection algorithm.

show abstract

An Improved Conjugate Gradient Image Reconstruction Algorithm for Electromagnetic Tomography

Liu

Wang

2022

Sens Imaging

View full text Add to dashboard Cite

Planar array magnetic induction tomography further improvement

Cited by 4 publications

References 25 publications

Application of Deep Neural Network to the Reconstruction of Two-Phase Material Imaging by Capacitively Coupled Electrical Resistance Tomography

Application of Deep Neural Network to the Reconstruction of Two-Phase Material Imaging by Capacitively Coupled Electrical Resistance Tomography

Feasible Magnetic Induction Tomography for Determining Parkinson’s Disease by Biomarker Imaging

An Improved Conjugate Gradient Image Reconstruction Algorithm for Electromagnetic Tomography

Contact Info

Product

Resources

About