2018
DOI: 10.1109/tmi.2017.2762741
|View full text |Cite
|
Sign up to set email alerts
|

A Fidelity-Embedded Regularization Method for Robust Electrical Impedance Tomography

Abstract: Electrical impedance tomography (EIT) provides functional images of an electrical conductivity distribution inside the human body. Since the 1980s, many potential clinical applications have arisen using inexpensive portable EIT devices. EIT acquires multiple trans-impedance measurements across the body from an array of surface electrodes around a chosen imaging slice. The conductivity image reconstruction from the measured data is a fundamentally ill-posed inverse problem notoriously vulnerable to measurement … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
44
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
9

Relationship

4
5

Authors

Journals

citations
Cited by 48 publications
(44 citation statements)
references
References 43 publications
0
44
0
Order By: Relevance
“…2(f)). The time-series images were reconstructed, by fidelity-embedded regularization (FER) algorithm, after fitting U UA to the original data size 18 . The conductivity change signal was computed as a sum of pixels then the upper airway closure signal (UA_closure) was expressed as the psercentage of conductivity changes.…”
Section: Methodsmentioning
confidence: 99%
“…2(f)). The time-series images were reconstructed, by fidelity-embedded regularization (FER) algorithm, after fitting U UA to the original data size 18 . The conductivity change signal was computed as a sum of pixels then the upper airway closure signal (UA_closure) was expressed as the psercentage of conductivity changes.…”
Section: Methodsmentioning
confidence: 99%
“…To this end, we preprocess the voltage measurements as in [39]. We extract the boundary error, denoted byV err , by using the boundary sensitive Jacobian matrix S bdry :V…”
Section: A Manifold Learning Based Image Reconstruction Methodmentioning
confidence: 99%
“…Before closing this introduction section, we should mention that our method does not use ground-truth labeled data for training, because lung EIT lacks a known ground truth at present. Although we have collected many human experiment data using 16 channel EIT system [39], its ground truthiness is not clear from a clinical point of view. Phantom experimental results cannot be used for ground-truth data, which are far from realistic.…”
mentioning
confidence: 99%
“…Linear methods usually linearize the forward model and reconstruct the conductivity changes between different time points. See [9,4,64,68,44,39,43] for some related work. Nonlinear methods can be further classified into two categories: iterative and direct (noniterative) methods.…”
mentioning
confidence: 99%