Shape-Driven EIT Reconstruction Using Fourier Representations

Liu, Dong; Gu, Danping; Smyl, Danny; Khambampati, Anil Kumar; Deng, Jiansong; Du, Jiangfeng

doi:10.1109/tmi.2020.3030024

Cited by 22 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Herein we demonstrate the proposed NN-QN method using Electrical Impedance Tomography (EIT) [34], [35], a nonlinear inverse problem aiming to estimate the conductivity σ provided voltage data g. Due to notational convention we write σ instead of f for the unknown. The resultant observation model for EIT is then written as g = A(σ) + δg where δg is a noise term and A(σ) is the nonlinear forward model characterized by the Complete Electrode Model [36], [37] and solved using finite elements.…”

Section: A Electrical Impedance Tomographymentioning

confidence: 99%

An Efficient Quasi-Newton Method for Nonlinear Inverse Problems via Learned Singular Values

Smyl

Tallman

Liu

et al. 2021

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

Solving complex optimization problems in engineering and the physical sciences requires repetitive computation of multi-dimensional function derivatives, which commonly require computationally-demanding numerical differentiation such as perturbation techniques. In particular, Gauss-Newton methods are used for nonlinear inverse problems that require iterative updates to be computed from the Jacobian and allow for flexible incorporation of prior knowledge. Computationally more efficient alternatives are Quasi-Newton methods, where the repeated computation of the Jacobian is replaced by an approximate update, but unfortunately are often too restrictive for highly ill-posed problems. To overcome this limitation, we present a highly efficient data-driven Quasi-Newton method applicable to nonlinear inverse problems, by using the singular value decomposition and learning a mapping from model outputs to the singular values to compute the updated Jacobian. Enabling time-critical applications and allowing for flexible incorporation of prior knowledge necessary to solve ill-posed problems. We present results for the highly non-linear inverse problem of electrical impedance tomography with experimental data.

show abstract

Section: A Electrical Impedance Tomographymentioning

confidence: 99%

An Efficient Quasi-Newton Method for Nonlinear Inverse Problems via Learned Singular Values

Smyl

Tallman

Liu

et al. 2021

IEEE Signal Process. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Shape reconstruction methods 45–48 directly incorporate geometry and prior information and preserve sharp edges, reducing the computational burden of the full reconstruction problem. Postprocessing approaches to improve resolution include machine learning methods 49,50 and the total variation (TV)‐enhanced D‐bar method 51 …”

Section: Introductionmentioning

confidence: 99%

Improved resolution of D‐bar images of ventilation using a Schur complement property and an anatomical atlas

et al. 2022

View full text Add to dashboard Cite

Background: Electrical impedance tomography (EIT) is a nonionizing imaging technique for real-time imaging of ventilation of patients with respiratory distress. Cross-sectional dynamic images are formed by reconstructing the conductivity distribution from measured voltage data arising from applied alternating currents on electrodes placed circumferentially around the chest. Since the conductivity of lung tissue depends on air content, blood flow, and the presence of pathology, the dynamic images provide regional information about ventilation, pulsatile perfusion, and abnormalities. However, due to the ill-posedness of the inverse conductivity problem, EIT images have a coarse spatial resolution. One method of improving the resolution is to include prior information in the reconstruction. Purpose: In this work, we propose a technique in which a statistical prior built from an anatomical atlas is used to postprocess EIT reconstructions of human chest data. The effectiveness of the method is demonstrated on data from two patients with cystic fibrosis. Methods: A direct reconstruction algorithm known as the D-bar method was used to compute a two-dimensional reconstruction of the conductivity distribution in the plane of the electrodes. Reconstructions using one step in an iterative (regularized) Newton's method were also computed for comparison. An anatomical atlas consisting of 1589 synthetic EIT images computed from X-ray computed tomography (CT) scans of 74 adult male subjects was computed for use as a statistical prior. The resolution of the D-bar images was then improved by maximizing the conditional probability density function of an image that is consistent with the a priori information and the statistical model. A new method to evaluate the accuracy of the EIT images using CT scans of the imaged patient as ground truth is presented. The novel approach is tested on data from two patients with cystic fibrosis. Results and Conclusions:The D-bar images resulted in better structural similarity index measures (SSIM) and multiscale (MS) SSIM measures for both subjects using the mask or amplitude evaluation approach than the one-step (regularized) Newton's method. Further improvement was achieved using the Schur complement (SC) approach, with MS-SSIM values of 0.718 and 0.682 using SC evaluated with the mask and amplitude approach, respectively, for PatientThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

“…Assessing the performance of EIT systems [4]- [18] is a very challenging task in vivo environment. As shown in figure 1, improving the phantom design is essential for evaluating and calibrating the EIT system in vitro environment [19], [20].…”

Section: Introductionmentioning

confidence: 99%

Design Automation of a Dynamic Thorax-Like Mesh Phantom for Evaluating the Performance of Electrical Impedance Tomography System

Guo

Huang

et al. 2022

IEEE Open J. Instrum. Meas.

View full text Add to dashboard Cite

Phantoms are used to evaluate, calibrate, and compare the performance of electrical impedance tomography (EIT) systems. This paper presents a dynamic thorax-like mesh phantom, which mimics the changes in electrical conductivity distribution within a human thorax at different time frames. Furthermore, element merging and contour smoothing, electrode placement techniques, and PCB design automation methods are proposed to simplify, optimize the mesh phantom, and reduce the hardware implementation cost. To verify the accuracy of the mesh phantom and its PCB, SPICE simulations and experimental testings are performed to obtain the conductance of the mesh phantom and reconstruct the images through the EIDORS software. These images achieve an image correlation coefficient (ICC) of 0.680 (model versus SPICE simulation) and 0.9098 (SPICE simulation versus measurement result), respectively. This demonstrates the validity of our proposed dynamic thorax-like mesh phantom.

show abstract

Shape-Driven EIT Reconstruction Using Fourier Representations

Cited by 22 publications

References 48 publications

An Efficient Quasi-Newton Method for Nonlinear Inverse Problems via Learned Singular Values

An Efficient Quasi-Newton Method for Nonlinear Inverse Problems via Learned Singular Values

Improved resolution of D‐bar images of ventilation using a Schur complement property and an anatomical atlas

Design Automation of a Dynamic Thorax-Like Mesh Phantom for Evaluating the Performance of Electrical Impedance Tomography System

Contact Info

Product

Resources

About