Abstract
Electrical impedance tomography is a modern biomedical imaging method. Its goal is to image the electrical properties of human tissues. This approach is safe for the patient’s health, is non-invasive and has no known hazards. However, the approach suffers from low accuracy. Linear inverse solvers are commonly used in medical applications, as they are strongly robust to noise. However, linear methods can give only an approximation of the solution that corresponds to a linear perturbation from an initial estimate. This paper proposes a novel reconstruction process. After applying a linear solver, the conductivity distribution is post-processed with a nonlinear algorithm, with the aim of reproducing the abrupt change in conductivity at the boundaries between tissues or organs. The results are used to compare the proposed method with three other widely used methods. The proposed method offers higher quality images and a higher robustness to noise, and significantly reduces the error associated with image reconstruction.
Highlights
An EIT inverse problem is highly nonlinear and very ill-posed[5], and the solution is not trivial and usually requires a certain conductivity distribution[6] as an initial estimate of the solution
EIT image reconstruction was performed with four different methods: the linear one-step GN, the iterative primal dual interior point method (PDIPM) solver, an Artificial neural networks (ANNs) used as an inverse solver and the proposed post-processing method
Simulation data do not show significant amelioration between the existing methods based on the ANN and novel method presented in this paper, phantom and lung data clearly show the advantages of the new method, especially its ability to produce high quality images from a noisy environment
Summary
An EIT inverse problem is highly nonlinear and very ill-posed[5], and the solution is not trivial and usually requires a certain conductivity distribution[6] as an initial estimate of the solution. The conductivity distribution is approximated as a small perturbation from an initial estimate[13]. By assuming an initial conductivity distribution, such as by using a regularisation method or prior distribution, a satisfactory solution to the inverse problem can be better approximated by the reconstruction algorithm. The main weakness of ANNs is their inability to extrapolate and estimate solutions from previously unseen data The latter is the major drawback of using an ANN to solve the EIT inverse problem in a biomedical environment. The linear algorithms are known to be extremely robust to noise, and the resulting conductivity distribution is not strongly influenced by the modelling errors compared with the measured voltages. The results show that the proposed method is efficient, stable and rapid
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
