Browsing by Author "Martin, Sebastien"

Now showing 1 - 9 of 9

A Mesh-Refinement Method Based on Artificial Neural Networks for Electrical Impedance Tomography
(2016-01-01)
Martin, Sebastien
;
Choi, Charles T. M.
;
交大名義發表
;
National Chiao Tung University
Inverse boundary problem are usually solved with a finite element model, with either limited accuracy or huge computation resources. Using a fine mesh results in a computationally demanding task, but when the region of interest is known, when one can easily locally refine the model, aiming for greater local accuracy. In this paper, a novel approach uses artificial neural network to estimate the location of the region of interest and refine this region before solving the inverse problem. The idea is illustrated by solving the electrical impedance tomography inverse problem. Result shows that the proposed method increases the accuracy without significantly affecting the computation resources necessary to solve the inverse problem.
A New Divide-and-Conquer Method for 3-D Electrical Impedance Tomography
(2018-03-01)
Martin, Sebastien
;
Choi, Charles T. M.
;
分子醫學與生物工程研究所
;
電機工程學系
;
Institute of Molecular Medicine and Bioengineering
Electrical impedance tomography (EIT) is a patient-safe approach for imaging applications and is a promising technology for biomedical imaging. By applying a small electrical current to living tissue and measuring the electrical potential at different points of the tissue's boundary, it is possible to solve the inverse problem and to generate a map of the tissue's conductivities. Although it is a promising method, the reconstruction process remains a complicated task, and real-time nonlinear image reconstruction algorithms have not yet been widely adopted. Recent studies have proposed the use of artificial neural networks (ANN) to solve the EIT inverse problem. ANNs can give a nonlinear conductivity distribution. Although several studies have examined 2-D finite-element models, very little work has been done on 3-D problems. In this paper, a solution based on the divide-and-conquer method and ANNs is used to solve the nonlinear inverse problem without any linearization. The solution presented here reduces the difficulty of training large ANNs, which are commonly required to solve a 3-D EIT problem with artificial intelligence algorithms.
A novel post-processing scheme for two-dimensional electrical impedance tomography based on artificial neural networks
(2017-12-05)
Martin, Sebastien
;
Choi, Charles T. M.
;
分子醫學與生物工程研究所
;
資訊工程學系
;
電機工程學系
Objective Electrical Impedance Tomography (EIT) is a powerful non-invasive technique for imaging applications. The goal is to estimate the electrical properties of living tissues by measuring the potential at the boundary of the domain. Being safe with respect to patient health, non-invasive, and having no known hazards, EIT is an attractive and promising technology. However, it suffers from a particular technical difficulty, which consists of solving a nonlinear inverse problem in real time. Several nonlinear approaches have been proposed as a replacement for the linear solver, but in practice very few are capable of stable, high-quality, and real-time EIT imaging because of their very low robustness to errors and inaccurate modeling, or because they require considerable computational effort. Methods In this paper, a post-processing technique based on an artificial neural network (ANN) is proposed to obtain a nonlinear solution to the inverse problem, starting from a linear solution. While common reconstruction methods based on ANNs estimate the solution directly from the measured data, the method proposed here enhances the solution obtained from a linear solver. Conclusion Applying a linear reconstruction algorithm before applying an ANN reduces the effects of noise and modeling errors. Hence, this approach significantly reduces the error associated with solving 2D inverse problems using machine-learning-based algorithms.
A Post-Processing Method for Three-Dimensional Electrical Impedance Tomography
(2017-08-03)
Martin, Sebastien
;
Choi, Charles T. M.
;
分子醫學與生物工程研究所
;
電機工程學系
;
Institute of Molecular Medicine and Bioengineering
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.
Electrical Impedance Tomography: A Reconstruction Method Based on Neural Networks and Particle Swarm Optimization
(2015-01-01)
Martin, Sebastien
;
Choi, Charles T. M.
;
交大名義發表
;
National Chiao Tung University
Electrical Impedance Tomography (EIT) is a non-invasive image reconstruction technique. Typically, an EIT scheme involves the solution to an inverse problem, which usually gives a poor resolution, due to linearization and ill-posedness of the problem. An alternative approach based on Artificial Neural Networks (ANN) has been used as a replacement of the inverse problem, giving correct results without linearizing the problem. However, training an ANN may be time consuming and usually requires a large amount of iterations before achieving a correct answer to the input stimulation. Several studies focused on training ANNs, and Evolutionary Algorithms (EA) gives a faster global convergence. In this paper, a novel approach based on Artificial Neural Networks and Particle Swarm Optimization (PSO) is proposed to improve the training process. A training method based on PSO algorithm achieves a faster global convergence.
Fast and Accurate Solution of the Inverse Problem for Image Reconstruction Using Electrical Impedance Tomography
(2019-06-01)
Martin, Sebastien
;
Choi, Charles T. M.
;
分子醫學與生物工程研究所
;
電機工程學系
;
電控工程研究所
The goal in electrical impedance tomography is to obtain the electrical properties of different materials by applying an electrical current and measuring the resulting potential difference at the boundaries of the domain. While the numerical accuracy is technically limited by the size of the elements within the finite-element (FE) mesh, using a fine mesh will result in a computationally demanding reconstruction, especially when the region of interest (ROI) is not known. However, this situation is different when the location is known, when one can easily refine the FE model around the target, aiming for greater accuracy around the ROI. In this paper, an innovative approach estimates the location of the target object before solving the inverse problem, so that it becomes possible to refine only a specific area of the FE model. A powerful artificial intelligence method is used to obtain this region.
Nonlinear Electrical Impedance Tomography Reconstruction Using Artificial Neural Networks and Particle Swarm Optimization
(2016-03)
Martin, Sebastien
;
Choi, Charles T. M.
;
分子醫學與生物工程研究所
;
電機學院
;
Institute of Molecular Medicine and Bioengineering
Electrical impedance tomography (EIT) is an imaging technology that offers the advantages of being noninvasive, and it does not generate ionizing radiation. The main difficulty in applying EIT is to solve an ill-posed nonlinear inverse problem. Given a set of electrical voltages measured at the surface of a volume conductor, the goal is to identify the materials that are present in the domain by determining their electrical conductivities. However, since EIT is a nonlinear problem, various algorithms proposed in the literature can only approximate real conductivity distributions. Nonlinear algorithms, especially artificial neural networks (ANNs), have been proposed to solve this inverse problem, but these algorithms are usually limited by slow convergence issues during the training phase. In this paper, the particle swarm optimization (PSO) method is used to train an ANN to solve the EIT problem. It has been found that, compared with the back-propagation algorithm, PSO is capable of generating both faster and higher convergence. This paper also shows that the proposed method is capable of dealing with noisy data and the imperfections in the finite-element discretization, an important source of errors in EIT imaging.
On the influence of spread constant in radial basis networks for electrical impedance tomography
(2016-06-01)
Martin, Sebastien
;
Choi, Charles T. M.
;
交大名義發表
;
National Chiao Tung University
Electrical impedance tomography (EIT) is a non-invasive imaging technique. The main task of this work is to solve a non-linear inverse problem, for which several techniques have been suggested, but none of which gives a very high degree of accuracy. This paper introduces a novel approach, based on radial basis function (RBF) artificial neural networks (ANNs), to solve this problem, and uses several ANNs to obtain the best solution to the EIT inverse problem. ANNs have the potential to directly estimate the solution of the inverse problem with a high degree of accuracy. While different radial basis neural networks do not always perform well on different problems, they usually give good results on some specific problems. This paper evidences a strong correlation between the area of the target and the spread constant of the RBF network that gives the best reconstruction. A solution to automatically estimate the size of the target and pick the best neural network directly from voltage measurements is presented, making the reconstruction process automatic. By automatically selecting the best ANN for each specific set of voltage measurements, the proposed solution gives a more accurate reconstruction of both small and large targets.
On the influence of spread constant in radial basis networks for electrical impedance tomography
(2016-06)
Martin, Sebastien
;
Choi, Charles T. M.
;
交大名義發表
;
National Chiao Tung University
Electrical impedance tomography (EIT) is a non-invasive imaging technique. The main task of this work is to solve a non-linear inverse problem, for which several techniques have been suggested, but none of which gives a very high degree of accuracy. This paper introduces a novel approach, based on radial basis function (RBF) artificial neural networks (ANNs), to solve this problem, and uses several ANNs to obtain the best solution to the EIT inverse problem. ANNs have the potential to directly estimate the solution of the inverse problem with a high degree of accuracy. While different radial basis neural networks do not always perform well on different problems, they usually give good results on some specific problems. This paper evidences a strong correlation between the area of the target and the spread constant of the RBF network that gives the best reconstruction. A solution to automatically estimate the size of the target and pick the best neural network directly from voltage measurements is presented, making the reconstruction process automatic. By automatically selecting the best ANN for each specific set of voltage measurements, the proposed solution gives a more accurate reconstruction of both small and large targets.