Electrical impedance tomography (EIT) is a noninvasive imaging technique that reconstructs the internal conductivity distribution of an object by measuring electric potentials on its surface. Mathematically, EIT is twofold: the forward problem solves a generalized Laplace equation with conductivity coefficients to determine the electric potential, while the inverse problem requires estimating conductivity from noisy and incomplete boundary measurements—an ill-posed task highly sensitive to noise. This paper proposed a hybrid deep learning–evolutionary framework for EIT image reconstruction. The fully-connected feedforward neural networks (FNNs) and convolutional neural networks (CNNs) were trained to approximate the forward map from conductivity to electric potential, eliminating the need for repeated finite element simulations during inversion. For the inverse problem, we formulate the recovery of conductivity distributions as a global optimization task using differential evolution and its variants. Among them, success-history based adaptive differential evolution (SHADE) achieved the most accurate and robust results. While the proposed CNN-SHADE algorithm demonstrated competitive reconstruction performance, the FNN-SHADE approach provided a favorable trade-off between accuracy and computational efficiency. Furthermore, the FNN-SHADE framework outperformed the traditional finite element-based method in computational speed, while maintaining accuracy. By embedding a neural forward operator into the differential evolution loop, the framework offered a scalable, data-driven alternative to traditional EIT reconstruction methods.
Citation: Margaret Esther C. Cruz, Renier G. Mendoza, Rhudaina Z. Mohammad. Image reconstruction in electrical impedance tomography using deep neural networks with differential evolution[J]. Electronic Research Archive, 2025, 33(12): 7637-7675. doi: 10.3934/era.2025338
Electrical impedance tomography (EIT) is a noninvasive imaging technique that reconstructs the internal conductivity distribution of an object by measuring electric potentials on its surface. Mathematically, EIT is twofold: the forward problem solves a generalized Laplace equation with conductivity coefficients to determine the electric potential, while the inverse problem requires estimating conductivity from noisy and incomplete boundary measurements—an ill-posed task highly sensitive to noise. This paper proposed a hybrid deep learning–evolutionary framework for EIT image reconstruction. The fully-connected feedforward neural networks (FNNs) and convolutional neural networks (CNNs) were trained to approximate the forward map from conductivity to electric potential, eliminating the need for repeated finite element simulations during inversion. For the inverse problem, we formulate the recovery of conductivity distributions as a global optimization task using differential evolution and its variants. Among them, success-history based adaptive differential evolution (SHADE) achieved the most accurate and robust results. While the proposed CNN-SHADE algorithm demonstrated competitive reconstruction performance, the FNN-SHADE approach provided a favorable trade-off between accuracy and computational efficiency. Furthermore, the FNN-SHADE framework outperformed the traditional finite element-based method in computational speed, while maintaining accuracy. By embedding a neural forward operator into the differential evolution loop, the framework offered a scalable, data-driven alternative to traditional EIT reconstruction methods.
| [1] | T. K. Bera, Applications of electrical impedance tomography (EIT): A short review, in 3rd International Conference on Communication Systems (ICCS-2017), (2017), 14–16. https://doi.org/10.1088/1757-899X/331/1/012004 |
| [2] |
S. Mansouri, S. Chabchoub, Y. Alharbi, A. Alshrouf, EIT 40-electrodes breast cancer detection and screening, IEEJ Trans. Electr. Electron. Eng., 17 (2022), 1141–1147. https://doi.org/10.1002/tee.23605 doi: 10.1002/tee.23605
|
| [3] |
W. Kuk, N. Wright, Bedside diagnosis of pulmonary embolism using electrical impedance tomography: A case report, A & A Pract., 16 (2022), e01606. https://doi.org/10.1213/XAA.0000000000001606 doi: 10.1213/XAA.0000000000001606
|
| [4] |
M. Kamiński, P. Zientara, M. Krawczyk, Electrical resistivity tomography and digital aerial photogrammetry in the research of the "Bachledzki Hill" active landslide – in Podhale (Poland), Eng. Geol., 285 (2021), 106004. https://doi.org/10.1016/j.enggeo.2021.106004 doi: 10.1016/j.enggeo.2021.106004
|
| [5] | A. A. Konaté, O. B. Kaba, M. S. M. Conté, M. Zaheer, B. M. Thiam, F. Oularé, et al., Use of electrical resistivity tomography (ERT) for detecting underground voids on electrical pylon installation sites: Case studies from Labé Prefecture, Republic of Guinea, in Proceedings of the 9th International Conference on Civil Engineering (ICCE), Springer, (2023), 611–620. https://doi.org/10.1007/978-981-99-2532-2_51 |
| [6] |
A. J. Thomas, J. J. Kim, T. N. Tallman, C. E. Bakis, Damage detection in self-sensing composite tubes via electrical impedance tomography, Composites, Part B, 177 (2019), 107276. https://doi.org/10.1016/j.compositesb.2019.107276 doi: 10.1016/j.compositesb.2019.107276
|
| [7] |
G. Rao, S. Aghajanian, Y. Zhang, L. Jackowska-Strumiłło, T. Koiranen, M. Fjeld, Monitoring and visualization of crystallization processes using electrical resistance tomography: CaCO3 and sucrose crystallization case studies, Sensors, 22 (2022), 4431. https://doi.org/10.3390/s22124431 doi: 10.3390/s22124431
|
| [8] |
M. Cheney, D. Isaacson, J. C. Newell, Electrical impedance tomography, SIAM Rev., 41 (1999), 85–101. https://doi.org/10.1137/S0036144598333613 doi: 10.1137/S0036144598333613
|
| [9] |
L. Borcea, Electrical impedance tomography, Inverse Probl., 18 (2002), R99. http://doi.org/10.1088/0266-5611/18/6/201 doi: 10.1088/0266-5611/18/6/201
|
| [10] | S. J. Hamilton, S. Siltanen, Nonlinear inversion from partial EIT data: Computational experiments, Contemp. Math., 615 (2014), 105–129. |
| [11] |
G. Alessandrini, Stable determination of conductivity by boundary measurements, Appl. Anal., 27 (1988), 153–172. https://doi.org/10.1080/00036818808839730 doi: 10.1080/00036818808839730
|
| [12] |
E. J. Woo, P. Hua, J. G. Webster, W. J. Tompkins, Finite-element method in electrical impedance tomography, Med. Biol. Eng. Comput., 32 (1994), 530–536. https://doi.org/10.1007/BF02515311 doi: 10.1007/BF02515311
|
| [13] | H. Jo, K. Josić, J. K. Kim, Neural network-based parameter estimation for non-autonomous differential equations with discontinuous signals, preprint, arXiv: 2507.06267. |
| [14] | T. Huuhtanen, A. Jung, Anomaly location detection with electrical impedance tomography using multilayer perceptrons, in 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing (MLSP), IEEE, (2020), 1–6. https://doi.org/10.1109/MLSP49062.2020.9231818 |
| [15] |
X. Li, R. Lu, Q. Wang, J. Wang, X. Duan, Y. Sun, et al., One-dimensional convolutional neural network (1D-CNN) image reconstruction for electrical impedance tomography, Rev. Sci. Instrum., 91 (2020), 124704. https://doi.org/10.1063/5.0025881 doi: 10.1063/5.0025881
|
| [16] | R. Storn, K. Price, Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim., 11 (1997), 341–359. https://doi.org/10.1023/A: 1008202821328 |
| [17] | A. A. Kawam, N. Mansour, Metaheuristic optimization algorithms for training artificial neural networks, Int. J. Comput. Inf. Technol., 1 (2012), 156–161. |
| [18] |
L. M. R. Rere, M. I. Fanany, A. M. Arymurthy, Metaheuristic algorithms for convolution neural network, Comput. Intell. Neurosci., 2016 (2016), 1537325. https://doi.org/10.1155/2016/1537325 doi: 10.1155/2016/1537325
|
| [19] | D. Karaboğa, S. Ökdem, A simple and global optimization algorithm for engineering problems: Differential evolution algorithm, Turk. J. Electr. Eng. Comput. Sci., 12 (2004), 53–60. |
| [20] |
A. P. Piotrowski, J. J. Napiorkowski, A. E. Piotrowska, Particle swarm optimization or differential evolution – a comparison, Eng. Appl. Artif. Intell., 121 (2023), 106008. https://doi.org/10.1016/j.engappai.2023.106008 doi: 10.1016/j.engappai.2023.106008
|
| [21] | R. R. Ribeiro, A. R. S. Feitosa, R. E. de Souza, W. P. dos Santos, A modified differential evolution algorithm for the reconstruction of electrical impedance tomography images, in 5th ISSNIP-IEEE Biosignals and Biorobotics Conference (2014): Biosignals and Robotics for Better and Safer Living (BRC), IEEE, (2014), 1–6. https://doi.org/10.1109/BRC.2014.6880982 |
| [22] | R. H. Tan, C. Rossa, Electrical impedance tomography using differential evolution integrated with a modified Newton Raphson algorithm, in 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), IEEE, (2020), 2528–2534. https://doi.org/10.1109/SMC42975.2020.9282957 |
| [23] | P. Wang, L. L. Xie, Y. C. Sun, Application of PSO algorithm and RBF neural network in electrical impedance tomography, in 2009 9th International Conference on Electronic Measurement & Instruments (ICEMI), IEEE, (2009), 2-517–2-521. https://doi.org/10.1109/ICEMI.2009.5274525 |
| [24] | P. Wang, L. L. Xie, Y. C. Sun, Electrical impedance tomography based on BP neural network and improved PSO, in 2009 International Conference on Machine Learning and Cybernetics (ICMLC), IEEE, (2009), 1059–1064. https://doi.org/10.1109/ICMLC.2009.5212387 |
| [25] |
S. Martin, C. T. M. Choi, Nonlinear electrical impedance tomography reconstruction using artificial neural networks and particle swarm optimization, IEEE Trans. Magn., 52 (2015), 1–4. https://doi.org/10.1109/TMAG.2015.2488901 doi: 10.1109/TMAG.2015.2488901
|
| [26] |
H. Wang, K. Liu, Y. Wu, S. Wang, Z. Zhang, F. Li, et al., Image reconstruction for electrical impedance tomography using radial basis function neural network based on hybrid particle swarm optimization algorithm, IEEE Sens. J., 21 (2020), 1926–1934. https://doi.org/10.1109/JSEN.2020.3019309 doi: 10.1109/JSEN.2020.3019309
|
| [27] |
A. P. Bagshaw, A. D. Liston, R. H. Bayford, A. Tizzard, A. P. Gibson, A. T. Tidswell, et al., Electrical impedance tomography of human brain function using reconstruction algorithms based on the finite element method, NeuroImage, 20 (2003), 752–764. https://doi.org/10.1016/S1053-8119(03)00301-X doi: 10.1016/S1053-8119(03)00301-X
|
| [28] |
T. Murai, Y. Kagawa, Electrical impedance computed tomography based on a finite element model, IEEE Trans. Biomed. Eng., BME-32 (1985), 177–184. https://doi.org/10.1109/TBME.1985.325526 doi: 10.1109/TBME.1985.325526
|
| [29] | A. P. Calderón, On an inverse boundary value problem, Comput. Appl. Math., 25 (2006), 133–138. |
| [30] |
R. Mendoza, S. Keeling, A two-phase segmentation approach to the impedance tomography problem, Inverse Probl., 33 (2017), 015001. https://doi.org/10.1088/0266-5611/33/1/015001 doi: 10.1088/0266-5611/33/1/015001
|
| [31] | A. C. Velasco, M. Darbas, R. Mendoza, M. Bacon, J. C. de Leon, Comparative study of heuristic algorithms for electrical impedance tomography, Philipp J. Sci., 149 (2020), 747–772. |
| [32] |
K. Astala, L. Päivärinta, Calderón's inverse conductivity problem in the plane, Ann. Math., 163 (2006), 265–299. https://doi.org/10.4007/annals.2006.163.265 doi: 10.4007/annals.2006.163.265
|
| [33] | Dask Development Team, Dask: Library for dynamic task scheduling, 2016. Available from: http://dask.pydata.org. |
| [34] | F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, et al., Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12 (2011), 2825–2830. |
| [35] |
D. P. Leins, C. Gibas, R. Brück, R. Haschke, Toward more robust hand gesture recognition on EIT data, Front. Neurorobot., 15 (2021), 659311. https://doi.org/10.3389/fnbot.2021.659311 doi: 10.3389/fnbot.2021.659311
|
| [36] | O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, (2015), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [37] | A. Wirgin, The inverse crime, preprint, arXiv: math-ph/0401050. |
| [38] | A. K. Qin, P. N. Suganthan, Self-adaptive differential evolution algorithm for numerical optimization, in 2005 IEEE Congress on Evolutionary Computation (CEC), IEEE, (2005), 1785–1791. https://doi.org/10.1109/CEC.2005.1554904 |
| [39] |
J. Zhang, A. C. Sanderson, JADE: Adaptive differential evolution with optional external archive, IEEE Trans. Evol. Comput., 13 (2009), 945–958. https://doi.org/10.1109/TEVC.2009.2014613 doi: 10.1109/TEVC.2009.2014613
|
| [40] | R. Tanabe, A. Fukunaga, Success-history based parameter adaptation for differential evolution, in 2013 IEEE Congress on Evolutionary Computation (CEC), IEEE, (2013), 71–78. https://doi.org/10.1109/CEC.2013.6557555 |
| [41] |
J. Teo, Exploring dynamic self-adaptive populations in differential evolution, Soft Comput., 10 (2006), 673–686. https://doi.org/10.1007/s00500-005-0537-1 doi: 10.1007/s00500-005-0537-1
|
| [42] |
J. K. Pattanaik, M. Basu, D. P. Dash, Dynamic economic dispatch: A comparative study for differential evolution, particle swarm optimization, evolutionary programming, genetic algorithm, and simulated annealing, J. Electr. Syst. Inf. Technol., 6 (2019), 1. https://doi.org/10.1186/s43067-019-0001-4 doi: 10.1186/s43067-019-0001-4
|
| [43] |
C. Dimas, V. Alimisis, N. Uzunoglu, P. P. Sotiriadis, Advances in electrical impedance tomography inverse problem solution methods: From traditional regularization to deep learning, IEEE Access, 12 (2024), 47797–47829. https://doi.org/10.1109/ACCESS.2024.3382939 doi: 10.1109/ACCESS.2024.3382939
|
| [44] |
M. Cheney, D. Isaacson, J. C. Newell, S. Simske, J. Goble, NOSER: An algorithm for solving the inverse conductivity problem, Int. J. Imaging Syst. Technol., 2 (1990), 66–75. https://doi.org/10.1002/ima.1850020203 doi: 10.1002/ima.1850020203
|
| [45] |
B. Sun, S. Yue, Z. Hao, Z. Cui, H. Wang, An improved Tikhonov regularization method for lung cancer monitoring using electrical impedance tomography, IEEE Sens. J., 19 (2019), 3049–3057. https://doi.org/10.1109/JSEN.2019.2892179 doi: 10.1109/JSEN.2019.2892179
|
| [46] |
S. Li, H. Wang, T. Liu, Z. Cui, J. N. Chen, Z. Xia, et al., A fast Tikhonov regularization method based on homotopic mapping for electrical resistance tomography, Rev. Sci. Instrum., 93 (2022), 043709. https://doi.org/10.1063/5.0077483 doi: 10.1063/5.0077483
|
| [47] |
Y. Shi, J. Liao, M. Wang, Y. Li, F. Fu, M. Soleimani, Total fractional-order variation regularization based image reconstruction method for capacitively coupled electrical resistance tomography, Flow Meas. Instrum., 82 (2021), 102081. https://doi.org/10.1016/j.flowmeasinst.2021.102081 doi: 10.1016/j.flowmeasinst.2021.102081
|
| [48] |
W. Zhang, C. Tan, Y. Xu, F. Dong, Electrical resistance tomography image reconstruction based on modified OMP algorithm, IEEE Sens. J., 19 (2019), 5723–5731. https://doi.org/10.1109/JSEN.2019.2906264 doi: 10.1109/JSEN.2019.2906264
|
| [49] |
A. Beck, M. Teboulle, A fast iterative shrinkage-thresholding algorithm for linear inverse problems, SIAM J. Imaging Sci., 2 (2009), 183–202. https://doi.org/10.1137/080716542 doi: 10.1137/080716542
|
| [50] |
D. Liu, V. Kolehmainen, S. Siltanen, A. Laukkanen, A. Ursin, Estimation of conductivity changes in a region of interest with electrical impedance tomography, Inverse Probl. Imaging, 9 (2015), 211–229. https://doi.org/ 10.3934/ipi.2015.9.211 doi: 10.3934/ipi.2015.9.211
|
| [51] |
B. Liu, B. Yang, C. Xu, J. Xia, M. Dai, Z. Ji, et al., pyEIT: A python based framework for electrical impedance tomography, SoftwareX, 7 (2018), 304–308. https://doi.org/10.1016/j.softx.2018.09.005 doi: 10.1016/j.softx.2018.09.005
|
| [52] |
K. Knudsen, M. Lassas, J. L. Mueller, S. Siltanen, Regularized D-bar method for the inverse conductivity problem, Inverse Probl. Imaging, 35 (2009), 599–624. https://doi.org/10.3934/ipi.2009.3.599 doi: 10.3934/ipi.2009.3.599
|
| [53] |
J. L. Mueller, S. Siltanen, The D-bar method for electrical impedance tomography—demystified, Inverse Probl., 36 (2020), 093001. https://doi.org/10.1088/1361-6420/aba2f5 doi: 10.1088/1361-6420/aba2f5
|
| [54] |
E. T. Chung, T. F. Chan, X. C. Tai, Electrical impedance tomography using level set representation and total variational regularization, J. Comput. Phys., 205 (2005), 357–372. https://doi.org/10.1016/j.jcp.2004.11.022 doi: 10.1016/j.jcp.2004.11.022
|
| [55] |
M. Soleimani, W. R. B. Lionheart, O. Dorn, Level set reconstruction of conductivity and permittivity from boundary electrical measurements using experimental data, Inverse Probl. Sci. Eng., 14 (2006), 193–210. https://doi.org/10.1080/17415970500264152 doi: 10.1080/17415970500264152
|
| [56] |
L. Zhou, B. Harrach, J. K. Seo, Monotonicity-based electrical impedance tomography for lung imaging, Inverse Probl., 34 (2018), 045005. https://doi.org/10.1088/1361-6420/aaaf84 doi: 10.1088/1361-6420/aaaf84
|
| [57] |
A. C. Carcavilla, M. Meribout, Algorithms on electrical impedance tomography, focusing on deep learning architectures and their implementations: A review, IEEE Sens. J., 25 (2025), 34252–34274. https://doi.org/10.1109/JSEN.2025.3589157 doi: 10.1109/JSEN.2025.3589157
|
| [58] |
N. Van Thieu, S. Mirjalili, MEALPY: An open-source library for latest meta-heuristic algorithms in Python, J. Syst. Archit., 139 (2023), 102871. https://doi.org/10.1016/j.sysarc.2023.102871 doi: 10.1016/j.sysarc.2023.102871
|
Figures(18) / Tables(11)
Margaret Esther C. Cruz, Renier G. Mendoza, Rhudaina Z. Mohammad. Image reconstruction in electrical impedance tomography using deep neural networks with differential evolution[J]. Electronic Research Archive, 2025, 33(12): 7637-7675. doi: 10.3934/era.2025338
DownLoad: