RESEARCH PAPER
Reliable 3D EIT reconstruction for masonry condition monitoring using conditional diffusion and cascaded FEM-space refinement
1
Lublin University of Technology, Poland
2
Wrocław University of Science and Technology, Poland
3
Netrix S.A., Poland
4
WSEI University, Poland
A – Conceptualization; B – Methodology; C – Software; D – Validation; E – Formal analysis; F – Investigation; G – Resources; H – Data curation; I – Writing – original draft; J – Writing – review & editing; K – Visualization; L – Supervision; M – Project administration; N – Funding acquisition
Submission date: 2026-07-29
Final revision date: 2026-09-20
Acceptance date: 2026-10-29
Online publication date: 2026-11-13
Corresponding author
HIGHLIGHTS
- cDDPM-SFR pipeline combines conditional diffusion with cascaded FEM-space refinement
- A conditional diffusion model reconstructs global 3D conductivity patterns
- Consensus reconstruction limits acquisition-specific variation in real EIT data
KEYWORDS
inverse problemelectrical impedance tomographymasonry condition monitoringconditional diffusion modelfinite-element meshresidual refinement
TOPICS
ABSTRACT
Three-dimensional electrical impedance tomography (EIT) reconstruction of moisture-related conductivity in masonry requires preservation of both global structure and local finite-element variations. This study proposes a conditional denoising diffusion probabilistic model with cascaded FEM-space residual refiners (cDDPM-SFR). A 448-component voltage vector conditions a 3D U-Net on a 16 × 16 × 16 voxel grid, followed by three multilayer perceptron (MLP) stages producing 3050 outputs. Training used 49,000 synthetic cases and evaluation 1,000. Compared with MLP, mean squared error (MSE) decreased from 0.119 to 0.048, peak signal-to-noise ratio (PSNR) rose from 21.692 to 26.961 dB, structural similarity index (SSIM) from 0.978 to 0.992, and Pearson correlation coefficient from 0.981 to 0.992 (Holm-adjusted p < 0.001). Four field acquisitions showed correlations of 0.196–0.935 and mean median absolute deviation of 0.689. Independent dielectric profiles and the EIT surface proxy identified the same moisture-related zone near 360 cm, supporting physical plausibility.
REFERENCES (34)
1.
Proietti N, Calicchia P, Colao F, De Simone S, Di Tullio V, Luvidi L, Prestileo F, Romani M, Tatì A. Moisture Damage in Ancient Masonry: A Multidisciplinary Approach for In Situ Diagnostics. Minerals 2021; 11(4): 406. https://doi.org/10.3390/MIN110....
2.
Tallman TN, Smyl DJ. Structural health and condition monitoring via electrical impedance tomography in self-sensing materials: a review. Smart Materials and Structures 2020; 29(12): 123001. https://doi.org/10.1088/1361-6....
3.
Brazey B, Haddab Y, Zemiti N. Robust imaging using electrical impedance tomography: review of current tools. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 2022; 478(2258): 20210713. https://doi.org/10.1098/rspa.2....
4.
Dimas C, Alimisis V, Uzunoglu N, Sotiriadis PP. Advances in Electrical Impedance Tomography Inverse Problem Solution Methods: From Traditional Regularization to Deep Learning. IEEE Access 2024; 12: 47797-47829. https://doi.org/10.1109/ACCESS....
5.
Smyl D, Hallaji M, Seppänen A, Pour-Ghaz M. Quantitative electrical imaging of three-dimensional moisture flow in cement-based materials. International Journal of Heat and Mass Transfer 2016; 103: 1348-1358. https://doi.org/10.1016/J.IJHE....
6.
Hallaji M, Seppänen A, Pour-Ghaz M. Electrical resistance tomography to monitor unsaturated moisture flow in cementitious materials. Cement and Concrete Research 2015; 69: 10-18. https://doi.org/10.1016/J.CEMC....
7.
Kendzierawska W, Trochonowicz M, Szostak B. Moisture investigations in heritage structures – the influence of masonry salt content on the reliability of dielectric measurements. Budownictwo i Architektura / Civil and Architectural Engineering 2025; 24(4): 25014. https://doi.org/10.35784/BUD-A....
8.
Jurdziak L, Błażej R, Kirjanów-Błażej A, Rzeszowska A, Kostrzewa P. Improving the effectiveness of the DiagBelt+ diagnostic system - analysis of the impact of measurement parameters on the quality of signals. Eksploatacja i Niezawodność – Maintenance and Reliability 2024; 26(3): 187275. https://doi.org/10.17531/EIN/1....
9.
Kozłowski E, Antosz K, Mazurkiewicz D, Sęp J, Żabiński T. Integrating advanced measurement and signal processing for reliability decision-making. Eksploatacja i Niezawodność – Maintenance and Reliability 2021; 23(4): 777-787. https://doi.org/10.17531/EIN.2....
10.
Aghajanian S, Rao G, Ruuskanen V, Wajman R, Jackowska‐Strumillo L, Koiranen T. Real‐time fault detection and diagnosis of CaCO3 reactive crystallization process by electrical resistance tomography measurements. Sensors 2021; 21(21): 6958. https://doi.org/10.3390/S21216....
11.
Wajman R, Nowakowski J, Łukiański M, Banasiak R. Machine learning for two-phase gas-liquid flow regime evaluation based on raw 3D ECT measurement data. Bulletin of the Polish Academy of Sciences: Technical Sciences 2024; 72(1): e148842. https://doi.org/10.24425/BPAST....
12.
Tomaszewska-Wach B, Rzasa M. A correction method for wet gas flow metering using a standard orifice and slotted orifices. Sensors 2021; 21(7): 2291. https://doi.org/10.3390/S21072....
13.
Rzasa MR, Czapla-Nielacna B. Analysis of the Influence of the Vortex Shedder Shape on the Metrological Properties of the Vortex Flow Meter. Sensors 2021; 21(14): 4697. https://doi.org/10.3390/S21144....
14.
Korzeniewska E, Zawiślak R, Przybył S, Sarna P, Bilska A, Mączka M. Prototype of Data Collector from Textronic Sensors. Sensors 2023; 23(24): 9813. https://doi.org/10.3390/S23249....
15.
Pawłowski S, Plewako J, Korzeniewska E. Field Modeling of the Influence of Defects Caused by Bending of Conductive Textronic Layers on Their Electrical Conductivity. Sensors 2023; 23(3): 1487. https://doi.org/10.3390/S23031....
16.
Zhang M, Ma Y, Huang N, Ge H. Survey of EIT Image Reconstruction Algorithms. Journal of Shanghai Jiaotong University (Science) 2022; 27: 211-218. https://doi.org/10.1007/s12204....
17.
Shi Y, Zhang Y, Wang M, Lou Y, Zheng S. Reconstruction of conductivity distribution variation with Tikhonov and wavelet frame combined method for electrical impedance tomography. Transactions of the Institute of Measurement and Control 2023; 45(14): 2658-2668. https://doi.org/10.1177/014233....
18.
Chen Y, Dong F, Tan C. Space-constrained optimized Tikhonov regularization method for 3D hemorrhage reconstruction by open magnetic induction tomography. Physics in Medicine & Biology 2022; 67(22): 225012. https://doi.org/10.1088/1361-6....
19.
Li Y, Zhu Q, Liu Z. Deep Learning for Image Reconstruction in Electrical Tomography: A Review. IEEE Sensors Journal 2025; 25(9): 14522-14538. https://doi.org/10.1109/JSEN.2....
20.
Shi S, Kang R, Liatsis P. A Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction. IEEE Transactions on Instrumentation and Measurement 2025; 74: 4504816. https://doi.org/10.1109/TIM.20....
21.
Kulisz M, Kłosowski G, Rymarczyk T, Hoła A, Niderla K, Sikora J. The use of the multi-sequential LSTM in electrical tomography for masonry wall moisture detection. Measurement 2024; 234: 114860. https://doi.org/10.1016/J.MEAS....
22.
Kłosowski G, Kulisz M, Rymarczyk T, Skowron Ł, Olszewski P, Niderla K. Application of machine learning in electrical process tomography with variable frequency measurement sequences. Measurement 2025; 247: 116770. https://doi.org/10.1016/J.MEAS....
23.
Kłosowski G, Hoła A, Kulisz M, Rymarczyk T, Niderla K, Sikora J. A multi-head neural network architecture for EIT inverse problem resolution in wall moisture imaging. Measurement 2026; 283: 122107. https://doi.org/10.1016/J.MEAS....
24.
Przysucha B, Wójcik D, Rymarczyk T, Król K, Kozłowski E, Gąsior M. Analysis of Reconstruction Energy Efficiency in EIT and ECT 3D Tomography Based on Elastic Net. Energies 2023; 16(3): 1490. https://doi.org/10.3390/EN1603....
25.
Liu J, Shi F, Xiong H, Zhou Y. DiffusionEIT: Diffusion Model for Electrical Impedance Tomography. IEEE Transactions on Instrumentation and Measurement 2024; 73: 4509209. https://doi.org/10.1109/TIM.20....
26.
Zhang T, Wang Z, Wang Q. A Sensitivity Prior Generation With Conditional Diffusion Model for EIT Reconstruction. IEEE Signal Processing Letters 2025; 32: 3042-3046. https://doi.org/10.1109/LSP.20....
27.
Zhang X, Rong Z. A Data-Constrained and Physics-Guided Conditional Diffusion Model for Electrical Impedance Tomography Image Reconstruction. Sensors 2026; 26(5): 1728. https://doi.org/10.3390/S26051....
28.
Hu J, Song B, Fessler JA, Shen L. Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems. arXiv preprint 2024; https://arxiv.org/abs/2410.117....
29.
Herzberg W, Hauptmann A, Hamilton SJ. Domain independent post-processing with graph U-nets: applications to electrical impedance tomographic imaging. Physiological Measurement 2023; 44(12): 125008. https://doi.org/10.1088/1361-6....
30.
Liu Z, Wang J, Shan Q, Liu D. GraphEIT: Unsupervised Graph Neural Networks for Electrical Impedance Tomography. IEEE Transactions on Computational Imaging 2024; 10: 1559-1570. https://doi.org/10.1109/TCI.20....
31.
Hu Z, Bai X, Shang J, Zhang R, Dong J, Wang X, Sun G, Fu H, Tai CL. VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV); Montreal, QC, Canada. 2021; p.15468-74. https://doi.org/10.1109/ICCV48....
32.
Xu J, Zhang R, Dou J, Zhu Y, Sun J, Pu S. RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV); Montreal, QC, Canada. 2021; p.16004-16013. https://doi.org/10.1109/ICCV48....
33.
Sypek A, Sypek R. Zamki i obiekty warowne Pomorza Gdańskiego. Warsaw: Oficyna Wydawnicza Alma-Press; 2004.
34.
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 2004; 13(4): 600–612. https://doi.org/10.1109/TIP.20....
| eISSN: | 2956-3860 |
| ISSN: | 1507-2711 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
