{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T14:46:17Z","timestamp":1780325177253,"version":"3.54.1"},"reference-count":58,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The internal grant for employees of the Warsaw University of 463 Technology supporting scientific activity in the discipline of Biomedical Engineering","award":["3\/2023\/RNDIB\/WEITI"],"award-info":[{"award-number":["3\/2023\/RNDIB\/WEITI"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This study investigates the influence of variable electrode positions on image reconstruction in capacitively coupled electrical impedance tomography (CC-EIT) of the human thorax. Images were reconstructed by an adversarial neural network trained on a synthetic dataset generated using a tomographic model that included a wearable elastic band with 32 electrodes attached. Dataset generation was conducted using a previously developed numerical phantom of the thorax, combined with a newly developed algorithm for random selection of electrode positions based on physical limitations resulting from the elasticity of the band and possible position inaccuracies while putting the band on the patient\u2019s chest. The thorax phantom included the heart, lungs, aorta, and spine. Four training and four testing datasets were generated using four different levels of electrode displacement. Reconstruction was conducted using four versions of neural networks trained on the datasets, with random ellipses included and noise added to achieve an SNR of 30 dB. The quality was assessed using pixel-to-pixel metrics such as the root-mean-square error, structural similarity index, 2D correlation coefficient, and peak signal-to-noise ratio. The results showed a strong negative influence of electrode displacement on reconstruction quality when no samples with displaced electrodes were present in the training dataset. Training the network on the dataset containing samples with electrode displacement allowed us to significantly improve the quality of the reconstructed images. Introducing samples with misplaced electrodes increased neural network robustness to electrode displacement while testing.<\/jats:p>","DOI":"10.3390\/s25216543","type":"journal-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T01:35:11Z","timestamp":1761269711000},"page":"6543","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine Learning-Based Image Reconstruction in Wearable CC-EIT of the Thorax: Robustness to Electrode Displacement"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2765-9370","authenticated-orcid":false,"given":"Jan","family":"Jeschke","sequence":"first","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8682-2751","authenticated-orcid":false,"given":"Mikhail","family":"Ivanenko","sequence":"additional","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1524-5049","authenticated-orcid":false,"given":"Waldemar T.","family":"Smolik","sequence":"additional","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-6524","authenticated-orcid":false,"given":"Damian","family":"Wanta","sequence":"additional","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2449-0652","authenticated-orcid":false,"given":"Mateusz","family":"Midura","sequence":"additional","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6713-9088","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Wr\u00f3blewski","sequence":"additional","affiliation":[{"name":"Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15\/19, 00-665 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1049\/el:19880283","article-title":"Capacitance-based tomographic flow imaging system","volume":"24","author":"Huang","year":"1988","journal-title":"Electron. Lett."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3708","DOI":"10.1021\/ie0713590","article-title":"Electrical capacitance tomography\u2014A perspective","volume":"47","author":"Marashdeh","year":"2008","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1080\/00102202.2010.497420","article-title":"Flame Imaging Using 3D Electrical Capacitance Tomography","volume":"182","author":"Gut","year":"2010","journal-title":"Combust. Sci. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.5604\/05096669.1226349","article-title":"Selected Application of Electrical Capacitance Tomography in Monitoring of Combustion Process","volume":"245","author":"Gut","year":"2016","journal-title":"Trans. Inst. Aviat."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"van Oudheusden, B. (1996). Imaging Industrial Flow: Applications of Electrical Process Tomography, IOP Publishing Ltd.","DOI":"10.1016\/S0924-4247(97)80082-9"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"332","DOI":"10.1515\/phys-2018-0046","article-title":"Applying industrial tomography to control and optimization flow systems","volume":"16","author":"Rymarczyk","year":"2018","journal-title":"Open Phys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"042001","DOI":"10.1088\/0957-0233\/21\/4\/042001","article-title":"Design of electrical capacitance tomography sensors","volume":"21","author":"Yang","year":"2010","journal-title":"Meas. Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1567","DOI":"10.1109\/JSEN.2014.2363901","article-title":"Optimizing the geometry of three-dimensional electrical capacitance tomography sensors","volume":"15","author":"Li","year":"2015","journal-title":"IEEE Sens. J."},{"key":"ref_9","first-page":"133","article-title":"Electrical tomography system for innovative imaging and signal analysis","volume":"95","author":"Rymarczyk","year":"2019","journal-title":"Prz. Elektrotechniczny"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Ivanenko, M., Smolik, W.T., Wanta, D., Midura, M., Wr\u00f3blewski, P., Hou, X., and Yan, X. (2023). Image Reconstruction Using Supervised Learning in Wearable Electrical Impedance Tomography of the Thorax. Sensors, 23.","DOI":"10.3390\/s23187774"},{"key":"ref_11","first-page":"6","article-title":"Pulmovista 500 by drager: A snapshot of clinical usability in the ICU setting","volume":"57","author":"Kidwai","year":"2021","journal-title":"Can. J. Respir. Ther."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hu, C.L., Cheng, I.C., Huang, C.H., Liao, Y.T., Lin, W.C., Tsai, K.J., Chi, C.H., Chen, C.W., Wu, C.H., and Lin, I.T. (2021). Dry wearable textile electrodes for portable electrical impedance tomography. Sensors, 21.","DOI":"10.3390\/s21206789"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1109\/JSEN.2006.890149","article-title":"A Multimodal Tomography System Based on ECT Sensors","volume":"7","author":"Teixeira","year":"2007","journal-title":"IEEE Sens. J."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jiang, Y., and Soleimani, M. (2018). Capacitively Coupled Phase-based Dielectric Spectroscopy Tomography. Sci. Rep., 8.","DOI":"10.1038\/s41598-018-35904-4"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2104","DOI":"10.1109\/TMI.2019.2895035","article-title":"Capacitively Coupled Electrical Impedance Tomography for Brain Imaging","volume":"38","author":"Jiang","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhu, Z., and Wang, Y. (2019, January 3\u20135). Simultaneous Reconstruction of Conductivity and Permittivity in Electrical Impedance Tomography. Proceedings of the 31st Chinese Control and Decision Conference, CCDC 2019, Nanchang, China.","DOI":"10.1109\/CCDC.2019.8833397"},{"key":"ref_17","first-page":"178","article-title":"Reconstruction of permittivity profile from boundary capacitance data","volume":"177","author":"Fang","year":"2006","journal-title":"Appl. Math. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Jia, Y. (2023). A review on reconstruction algorithms and hardware implementation in electrical impedance tomography. J. Phys. Conf. Ser., 2634.","DOI":"10.1088\/1742-6596\/2634\/1\/012038"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1088\/0967-3334\/25\/1\/021","article-title":"EIT reconstruction algorithms: Pitfalls, challenges and recent developments","volume":"25","author":"Lionheart","year":"2004","journal-title":"Physiol. Meas."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yan, H., Liu, L.J., and Qiang, D.Z. (2009, January 12\u201314). An iterative electrical capacitance tomography image reconstruction algorithm. Proceedings of the ISCID 2009\u20142009 International Symposium on Computational Intelligence and Design, Changsha, China.","DOI":"10.1109\/ISCID.2009.85"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"094014","DOI":"10.1088\/0957-0233\/19\/9\/094014","article-title":"Image reconstruction by nonlinear Landweber iteration for complicated distributions","volume":"19","author":"Li","year":"2008","journal-title":"Meas. Sci. Technol."},{"key":"ref_22","unstructured":"Latourette, K. (2008). A Comparison Of The Levenberg-Marquardt Method with Standard Optimization Algorithms. Minimizing the Tikhonov-Total Variational Functional, University of Arizona."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Smolik, W. (2010, January 1\u20132). Accelerated Levenberg-Marquardt method with an optimal step length in electrical capacitance tomography. Proceedings of the 2010 IEEE International Conference on Imaging Systems and Techniques, IST 2010\u2014Proceedings, Thessaloniki, Greece.","DOI":"10.1109\/IST.2010.5548490"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.flowmeasinst.2012.05.006","article-title":"Image reconstruction for an Electrical Capacitance Tomography (ECT) system based on a least squares support vector machine and bacterial colony chemotaxis algorithm","volume":"27","author":"Wang","year":"2012","journal-title":"Flow Meas. Instrum."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1038\/s42256-020-00273-z","article-title":"Deep learning for tomographic image reconstruction","volume":"2","author":"Wang","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"34252","DOI":"10.1109\/JSEN.2025.3589157","article-title":"Algorithms on electrical impedance tomography, focusing on deep learning architectures and their implementations: A Review","volume":"25","author":"Carcavilla","year":"2025","journal-title":"IEEE Sens. J."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"104006","DOI":"10.1088\/0957-0233\/22\/10\/104006","article-title":"Neural networks in electrical capacitance tomography (ECT)-based interface detection","volume":"22","author":"Ru","year":"2011","journal-title":"Meas. Sci. Technol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Navab, N., Hornegger, J., Wells, W.M., and Frangi, A.F. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention, Proceedings of the MICCAI 2015, Munich, Germany, 5\u20139 October 2015, Springer.","DOI":"10.1007\/978-3-319-24553-9"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"012013","DOI":"10.1088\/1742-6596\/1757\/1\/012013","article-title":"EIT-4LDNN: A Novel Neural Network for Electrical Impedance Tomography","volume":"1757","author":"Zhang","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"S103","DOI":"10.1088\/0967-3334\/27\/5\/S09","article-title":"Imaging of conductivity changes and electrode movement in EIT","volume":"27","author":"Soleimani","year":"2006","journal-title":"Physiol. Meas."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1088\/0967-3334\/36\/6\/1109","article-title":"Positioning of electrode plane systematically influences EIT imaging","volume":"36","author":"Schullcke","year":"2015","journal-title":"Physiol. Meas."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"7375","DOI":"10.1016\/j.ifacol.2023.10.354","article-title":"Machine Learning Applied to EIT: Image Reconstruction, Displaced Electrodes and Boundary Shape","volume":"56","author":"Ueda","year":"2023","journal-title":"IFAC-PapersOnLine"},{"key":"ref_33","unstructured":"Wanta, D., Smolik, W.T., and Kryszyn, J. (2024). ECTsim. Zenodo."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1007\/s40010-021-00748-7","article-title":"A Finite Volume Method using a Quadtree Non-Uniform Structured Mesh for Modeling in Electrical Capacitance Tomography","volume":"92","author":"Wanta","year":"2021","journal-title":"Proc. Natl. Acad. Sci. India Sect. A-Phys. Sci."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Smolik, W.T., and Kryszyn, J. (2013, January 22\u201323). Refined cartesian mesh for modeling in electrical capacitance tomography. Proceedings of the IST 2013\u20142013 IEEE International Conference on Imaging Systems and Techniques, Proceedings, Beijing, China.","DOI":"10.1109\/IST.2013.6729724"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"124004","DOI":"10.1088\/1361-6579\/aaf271","article-title":"Portable multi-parameter electrical impedance tomography for sleep apnea and hypoventilation monitoring: Feasibility study","volume":"39","author":"Lee","year":"2018","journal-title":"Physiol. Meas."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3810","DOI":"10.1109\/TCSI.2018.2858148","article-title":"A high frame rate wearable EIT system using active electrode ASICs for lung respiration and heart rate monitoring","volume":"65","author":"Wu","year":"2018","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1109\/TBCAS.2019.2925713","article-title":"A 122 fps, 1 MHz Bandwidth Multi-Frequency Wearable EIT Belt Featuring Novel Active Electrode Architecture for Neonatal Thorax Vital Sign Monitoring","volume":"13","author":"Wu","year":"2019","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3137","DOI":"10.1109\/TIM.2018.2874127","article-title":"The ACE1 Electrical Impedance Tomography System for Thoracic Imaging","volume":"68","author":"Mellenthin","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"955","DOI":"10.1109\/TBME.2021.3110527","article-title":"Wearable Electrical Impedance Tomography Belt with Dry Electrodes","volume":"69","author":"Lin","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1109\/TBCAS.2023.3307500","article-title":"Flexi-EIT: A Flexible and Reconfigurable Active Electrode Electrical Impedance Tomography System","volume":"18","author":"Wang","year":"2024","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wanta, D., Ivanenko, M., Smolik, W.T., Wr\u00f3blewski, P., and Midura, M. (2024). Real-Time Nonlinear Image Reconstruction in Electrical Capacitance Tomography Using the Generative Adversarial Network. Information, 15.","DOI":"10.3390\/info15100617"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Wanta, D., Makowiecka, O., Smolik, W.T., Kryszyn, J., Doma\u0144ski, G., Midura, M., and Wr\u00f3blewski, P. (2022). Numerical Evaluation of Complex Capacitance Measurement Using Pulse Excitation in Electrical Capacitance Tomography. Electronics, 11.","DOI":"10.3390\/electronics11121864"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1080\/21681163.2019.1672210","article-title":"Fast and automatic segmentation of pulmonary lobes from chest CT using a progressive dense V-network","volume":"8","author":"Imran","year":"2020","journal-title":"Comput. Methods Biomech. Biomed. Eng. Imaging Vis."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1360612.1360662","article-title":"Discrete elastic rods","volume":"27","author":"Bergou","year":"2008","journal-title":"ACM Trans. Graph."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/s41664-018-0068-2","article-title":"On Splitting Training and Validation Set: A Comparative Study of Cross-Validation, Bootstrap and Systematic Sampling for Estimating the Generalization Performance of Supervised Learning","volume":"2","author":"Xu","year":"2018","journal-title":"J. Anal. Test."},{"key":"ref_47","unstructured":"Mirza, M., and Osindero, S. (2014). Conditional Generative Adversarial Nets. arXiv."},{"key":"ref_48","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. Machine Learning for Data Science Handbook: Data Mining and Knowledge Discovery Handbook, Springer. [3rd ed.]."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, R., Wang, Q., Duan, X., Sun, Y., and Wang, J. (2023). SAR-CGAN: Improved generative adversarial network for EIT reconstruction of lung diseases. Biomed. Signal Process. Control, 81.","DOI":"10.1016\/j.bspc.2022.104421"},{"key":"ref_50","unstructured":"Deabes, W., and Abdel-Hakim, A.E. (2022). CGAN-ECT: Tomography Image Reconstruction from Electrical Capacitance Measurements Using CGANs. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21\u201326). Image-to-image translation with conditional adversarial networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref_52","unstructured":"Loshchilov, I., and Hutter, F. (2017, January 24\u201326). SGDR: Stochastic gradient descent with warm restarts. Proceedings of the 5th International Conference on Learning Representations, ICLR 2017\u2014Conference Track Proceedings, Toulon, France."},{"key":"ref_53","unstructured":"Loshchilov, I., and Hutter, F. (2019, January 6\u20139). Decoupled weight decay regularization. Proceedings of the 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"8","DOI":"10.4236\/jcc.2019.73002","article-title":"Image Quality Assessment through FSIM, SSIM, MSE and PSNR\u2014A Comparative Study","volume":"7","author":"Sara","year":"2019","journal-title":"J. Comput. Commun."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Creegan, A., Nielsen, P.M., and Tawhai, M.H. (2024). A novel two-dimensional phantom for electrical impedance tomography using 3D printing. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-52696-y"},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.promfg.2020.05.111","article-title":"48th SME North American Manufacturing Research Conference, NAMRC 48 (Cancelled due to COVID-19) Carbon nanotubes reinforced alumina matrix nanocomposites for conductive ceramics by additive manufacturing","volume":"48","author":"Liu","year":"2020","journal-title":"Procedia Manuf."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Owda, A.Y., Casson, A.J., Owda, A.Y., and Casson, A.J. (2020). Electrical properties, accuracy, and multi-day performance of gelatine phantoms for electrophysiology. BioRxiv.","DOI":"10.1101\/2020.05.30.125070"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6543\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T04:42:41Z","timestamp":1761367361000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/21\/6543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":58,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["s25216543"],"URL":"https:\/\/doi.org\/10.3390\/s25216543","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,23]]}}}