A Combined Network Model-Based Abnormal Data Compensation Method for Enhanced Electrical Impedance Tomography
IEEE Sensors Journal · 01.04.2026 · 26 (7) · 11120-11129
DOI: 10.1109/jsen.2026.3667189 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.04.2026. Verfasst von Weicheng Liu und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hainan Province, Science and Technology Project of Henan Province of China.
Abstract (Originalsprache)
During bedside monitoring with brain electrical impedance tomography (EIT), electrode detachment is identified as a common occurrence. It causes abnormal voltage measurement and affects image reconstruction quality. To address this issue, this article proposes an abnormal data compensation method based on a combined network model. Specifically, boundary measurement data are first analyzed to identify the electrode experiencing detachment. Subsequently, the framework employs a hybrid model that integrates a temporal-spatial convolutional network (TCN), a long short-term memory (LSTM) network, and an attention mechanism to compensate for the abnormal data induced by electrode detachment. Comprehensive research is performed to examine the performance of the proposed approach under electrode detachment conditions in brain EIT. The results show that the compensated voltage is highly consistent with the normal measurement. Image reconstructions are also carried out for the scenarios of single-electrode detachment and dual-electrode detachment. It is found that imaging quality can be guaranteed when the compensated voltage is used. Moreover, the approach is examined for its robustness against noise interference, model deformation, and conductivity variation. Qualitative and quantitative results verify the capability of the proposed method in terms of abnormal voltage data compensation under electrode disconnection. This study holds potential for ensuring accuracy of brain imaging when using EIT for long-time monitoring.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Hainan Province
- Science and Technology Project of Henan Province of China
- National Key Research and Development Program of China
Zitieren
APA
Liu, W., Shi, Y., Liang, J., Wang, M., Zhou, Y., & Fu, F. (2026). A Combined Network Model-Based Abnormal Data Compensation Method for Enhanced Electrical Impedance Tomography. IEEE Sensors Journal, 26(7), 11120-11129. https://doi.org/10.1109/jsen.2026.3667189
Vancouver
Liu W, Shi Y, Liang J, Wang M, Zhou Y, Fu F. A Combined Network Model-Based Abnormal Data Compensation Method for Enhanced Electrical Impedance Tomography. IEEE Sensors Journal. 2026;26(7):11120-11129. doi:10.1109/jsen.2026.3667189
BibTeX
@article{Liu2026,
author = {Liu, Weicheng and Shi, Yanyan and Liang, Jie and Wang, Meng and Zhou, Yimin and Fu, Feng},
title = {A Combined Network Model-Based Abnormal Data Compensation Method for Enhanced Electrical Impedance Tomography},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {7},
pages = {11120--11129},
doi = {10.1109/jsen.2026.3667189}
}
EUVIMED