基于全连接神经网络的颅脑电阻抗成像参考电压预测方法

doi:10.19595/j.cnki.1000-6753.tces.230766

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (8131 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Electrical impedance tomography (EIT) is a visualization techniquetoreconstruct conductivity distribution variations that reflect pathological changes in human tissues based on the boundary voltage measurement. Difference imaging is commonly used in the reconstruction to reduce modeling errors. Cerebral hemorrhage or ischemia can cause concentration changes of the intracranial ions, affecting the conductivity distribution. Consequently, the reference voltage obtained at a specific instant is inaccurate in the difference imaging. This paper proposesa reference voltage prediction method for brain EIT by fully connecting a neural network (FCNN). The reference voltage can be accurately predicted by establishing a nonlinear mapping between the measured and reference voltages.
Firstly, a three-layer brain model is constructed, including the scalp, skull, and brain tissue layers. The measured boundary voltage is used to construct the input matrix, and the true reference voltage is applied to construct the output matrix in the network. Anumber of training datasets are established to train the network. During the back-propagation of the loss function, an adaptive moment estimation algorithm is employed to update the parameters of FCNN. Then, the nonlinear relationship between the boundary measurement and the true reference voltage can be acquired, and the reference voltage can be predicted.
Simulation and experiments validate the proposed method. Compared with the true reference voltage, simulation results show that the voltage relative error ranges from 0% to 0.10% under the noise-free condition and 0% to 0.15% under the noisy condition. The reference voltage predicted by the proposed method well approaches the true reference voltage. Image reconstruction is performed based on the predicted reference voltage. The results show that the simulated stroke in the brain tissue layer can be reconstructed. The average blur radius of the reconstructed image increases, and the average correlation coefficient decreases gradually when the signal-to-noise ratio decreases. The feasibility of the proposed method is also tested when the conductivity of the scalp layer, skull layer, and brain tissue layer changes. It is found that the reconstructed image is very similar to the true conductivity distribution. The phantom experiment also validates the excellent performance of the proposed method.
The following conclusions can be drawn. (1) Due to the powerful mapping ability of FCNN, the proposed method can establish the nonlinear relationship between the measured boundary voltage and the true reference voltage in the brain EIT. (2) The difference between the predicted and true reference voltage is minor. The conductivity distribution of different models can be well reconstructed using the predicted reference voltage in the image reconstruction. (3) The proposed method only requires boundary measurement to obtain the information of reference voltage, avoiding the reference voltage calibration problem.

Key words： Electrical impedance tomography image reconstruction reference voltage neural network

Received: 25 May 2023

PACS:

TH772A

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Shi Yanyan
	Li Yuzhu
	Wang Meng
	Zheng Shuo
	Fu Feng

Cite this article:

Shi Yanyan,Li Yuzhu,Wang Meng等. Research on Reference Voltage Prediction for Electrical Impedance Tomography Based on Fully Connected Neural Network[J]. Transactions of China Electrotechnical Society, 2024, 39(14): 4317-4327.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.230766 OR https://dgjsxb.ces-transaction.com/EN/Y2024/V39/I14/4317

[1] van den Berg L A, Koelman D L H, Berkhemer O A, et al. Type of anesthesia and differences in clinical outcome after intra-arterial treatment for ischemic stroke[J]. Stroke, 2015, 46(5): 1257-1262.
[2] 李云云, 屈洪党. 脑出血的诊断与治疗[J]. 中华全科医学, 2019, 17(2): 171-172.
Li Yunyun, Qu Hongdang.Diagnosis and treatment of cerebral hemorrhage[J]. Chinese Journal of General Practice, 2019, 17(2): 171-172.
[3] 王昭昳, 张涛, 杨滨, 等. 基于径向基函数神经网络的脑损伤电阻抗成像仿真研究[J]. 中国医学装备, 2023, 20(3): 1-5.
Wang Zhaoyi, Zhang Tao, Yang Bin, et al.Simulation study of electrical impedance imaging of brain injury based on RBF neural network[J]. China Medical Equipment, 2023, 20(3): 1-5.
[4] 李彩莲, 李元园, 刘国强. 基于磁声电技术的肺部组织成像仿真研究[J]. 电工技术学报, 2021, 36(4): 732-737.
Li Cailian, Li Yuanyuan, Liu Guoqiang.Simulation of lung tissue imaging based on magneto-acousto-electrical technology[J]. Transactions of China Electrotechnical Society, 2021, 36(4): 732-737.
[5] 曲洪一, 刘鑫, 王晖, 等. 磁共振成像磁体无源匀场改进策略及实验研究[J]. 电工技术学报, 2022, 37(24): 6284-6293.
Qu Hongyi, Liu Xin, Wang Hui, et al.Improved strategy and experimental research on passive shimming in magnetic resonance imaging magnet[J]. Transactions of China Electrotechnical Society, 2022, 37(24): 6284-6293.
[6] 赵营鸽, 李颖, 王灵月, 等. 基于均值点展开的单变元降维法在EIT不确定性量化研究中的应用[J]. 电工技术学报, 2021, 36(18): 3776-3786.
Zhao Yingge, Li Ying, Wang Lingyue, et al.The application of univariate dimension reduction method based on mean point expansion in the research of electrical impedance tomography uncertainty quanti-fication[J]. Transactions of China Electrotechnical Society, 2021, 36(18): 3776-3786.
[7] Ren Shangjie, Sun Kai, Tan Chao, et al.A two-stage deep learning method for robust shape reconstruction with electrical impedance tomography[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 69(7): 4887-4897.
[8] 付荣, 张新宇, 王子辰, 等. 基于V-ResNet的电阻抗层析成像方法[J]. 仪器仪表学报, 2021, 42(9): 279-287.
Fu Rong, Zhang Xinyu, Wang Zichen, et al.Electrical impedance tomography method based on V-ResNet[J]. Chinese Journal of Scientific Instrument, 2021, 42(9): 279-287.
[9] 刘学超, 张涛, 章伟睿, 等. 脑脊液变化对脑出血电阻抗成像表征的影响研究[J]. 中国医学装备, 2022, 19(1): 26-30.
Liu Xuechao, Zhang Tao, Zhang Weirui, et al.A study on the influence of the CSF changes on EIT representation of cerebral hemorrhage[J]. China Medical Equipment, 2022, 19(1): 26-30.
[10] 郭大龙, 尤富生, 代萌, 等. 适用于脑卒中筛查的电阻抗成像电极的比较研究[J]. 医疗卫生装备, 2014, 35(3): 19-22.
Guo Dalong, You Fusheng, Dai Meng, et al.Comparative study of bio-electrodes applied to stroke screening in brain electrical impedance tomo-graphy[J]. Chinese Medical Equipment Journal, 2014, 35(3): 19-22.
[11] ZhangYijia, Chen Huaijin, Yang Lu, et al. A proportional genetic algorithm for image reconstruction of static electrical impedance tomography[J]. IEEE Sensors Journal, 2020, 20(24): 15026-15033.
[12] Denaï M A, Mahfouf M, Mohamad-Samuri S, et al.Absolute electrical impedance tomography (aEIT) guided ventilation therapy in critical care patients: simulations and future trends[J]. IEEE Transactions on Information Technology in Biomedicine: a Publication of the IEEE Engineering in Medicine and Biology Society, 2010, 14(3): 641-649.
[13] Shi Yanyan, Wu Yuehui, Wang Meng, et al.Image reconstruction of conductivity distribution with combined L1-norm fidelity and hybrid total variation penalty[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 4500412.
[14] 王琦, 张鹏程, 汪剑鸣, 等. 基于块稀疏的电阻抗成像算法[J]. 电子与信息学报, 2018, 40(3): 676-682.
Wang Qi, Zhang Pengcheng, Wang Jianming, et al.Block-sparse reconstruction for electrical impedance tomography[J]. Journal of Electronics & Information Technology, 2018, 40(3): 676-682.
[15] 章伟睿, 张涛, 史学涛, 等. 基于差分迭代的电阻抗成像算法研究[J]. 电工技术学报, 2021, 36(4): 747-755.
Zhang Weirui, Zhang Tao, Shi Xuetao, et al.An algorithm of electrical impedance tomography based on differential iteration[J]. Transactions of China Electrotechnical Society, 2021, 36(4): 747-755.
[16] Hamilton S J, Hauptmann A.Deep D-bar: real-time electrical impedance tomography imaging with deep neural networks[J]. IEEE Transactions on Medical Imaging, 2018, 37(10): 2367-2377.
[17] 李晓南, 任雯廷, 刘国强, 等. 高分辨率磁共振电特性成像及脑肿瘤诊断初步研究[J]. 电工技术学报, 2021, 36(18): 3860-3866.
Li Xiaonan, Ren Wenting, Liu Guoqiang, et al.Preliminary conductivity reconstruction by high-resolution magnetic resonance electrical properties tomography for brain tumor diagnosis[J]. Transa-ctions of China Electrotechnical Society, 2021, 36(18): 3860-3866.
[18] Wang Zeying, Yue Shihong, Liu Xiaoyuan, et al.Estimating homogeneous reference frame for absolute electrical impedance tomography through measure-ments and scale feature[J]. IEEE Transactions on Instrumentation and Measurement, 2020, 70: 1002812.
[19] Yu Hao, Wan Xingchen, Dong Zhongxu, et al.Estimation of reference voltages for time-difference electrical impedance tomography[J]. IEEE Transa-ctions on Instrumentation and Measurement, 2022, 71: 4506710.
[20] Wu Yang, Chen Bai, Liu Kai, et al.Shape reconstruction with multiphase conductivity for electrical impedance tomography using improved convolutional neural network method[J]. IEEE Sensors Journal, 2021, 21(7): 9277-9287.
[21] Shi Yanyan, Tian Zhiwei, Wang Meng, et al.Residual convolutional neural network-based stroke classification with electrical impedance tomography[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 4502911.
[22] Sangari A, Sethares W.Convergence analysis of two loss functions in soft-max regression[J]. IEEE Transactions on Signal Processing, 2016, 64(5): 1280-1288.
[23] 李星, 杨帆, 余晓, 等. 基于自诊断正则化的电阻抗成像逆问题研究[J]. 生物医学工程学杂志, 2018, 35(3): 460-467.
Li Xing, Yang Fan, Yu Xiao, et al.Study on the inverse problem of electrical impedance tomography based on self-diagnosis regularization[J]. Journal of Biomedical Engineering, 2018, 35(3): 460-467.
[24] LiHaoting, Chen Rongqing, Xu Canhua, et al. Unveiling the development of intracranial injury using dynamic brain EIT: an evaluation of current reconstruction algorithms[J]. Physiological Measurement, 2017, 38(9): 1776-1790.
[25] Wendel K, Väisänen J, Seemann G, et al.The influence of age and skull conductivity on surface and subdermal bipolar EEG leads[J]. Computational Intelligence and Neuroscience, 2010, 2010: 397272-397278.
[26] Javaherian A, Movafeghi A, Faghihi R, et al.An exhaustive criterion for estimating quality of images in electrical impedance tomography with application to clinical imaging[J]. Journal of Visual Communication and Image Representation, 2013, 24(7): 773-785.
[27] 叶明, 李晓丞, 刘凯, 等. 一种基于U2-Net模型的电阻抗成像方法[J]. 仪器仪表学报, 2021, 42(2): 235-243.
Ye Ming, Li Xiaocheng, Liu Kai, et al.Image reconstruction method for electrical impedanceto-mography using U2-Net[J]. Chinese Journal of Scientific Instrument, 2021, 42(2): 235-243.