Abstract：Aiming at the ill-posedness and nonlinearity of electrical impedance tomography inverse problem, a DK-SVD-based block sparse image reconstruction method is proposed.The multi-layer perceptron is introduced to finetune optimal model parameters for measurement data considering the complexity of datasets and improve the image quality.The iterative shrinkage threshold algorithm is used to accelerate convergence in the sparse coding stage.The simulation results show that the structural similarity of the reconstructed image by DK-SVD algorithm can reach more than 0.95, the error can be controlled at about 0.1, and the average reconstruction speed is 0.034s, which effectively improves the quality and efficiency of electrical impedance tomography, and further experiments prove that the algorithm has good noise robustness and practical application value.
王琦,杨雨晗,李秀艳,段晓杰,汪剑鸣,孙玉宽,冯慧. 基于DK-SVD的深度学习电阻抗块稀疏成像方法研究[J]. 计量学报, 2024, 45(9): 1370-1377.
WANG Qi,YANG Yuhan,LI Xiuyan,DUAN Xiaojie,WANG Jianming,SUN Yukuan,FENG Hui. Study on the Electrical Impedance Block Sparse Imaging Method of Deep Learning Based on DK-SVD. Acta Metrologica Sinica, 2024, 45(9): 1370-1377.
REN C S, WANG Y, ZHAO S. Electrical impedance tomography measuring gastric emptying and gastric motility ［J］. World Chinese Journal of Digestology, 2008(8): 799-805.
YAN P M, CAO Y X. Electrical impedance tomography in chest based on the elliptical geometry model ［J］. Electronic Measurement Technology, 2016, 39(6): 81-84.
YOU Y, ZHAO Z W, DAI M, et al. Electrical impedance tomography experiment for transient cerebral ischemia ［J］. Chinese Journal of Neurology, 2008(2): 123-125.
LIU M C, XING J Y. Electrical impedance tomography in lung imaging of the respiratory system ［J］. Chinese Journal of Critical Care & Intensive Care Medicine(Electronic Edition), 2019, 5(4): 373-378.
VELASCO A C, DARBAS M, MENDOZA R. Numerical Resolution of the Electrical Impedance Tomography Inverse Problem with Fixed Inclusions ［J］. International Journal of Mathematics and Computer Science, 2021, 16(3): 1063-1076.
［8］
AHARON M, ELAD M, BRUCKSTREIN A M. The K-SVD: an algorithm for designing of over-complete dictionaries for sparse representation ［J］. IEEE Transaction on Image Processing, 2006, 54(11) : 4311-4322.
CHENG Y F, LIU Z L. Improved K-SVD Image Denoising Algorithm ［J］. Acta Metrology Sinica, 2018, 39(3): 332-336.
RUBINSTEIN R, ZIBULEVSKY M, ELAD M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit［R］. Computer Science Department, Technion, 2008.
HUA Z S, FU L H. K-SVD image denoising based on noisy image blocks classification and dictionary optimization ［J］. Computer Engineering and Applications, 2017, 53(16): 187-192.
［15］
LACRAMA D L, GHERHES V, ALEXA F, et al, Automatic survey processing using a MLP neural net［C］//10th Symposium on Neural Network Applications in Electrical Engineering. 2010:123-126.
［17］
BECK A, TEBOULLE M. A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems ［J］. Siam J Imaging Sciences, 2009, 2(1): 183-202.
［18］
DAUBECHIES I, DEFRISE M, MOL C D. An iterative thresholding algorithm for linear inverse problems with a sparsity constraint ［J］. Communications on Pure and Applied Mathematics, 2004, 57(11):1413-1457.
［19］
WANG Q, LIAN Z, WANG J, et al. Accelerated reconstruction of electrical impedance tomography images via patch based sparse representation ［J］. Review of Scientific Instruments, 2016, 87(11): 114707.
［22］
ALRUWAILI E, LI J. Majorization-Minimization Total Variation Solution Methods for Electrical Impedance Tomography ［J］. Mathematics, 2022, 10(9): 1-18.
［24］
MAIRAL J, SAPIRO G, ELAD M. Learning multiscale sparse representations for image and video restoration ［J］. Multiscale modeling & simulation, 2008, 7(1): 214-241.
［26］
WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity ［J］. IEEE transactions on image processing, 2004, 13(4): 600-612.
WANG C, LIU J X, WANG H X. Design of High-Frequency Medical EIT System ［J］. Acta Metrology Sinica, 2004, 25(2): 177-180.
ZENG M, ZHANG W, CHEN Z. Group-based K-SVD denoising for bearing fault diagnosis ［J］. IEEE Sensors Journal, 2019, 19(15): 6335-6343.
CHEN J, LIU Y Y,HUANG K X, et al. Rolling Bearing Fault Diagnosis Method Based on Singular Value Decomposition and Independent Component Analysis ［J］. Acta Metrology Sinica, 2022, 43(6): 777-785.
［16］
XIANG C, DING S, LEE T H. Geometrical interpretation and architecture selection of MLP. ［J］. IEEE transactions on neural networks, 2005, 16(1): 84-96.
［21］
WANG M. Electrical impedance tomography: US06940286B2［P］. 2005.
［25］
ZHANG Z Y, ZHU F S, ZHOU R, et al. An Efficient Method for Density Projection Field Solution Based on Finite Element Method［C］//Proceedings of 2020 2nd International Conference on Computer Modeling, Simulation and Algorithm(CMSA2020).2020: 703-710.
［7］
SEO J K, KIM K C, JARGAL A, et al. A Learning-Based Method for Solving Ill-Posed Nonlinear Inverse Problems: A Simulation Study of Lung EIT ［J］. SIAM Journal on Imaging Sciences, 2019, 12(3): 1275-1295
ZHENG H, FANG G, DUAN S, et al. A novel method for noise reduction of blade tip timing signals based on sparse representation and dictionary learning ［J］. Journal of Low Frequency Noise, Vibration and Active Control, 2023: 43(1): 437-454.
［20］
HE J C, LI L, XU J C. Approximation properties of deep ReLU CNNs ［J］. Research in the Mathematical Sciences, 2022, 9(3): 1-24.
XING C C, WU Y G, ZHAO X, et al. Application of Singular Value Decomposition (SVD) in Denoising of Potential Field Data ［J］. Global Geology, 2016, 35(4): 1119-1126.
2024, Vol. 45 
