As a noninvasive imaging technique for the interior of objects, Electrical Impedance Tomography (EIT) is widely used in many fields of biomedicine. Sparse reconstruction algorithms have made major breakthroughs in the field of image reconstruction in recent years. The K-SVD algorithm is an adaptive dictionary signal sparse representation algorithm, which could improve the reconstruction accuracy. However, the parameters in the K-SVD algorithm are fixed, which cannot match all the measurement data of EIT very well. Moreover, the K-SVD algorithm adopts a greedy algorithm in the sparse coding stage, which has high computational complexity. In this study, an electrical impedance sparse imaging method based on DK-SVD (deep k-singular value decomposition) was designed. It provides the corresponding optimal model parameters for each set of measurement data through the method of multi-layer perceptron (MLP) network training, thereby improving the imaging quality. At the same time, the iterative soft threshold algorithm (ISTA) is used in the sparse coding stage to improve the convergence speed. The reconstruction results show that compared with the K-SVD algorithm and Total Variation (TV) algorithm, the reconstruction error of the DK-SVD method is smaller, and the irregular and sharp inclusions can be accurately reconstructed. Image artifacts are also greatly reduced.
1. Hong, S., K. Lee, U. Ha, H. Kim, Y. Lee, Y. Kim, and H.-J. Yoo, "A 4.9 mΩ-sensitivity mobile electrical impedance tomography IC for early breast-cancer detection system," IEEE Journal of Solid-State Circuits, Vol. 50, No. 1, 245-257, 2015. doi:10.1109/JSSC.2014.2355835
2. Fabrizi, L., A. McEwan, T. Oh, E. J. Woo, and D. S. Holder, "A comparison of two EIT systems suitable for imaging impedance changes in epilepsy," Physiological Measurement, Vol. 30, No. 6, S103-S120, 2009. doi:10.1088/0967-3334/30/6/S07
3. Nissinen, A., J. P. Kaipio, M. Vauhkonen, and V. Kolehmainen, "Contrast enhancement in EIT imaging of the brain," Physiological Measurement, Vol. 37, No. 1, 1-24, 2016. doi:10.1088/0967-3334/37/1/1
4. Jang, G. Y., G. Ayoub, Y. E. Kim, T. I. Oh, C. R. Chung, G. Y. Suh, and E. J. Woo, "Integrated EIT system for functional lung ventilation imaging," BioMedical Engineering OnLine, Vol. 18, No. 1, 1-18, 2019. doi:10.1186/s12938-019-0701-y
5. Bradley, D. and J. Bagnell, "Differential sparse coding," Proc. Conf. Neural Information Processing Systems, 2008.
6. Wang, J., J. Yang, K. Yu, F. Lv, T. Huang, and Y. Gong, "Locality-constrained linear coding for image classification," 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 3360-3367, 2010.
7. Zylberberg, J., J. T. Murphy, and M. R. DeWeese, "A sparse codingmodel with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptivefields," PLOS Comput. Biol., Vol. 7, No. 10, e1002250, 2011. doi:10.1371/journal.pcbi.1002250
8. Davis, G., S. Mallat, and M. Avellaneda, "Adaptive greedy approximations," J. Construct. Approx., Vol. 13, 57-98, 1997. doi:10.1007/BF02678430
9. Aharon, M., M. Elad, and A. Bruckstein, "K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation," IEEE Transactions on Signal Processing, Vol. 54, No. 11, 4311-4322, Nov. 2006, doi: 10.1109/TSP.2006.881199. doi:10.1109/TSP.2006.881199
10. Yang, J., Y. Zhang, and W. Yin, "A fast alternating direction method for TVL1-L2 signal reconstruction from partial fourier data," IEEE Journal of Selected Topics in Signal Processing, Vol. 4, No. 2, 288-297, 2010. doi:10.1109/JSTSP.2010.2042333
11. Needell, D. and R. Vershynin, "Signal recovery from incomplete and inaccurate measurements via regularized orthogonal matching pursuit," IEEE Journal of Selected Topics in Signal Processing, Vol. 4, No. 2, 310-316, 2010. doi:10.1109/JSTSP.2010.2042412
12. Wang, Q., Z. Lian, J. Wang, Q. Chen, Y. Sun, X. Li, X. Duan, Z. Cui, and H. Wang, "Accelerated reconstruction of electrical impedance tomography images via patch based sparse representation," Review of Scientific Instruments, Vol. 87, No. 11, 114707, 2016. doi:10.1063/1.4966998
13. Wang, Q., P. Zhang, J. Wang, Q. Chen, Z. Lian, X. Li, Y. Sun, X. Duan, Z. Cui, B. Sun, and H.Wang, "Patch based sparse reconstruction for electrical impedance tomography," Sensor Review, Vol. 37, No. 3, 257-269, 2017. doi:10.1108/SR-07-2016-0126
14. Li, X., J. Zhang, J. Wang, Q. Wang, and X. Duan, "Recursive least squares dictionary learning algorithm for electrical impedance tomography," Progress In Electromagnetics Research C, Vol. 97, 151-162, 2019. doi:10.2528/PIERC19081001
15. Wang, C., D. Sun, and K. C. Toh, "Solving log-determinant optimization problems by a Newton-CG primal proximal point algorithm," Siam Journal on Optimization, Vol. 20, No. 6, 2994-3013, 2009. doi:10.1137/090772514
16. Hou, W. and Y. Mo, "Image reconstruction in electrical impedance tomography based on genetic algorithm," Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, Vol. 20, No. 1, 107-110, 2003.
17. Marquina, A. and S. Osher, "Image super-resolution by TV-regularization and Bregman iteration," Journal of Scientific Computing, Vol. 37, No. 3, 367-382, 2008. doi:10.1007/s10915-008-9214-8
18. Yu, C., S. Fan, Y. Bo, and D. Chen, "A novel quasi-newton image reconstruction algorithm for electrical capacitance tomography system," 2009 ISECS International Colloquium on Computing, Communication, Control, and Management, 89-93, 2009. doi:10.1109/CCCM.2009.5267974
19. Dai, T. and A. Adler, "Electrical impedance tomography reconstruction using l1 norms for data and image terms," 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2721-2724, 2008. doi:10.1109/IEMBS.2008.4649764
20. Gehre, M., T. Kluth, A. Lipponen, B. Jin, A. Seppänen, J. P. Kaipio, and P. Maassa, "Sparsity reconstruction in electrical impedance tomography: An experimental evaluation," Journal of Computational and Applied Mathematics, Vol. 236, No. 8, 2126-2136, 2012. doi:10.1016/j.cam.2011.09.035
21. Gehre, M., T. Kluth, C. Sebu, and P. Maass, "Sparse 3D reconstructions in electrical impedance tomography using real data," Inverse Problems in Science & Engineering, Vol. 22, No. 1, 31-44, 2014. doi:10.1080/17415977.2013.827183
22. Theertham, G. T., S. K. Varanasi, and P. Jampana, "Sparsity constrained reconstruction for electrical impedance tomography," IFAC-PapersOnLine, Vol. 53, No. 2, 355-360, 2020. doi:10.1016/j.ifacol.2020.12.185
23. Liu, S., R. Cao, Y. Huang, T. Ouypornkochagorn, and J. Jia, "Time sequence learning for electrical impedance tomography using bayesian spatiotemporal priors," IEEE Transactions on Instrumentation and Measurement, Vol. 69, No. 9, 6045-6057, 2020. doi:10.1109/TIM.2020.2972172
24. Shi, Y., Y. Wu, M. Wang, Z. Tian, X. Kong, and X. He, "Sparse image reconstruction of intracerebral hemorrhage with electrical impedance tomography," Journal of Medical Imaging, Vol. 8, No. 1, 014501, 2021. doi:10.1117/1.JMI.8.1.014501
25. Hu, G., J. Lin, G. Wang, and R. He, "Sparse reconstruction based channel estimation for underwater piezo-acoustic backscatter systems," 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), 1-5, 2021.
26. Li, S., H. Wang, J. N. Chen, and Z. Cui, "An improved sparse reconstruction algorithm based on singular value decomposition for electrical resistance tomography," 2021 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 1-6, 2021.
27. Kou, S. and X. Feng, "Angle-micro-Doppler frequency image of underwater target multi-highlight combining with sparse reconstruction," Applied Acoustics, Vol. 188, 108563, 2022. doi:10.1016/j.apacoust.2021.108563
29. Ye, J. M., H. G. Wang, and W. Q. Yang, "Image reconstruction for electrical capacitance tomography based on sparse representation," IEEE Transactions on Instrumentation and Measurement, Vol. 64, No. 1, 89-102, Jan. 2015. doi:10.1109/TIM.2014.2329738
30. Jin, B., T. Khan, and P. Maass, "A reconstruction algorithm for electrical impedance tomography based on sparsity regularization," Int. J. Numer. Methods Eng., Vol. 89, 337-353, Jan. 2012. doi:10.1002/nme.3247
31. Qu, X. B., Y. Hou, F. Lam, D. Guo, J. H. Zhong, and Z. Chen, "Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator," Med. Image Anal., Vol. 18, 843-856, Aug. 2014. doi:10.1016/j.media.2013.09.007
32. Elad, M. and M. Aharon, "Image denoising via sparse and redundant representations over learned dictionaries," IEEE Trans. Image Process., Vol. 12, 3736-3745, 2006. doi:10.1109/TIP.2006.881969
33. Wang, Q., K. Sun, J. Wang, and R. Zhang, "Reconstruction of EIT images via patch based sparse representation over learned dictionaries," 2015 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings, 2044-2048, 2015. doi:10.1109/I2MTC.2015.7151597
34. Wang, M. and W. Yin, "Electrical impedance tomography,", US06940286B2, 2005.
35. Donoho, D. L. and M. Elad, "Optimally sparse representation in general (nonorthogonal) dictionaries via l1 minimization," Proc. Nat. Acad. Sci. USA, Vol. 100, No. 5, 2197-2202, Mar. 2003. doi:10.1073/pnas.0437847100
36. Donoho, D. L., M. Elad, and V. N. Temlyakov, "Stable recovery of sparse overcomplete representations in the presence of noise," IEEE Trans. Inf. Theory, Vol. 52, No. 1, 6-18, Jan. 2006. doi:10.1109/TIT.2005.860430
37. Daubechies, I., M. Defrise, and C. D. Mol, "An iterative thresholding algorithm for linear inverse problems with a sparsity constraint," Commun. Pure Appl. Math., Vol. 57, No. 11, 1413-1457, 2004. doi:10.1002/cpa.20042
38. Xiang, C., S. Ding, and T. H. Lee, "Geometrical interpretation and architecture selection of MLP," IEEE Transactions on Neural Networks, Vol. 16, No. 1, 84-96, 2005, doi:10.1109/tnn.2004.836197. doi:10.1109/TNN.2004.836197
39. Lacrama, D. L., V. Gherhes, F. Alexa, and T. M. Karnyanszky, "Automatic survey processing using a MLP neural net," 10th Symposium on Neural Network Applications in Electrical Engineering, 123-126, 2010. doi:10.1109/NEUREL.2010.5644092