Vol. 102
Latest Volume
All Volumes
PIERM 115 [2023] PIERM 114 [2022] PIERM 113 [2022] PIERM 112 [2022] PIERM 111 [2022] PIERM 110 [2022] PIERM 109 [2022] PIERM 108 [2022] PIERM 107 [2022] PIERM 106 [2021] PIERM 105 [2021] PIERM 104 [2021] PIERM 103 [2021] PIERM 102 [2021] PIERM 101 [2021] PIERM 100 [2021] PIERM 99 [2021] PIERM 98 [2020] PIERM 97 [2020] PIERM 96 [2020] PIERM 95 [2020] PIERM 94 [2020] PIERM 93 [2020] PIERM 92 [2020] PIERM 91 [2020] PIERM 90 [2020] PIERM 89 [2020] PIERM 88 [2020] PIERM 87 [2019] PIERM 86 [2019] PIERM 85 [2019] PIERM 84 [2019] PIERM 83 [2019] PIERM 82 [2019] PIERM 81 [2019] PIERM 80 [2019] PIERM 79 [2019] PIERM 78 [2019] PIERM 77 [2019] PIERM 76 [2018] PIERM 75 [2018] PIERM 74 [2018] PIERM 73 [2018] PIERM 72 [2018] PIERM 71 [2018] PIERM 70 [2018] PIERM 69 [2018] PIERM 68 [2018] PIERM 67 [2018] PIERM 66 [2018] PIERM 65 [2018] PIERM 64 [2018] PIERM 63 [2018] PIERM 62 [2017] PIERM 61 [2017] PIERM 60 [2017] PIERM 59 [2017] PIERM 58 [2017] PIERM 57 [2017] PIERM 56 [2017] PIERM 55 [2017] PIERM 54 [2017] PIERM 53 [2017] PIERM 52 [2016] PIERM 51 [2016] PIERM 50 [2016] PIERM 49 [2016] PIERM 48 [2016] PIERM 47 [2016] PIERM 46 [2016] PIERM 45 [2016] PIERM 44 [2015] PIERM 43 [2015] PIERM 42 [2015] PIERM 41 [2015] PIERM 40 [2014] PIERM 39 [2014] PIERM 38 [2014] PIERM 37 [2014] PIERM 36 [2014] PIERM 35 [2014] PIERM 34 [2014] PIERM 33 [2013] PIERM 32 [2013] PIERM 31 [2013] PIERM 30 [2013] PIERM 29 [2013] PIERM 28 [2013] PIERM 27 [2012] PIERM 26 [2012] PIERM 25 [2012] PIERM 24 [2012] PIERM 23 [2012] PIERM 22 [2012] PIERM 21 [2011] PIERM 20 [2011] PIERM 19 [2011] PIERM 18 [2011] PIERM 17 [2011] PIERM 16 [2011] PIERM 14 [2010] PIERM 13 [2010] PIERM 12 [2010] PIERM 11 [2010] PIERM 10 [2009] PIERM 9 [2009] PIERM 8 [2009] PIERM 7 [2009] PIERM 6 [2009] PIERM 5 [2008] PIERM 4 [2008] PIERM 3 [2008] PIERM 2 [2008] PIERM 1 [2008]
2021-04-13
Non-Iterative Microwave Imaging Solutions for Inverse Problems Using Deep Learning
By
Progress In Electromagnetics Research M, Vol. 102, 53-63, 2021
Abstract
This paper describes a U-net based Deep Learning (DL) approach in combination with Subspace-Based Variational Born Iterative Method (SVBIM) to provide a solution for quantitative reconstruction of scatterer from the measured scattered field. The proposed technique can be used as an alternative to conventional time consuming and computationally complex iterative methods. This technique comprises of a numerical solver (SVBIM) for generating the initial contrast function and a DL network to reconstruct the scatterer profile from the initial contrast function. Further, the proposed technique is validated against theoretical and experimental results available from the literature. Root Mean Square Error (RMSE) value is used as the metric to measure the accuracy of the reconstructed image. The RMSE values of the proposed method show a significant reduction in the reconstruction error when compared with the recent Back Propagation-Direct Sampling Method (BP-DSM). The proposed method produces an RMSE value of 0.0813 against 0.1070 in the case of simulation (Austria Profile). The error value obtained by validating against the FoamDielExt experimental database in the case of the proposed method is 0.1037 against 0.1631 reported for BP-DSM method.
Citation
Thathamkulam Anjit Ria Benny Philip Cherian Palayyan Mythili , "Non-Iterative Microwave Imaging Solutions for Inverse Problems Using Deep Learning," Progress In Electromagnetics Research M, Vol. 102, 53-63, 2021.
doi:10.2528/PIERM21021304
http://www.jpier.org/PIERM/pier.php?paper=21021304
References

1. Chandra, R., H. Zhou, I. Balasingham, and R. M. Narayanan, "On the opportunities and challenges in microwave medical sensing and imaging," IEEE Transactions on Biomedical Engineering, Vol. 62, No. 7, 1667-1682, 2015.
doi:10.1109/TBME.2015.2432137

2. Ambrosanio, M., P. Kosmas, and V. Pascazio, "A multithreshold iterative DBIM-based algorithm for the imaging of heterogeneous breast tissues," IEEE Transactions on Biomedical Engineering\, Vol. 66, No. 2, 509-520, 2018.
doi:10.1109/TBME.2018.2849648

3. Chen, X., Computational Methods for Electromagnetic Inverse Scattering, Wiley, Hoboken, NJ, USA, 2018.
doi:10.1002/9781119311997

4. Randazzo, A., C. Ponti, A. Fedeli, C. Estatico, P. D'Atanasio, M. Pastorino, and G. Schettini, "A two-step inverse-scattering technique in variable-exponent lebesgue spaces for through-the-wall microwave imaging: Experimental results," IEEE Transactions on Geoscience and Remote Sensing, 2021.

5. Huang, T. and A. S. Mohan, "Microwave imaging of perfect electrically conducting cylinder by micro-genetic algorithm," IEEE Antennas and Propagation Society Symposium, Vol. 1, IEEE, 2004.

6. Semenov, S. Y., et al., "Microwave-tomographic imaging of the high dielectric-contrast objects using different image-reconstruction approaches," IEEE Trans. Microw. Theory Tech., Vol. 53, No. 7, 2284-2294, Jul. 2005.
doi:10.1109/TMTT.2005.850459

7. Rajan, S. D. and G. V. Frisk, "A comparison between the Born and Rytov approximations for the inverse backscattering problem," Geophysics, Vol. 54, 864-871, 1989.
doi:10.1190/1.1442715

8. Majobi, P. and J. LeVetri, "Comparison of TE and TM inversions in the framework of the Gauss-Newton Method," IEEE Transactions on Antennas and Propagation, Vol. 64, 1336-1348, 2010.
doi:10.1109/TAP.2010.2041156

9. Rocca, P., M. Benedetti, M. Donelli, D. Franceschini, and A. Massa, "Evolutionary optimization as applied to inverse problems," Inverse Probl., Vol. 25, 1-41, 2009.

10. Candes, E. J. and M. B. Wakin, "An introduction to compressive sampling," IEEE Signal Processing Magazine, Vol. 25, No. 2, 21-30, 2008.
doi:10.1109/MSP.2007.914731

11. Lustig, M., D. Donoho, and J. M. Pauly, "Sparse MRI: The application of compressed sensing for rapid MR imaging," Magnetic Resonance in Medicine, Vol. 58, No. 6, 1182-1195, 2008.
doi:10.1002/mrm.21391

12. Pan, X. and E. Y. Sidky, "Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization," Physics in Medicine and Biology, Vol. 53, No. 17, 4777-4807, 2008.
doi:10.1088/0031-9155/53/17/021

13. Naghsh, N. Z., A. Ghorbani, and H. Amindavar, "Compressive sensing for microwave breast cancer imaging," IET Signal Processing, Vol. 12, No. 2, 242-246, 2017.
doi:10.1049/iet-spr.2015.0537

14. Rekanos, I. T., "Neural-network-based inverse-scattering technique for online microwave medical imaging," IEEE Transactions on Magnetics, Vol. 38, No. 2, 1061-1064, 2002.
doi:10.1109/20.996272

15. Wei, Z. and X. Chen, "Deep-learning schemes for full-wave nonlinear inverse scattering problems," IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, No. 4, 1849-1860, 2019.
doi:10.1109/TGRS.2018.2869221

16. Guo, R., X. Song, M. Li, F. Yang, S. Xu, and A. Abubakar, "Supervised descent learning technique for 2-D microwave imaging," IEEE Transactions on Antennas and Propagation, Vol. 67, No. 5, 3550-3554, 2019.
doi:10.1109/TAP.2019.2902667

17. Zhang, L., K. Xu, R. Song, X. Z. Ye, G. Wang, and X. Chen, "Learning-based quantitative microwave imaging with a hybrid input scheme," IEEE Sensors Journal, Vol. 20, No. 24, 15007-15013, 2020.
doi:10.1109/JSEN.2020.3012177

18. Geffrin, J.-M., P. Sabouroux, and C. Eyraoud, "Free space experimental scattering database continuation: Experimental set-up and measurement precision," Inverse Probl., Vol. 21, No. 6, 117-130, 2005.
doi:10.1088/0266-5611/21/6/S09

19. Chew, W. C. and Y. M. Wang, "Reconstruction of two-dimensional permittivity distribution using the distorted Born iterative method," IEEE Trans. Medical. Imag., Vol. 9, No. 2, 218-225, 1990.
doi:10.1109/42.56334

20. Anzengruber, S. W. and R. Ramlau, "Convergence rates for morozov’s discrepancy principle using variational inequalities," Inverse Problems, Vol. 27, No. 10, 105007, 2011.
doi:10.1088/0266-5611/27/10/105007

21. Liu, Z. and Z. Nie, "Subspace-based variational born iterative method for solving inverse scattering problems," IEEE Geoscience and Remote Sensing Letters, Vol. 16, No. 7, 1017-1020, Jul. 2019.
doi:10.1109/LGRS.2018.2889886

22. Li, M., O. Semerci, and A. Abubakar, "A contrast source inversion method in the wavelet domain," Inverse Probl., Vol. 29, No. 2, 025015, 2013.
doi:10.1088/0266-5611/29/2/025015

23. Ye, X., X. Chen, Y. Zhong, and K. Agarwal, "Subspace-based optimization method for reconstructing perfectly electric conductors," Progress In Electromagnetic Research, Vol. 100, 119-128, 2010.
doi:10.2528/PIER09111606

24. Zhong, Y. and X. Chen, "An FFT twofold subspace-based optimization method for solving electromagnetic inverse scattering problems," IEEE Transactions on Antennas and Propagation, Vol. 59, No. 3, 914-927, 2011.
doi:10.1109/TAP.2010.2103027

25. Ronneberger, O., P. Fischer, and T. Brox, "U-net: Convolutional networks for biomedical image segmentation," Proc. 18th Int. Conf. Med. Image Comput. Comput.-Assist. Intervention, 234-241, 2015.

26. Yao, H. M., W. E. I. Sha, and L. Jiang, "Two-step enhanced deep learning approach for electromagnetic inverse scattering problems," IEEE Antennas and Wireless Propagation Letters, Vol. 18, No. 11, 2254-2258, Nov. 2019.
doi:10.1109/LAWP.2019.2925578

27. Xu, K., L. Wu, X. Ye, and X. Chen, "Deep learning-based inversion methods for solving inverse scattering problems with phaseless data," IEEE Transactions on Antennas and Propagation, Vol. 68, No. 11, 7457-7470, 2020.
doi:10.1109/TAP.2020.2998171

28. Zhang, Z., "Improved adam optimizer for deep neural networks," 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS), 1-2, Banff, AB, Canada, 2018.

29. Rahangdale, A. and S. Raut, "Deep neural network regularization for feature selection in learning-to-rank," IEEE Access, Vol. 7, 53988-54006, 2019.
doi:10.1109/ACCESS.2019.2902640

30. Deng, L., "The MNIST database of handwritten digit images for machine learning research [Best of the Web]," IEEE Signal Processing Magazine, Vol. 29, No. 6, 141-142, Nov. 2012.
doi:10.1109/MSP.2012.2211477

31. Azghani, M. and F. Marvasti, "L2-regularized iterative weighted algorithm for inverse scattering," IEEE Transactions on Antennas and Propagation, Vol. 64, No. 6, 2293-2300, 2016.
doi:10.1109/TAP.2016.2546385