| ELECTROMAGNETISM, OPTICS, ACOUSTICS, HEAT TRANSFER, CLASSICAL MECHANICS, AND FLUID DYNAMICS |
Prev
Next
|
|
|
Deep learning for image reconstruction in thermoacoustic tomography |
| Qiwen Xu(徐启文)1, Zhu Zheng(郑铸)2, and Huabei Jiang(蒋华北)3,† |
1 School of Electronic Science and Engineering(National Exemplary School of Microelectronics), University of Electronic Science and Technology of China, Chengdu 611731, China;
2 School of Optoelectronic Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China;
3 Department of Medical Engineering, University of South Florida, Tampa, FL 33620, USA |
|
|
|
|
Abstract Microwave-induced thermoacoustic tomography (TAT) is a rapidly-developing noninvasive imaging technique that integrates the advantages of microwave imaging and ultrasound imaging. While an image reconstruction algorithm is critical for the TAT, current reconstruction methods often creates significant artifacts and are computationally costly. In this work, we propose a deep learning-based end-to-end image reconstruction method to achieve the direct reconstruction from the sinogram data to the initial pressure density image. We design a new network architecture TAT-Net to transfer the sinogram domain to the image domain with high accuracy. For the scenarios where realistic training data are scarce or unavailable, we use the finite element method (FEM) to generate synthetic data where the domain gap between the synthetic and realistic data is resolved through the signal processing method. The TAT-Net trained with synthetic data is evaluated through both simulations and phantom experiments and achieves competitive performance in artifact removal and robustness. Compared with other state-of-the-art reconstruction methods, the TAT-Net method can reduce the root mean square error to 0.0143, and increase the structure similarity and peak signal-to-noise ratio to 0.988 and 38.64, respectively. The results obtained indicate that the TAT-Net has great potential applications in improving image reconstruction quality and fast quantitative reconstruction.
|
Received: 30 April 2021
Revised: 11 June 2021
Accepted manuscript online: 23 June 2021
|
|
PACS:
|
43.35.Ud
|
(Thermoacoustics, high temperature acoustics, photoacoustic effect)
|
| |
87.85.Pq
|
(Biomedical imaging)
|
| |
87.57.nf
|
(Reconstruction)
|
| |
84.35.+i
|
(Neural networks)
|
|
Corresponding Authors:
Huabei Jiang
E-mail: hjiang1@usf.edu
|
Cite this article:
Qiwen Xu(徐启文), Zhu Zheng(郑铸), and Huabei Jiang(蒋华北) Deep learning for image reconstruction in thermoacoustic tomography 2022 Chin. Phys. B 31 024302
|
[1] Zheng Z and Jiang H B 2019 Quant. Imaging Med. Surg. 9 625
[2] Zheng Z, Huang L and Jiang H 2019 International Applied Computational Electromagnetics Society Symposium, August 8-11, 2019, Nanjing, China, 1-2
[3] Zheng Z, Jiang Y, Huang L, Zhao Y and Jiang H 2020 J. Xray Sci. Technol. 28 137
[4] Chi Z, Zhao Y, Yang J, Li T, Zhang G and Jiang H 2019 IEEE Trans. Biomed. Eng. 66 1598
[5] Huang L, Yao L, Liu L X, Rong J and Jiang H B 2012 Appl. Phys. Lett. 101 244106
[6] Luo W, Ji Z, Yang S and Xing D 2018 Phys. Rev. Appl. 10 024044
[7] Xu F, Ji Z, Chen Q, Yang S and Xing D 2019 IEEE Trans. Med. Imaging 38 205
[8] Kruger R A, Kopecky K K, Aisen A M, Reinecke D R, Kruger G A and Kiser W L 1999 Radiology 211 275
[9] Fu Y, Ji Z, Ding W, Ye F and Lou C 2014 Med. Phys. 41 110701
[10] Ji Z, Lou C, Yang S and Xing D 2012 Med. Phys. 39 6738
[11] Wang B, Zhao Z, Liu S, Nie Z and Liu Q 2017 Appl. Phys. Lett. 111 223701
[12] Wang X, Bauer D R, Witte R and Xin H 2012 IEEE Trans. Biomed. Eng. 59 2782
[13] Patch S K and See W A 2016 Photons Plus Ultrasound:Imaging and Sensing, March 15, 2016, San Francisco, USA
[14] Eckhart A T, Balmer R T, See W A and Patch S K 2011 IEEE Trans. Biomed. Eng. 58 2238
[15] Huang Y, Kellnberger S, Sergiadis G and Ntziachristos V 2018 Sci. Rep. 8 15522
[16] Zheng Z, Huang L and Jiang H 2018 Appl. Phys. Lett. 113 253702
[17] Zhao Y, Chi Z, Huang L, Zheng Z, Yang J and Jiang H 2017 Journal of Innovative Optical Health Sciences 10 1740001
[18] Mrozowski M, Okoniewski M, Okoniewska E and Stuchly M A 1997 IEEE MTT-S International Microwave Symposium Digest, June 8-13, 1997, Denver, USA, pp. 95-97
[19] Xu M and Wang L V 2005 Phys. Rev. E 71 016706
[20] Haltmeier M 2013 Comput. Math. Appl. 65 1025
[21] Burgholzer P, Bauer-Marschallinger J, Grün H, Haltmeier M and Paltauf G 2007 Inverse Problems 23 S65
[22] Cox B T and Treeby B E 2010 IEEE Trans. Med. Imaging 29 387
[23] Treeby B E, Zhang E Z and Cox B T 2010 Inverse Problems 26 115003
[24] Hristova Y, Kuchment P and Nguyen L 2008 Inverse Problems 24 055006
[25] Yuan Z and Jiang H 2006 Appl. Phys. Lett. 88 231101
[26] Belhachmi Z, Glatz T and Scherzer O 2016 Inverse Problems 32 045005
[27] Huang C, Wang K, Nie L, Wang L V and Anastasio M A 2013 IEEE Trans. Med. Imaging 32 1097
[28] Schwab J, Pereverzyev S and Haltmeier M 2018 Siam Journal on Numerical Analysis 56 160
[29] Wang K, Su R, Oraevsky A A and Anastasio M A 2012 Phys. Med. Biol. 57 5399
[30] Javaherian A and Holman S 2017 IEEE Trans. Med. Imaging 36 696
[31] Arridge S R, Betcke M M, Cox B T, Lucka F and Treeby B E 2016 Inverse Problems 32 115012
[32] Xu Y, Wang L V, Ambartsoumian G and Kuchment P 2004 Med. Phys. 31 724
[33] Zhang Z, Liang X, Dong X, Xie Y and Cao G 2018 IEEE Trans. Med. Imaging 37 1407
[34] Li Y, Li K, Zhang C, Montoya J and Chen G 2019 IEEE Trans. Med. Imaging 38 2469
[35] Yin X, Zhao Q, Liu J, Yang W, Yang J, Quan G, Chen Y, Shu H, Luo L and Coatrieux J 2019 IEEE Trans. Med. Imaging 38 2903
[36] Hammernik K, Würfl T, Pock T and Maier A 2017 Bildverarbeitung für die Medizin, March 1, 2017, Berlin, Germany, pp. 92-97
[37] Kang E, Min J and Ye J C 2017 Med. Phys. 44 360
[38] Gupta H, Jin K H, Nguyen H Q, Mccann M T and Unser M 2018 IEEE Trans. Med. Imaging 37 1440
[39] Han Y S, Yoo J and Ye J C 2016 arXiv:1611.06391
[40] Jin K H, Mccann M T, Froustey E and Unser M 2017 IEEE Trans. Image Process 26 4509
[41] Hammernik K, Klatzer T, Kobler E, Recht M P, Sodickson D K, Pock T and Knoll F 2018 Magn. Reson. Med. 79 3055
[42] Han Y, Yoo J, Kim H H, Shin H J, Sung K and Ye J C 2018 Magn. Reson. Med. 80 1189
[43] Xiang L, Chen Y, Chang W, Zhan Y, Lin W, Wang Q and Shen D 2018 IEEE Trans. Biomed. Eng. 66 2105
[44] Allman D, Reiter A and Bell M a L 2018 IEEE Trans. Med. Imaging 37 1464
[45] Antholzer S, Haltmeier M, Nuster R and Schwab J 2018 Photons Plus Ultrasound:Imaging and Sensing, 2018, San Francisco, USA, 104944U
[46] Boink Y E, Manohar S and Brune C 2019 arXiv:1906.07499
[47] Johnstonbaugh K, Agrawal S, Abhishek D, Homewood M, Karri S P K and Kothapalli S R 2019 Photons Plus Ultrasound:Imaging and Sensing, 2019, San Francisco, USA, 108781L
[48] Allman D, Reiter A and Bell M a L 2017 IEEE International Ultrasonics Symposium, September 6-9, 2017, Washington, USA, pp. 1-4
[49] Lan H, Yang C, Jiang D and Gao F 2019 IEEE International Ultrasonics Symposium, October 6-9, 2019, Glasgow, Scotland, pp. 487-489
[50] Kim K, Wu D, Gong K, Dutta J, Kim J H, Son Y D, Kim H K, Fakhri G E and Li Q 2018 IEEE Trans. Med. Imaging 37 1478
[51] Waibel D, Groehl J, Isensee F, Kirchner T, Maier-Hein K and Maier-Hein L 2018 Photons Plus Ultrasound:Imaging and Sensing, 2018, San Francisco, USA, 104942S
[52] Anas E M A, Zhang H K, Audigier C and Boctor E M 2018 Simulation, Image Processing, and Ultrasound Systems for Assisted Diagnosis and Navigation, September 16-20, 2018, Granada, Spain, pp. 3-11
[53] Lan H, Yang C, Jiang D and Gao F 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, July 23-27, 2019, Berlin, Germany, pp. 7115-7118
[54] Lan H, Zhou K, Yang C, Cheng J, Liu J, Gao S and Gao F 2019 Medical Image Computing and Computer Assisted Intervention, October 13-17, 2019, Shenzhen, China, pp. 273-281
[55] Lan H, Zhou K, Yang C, Liu J, Gao S and Gao F 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, July 23-27, 2019, Berlin, Germany, pp. 6367-6370
[56] Hauptmann A, Lucka F, Betcke M, Huynh N, Adler J, Cox B, Beard P, Ourselin S and Arridge S 2018 IEEE Trans. Med. Imaging 37 1382
[57] Aggarwal H K, Mani M P and Jacob M 2019 IEEE Trans. Med. Imaging 38 394
[58] Odena A, Dumoulin V and Olah C 2016 Distill 1
[59] Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Qiao Y and Loy C C 2019 Computer Vision-ECCV 2018 Workshops, September, 8-14, 2019, Munich, Germany, pp. 63-79
[60] He K, Zhang X, Ren S and Sun J 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, June 27-30, 2016, Las Vegas, USA, pp. 770-778
[61] He K, Zhang X, Ren S and Sun J 2015 IEEE International Conference on Computer Vision, December 7-13, 2015, Santiago, Chile, pp. 1026-1034
[62] Kingma D P and Ba J 2014 arXiv:1412.6980
[63] Paszke A, Gross S, Massa F, et al. 2019 Adv. Neural Inf. Process. Syst. 32 8026
[64] Yao L, Guo G and Jiang H 2010 Med. Phys. 37 3752
[65] Wang B, Xiong W, Su T, Xiao J and Peng K 2018 Appl. Opt. 57 9123
[66] Zhou W, Bovik A C, Sheikh H R and Simoncelli E P 2004 IEEE Trans. Image Process. 13 600
[67] He Y, Shen Y C, Liu C J and Wang L H V 2017 Appl. Phys. Lett. 110 053701 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
