-
由于流场中的微粒分布状态能够充分表征场的特性,因此通过稀疏采样实现快速和高质量的粒子场成像始终是实验流体力学等领域高度期盼的.近年来,随着深度学习应用于粒子计算层析成像,如何提高神经网络的处理效率和质量以消除稀疏采样所致的粒子层析图像伪影噪声仍然是一个挑战性课题.为解决这一问题,本文提出了一种新的抑制粒子场层析成像伪影噪声和提高网络效率的神经网络方法.该方法在设计上包含了轻量化双残差下采样图像压缩和特征识别提取、快速特征收敛的上采样图像恢复,以及基于经典计算层析成像算法的优化信噪比网络输入样本集构建.对整个成像系统的模拟分析和实验测试表明,相较于经典的U-net和Resnet50网络方法,本文提出的方法不仅在输出/输入的粒子图像信噪比、重建像的残余伪影噪声(即鬼粒子占比)和有效粒子损失比方面获得了极大的改进,而且也显著提高了网络的训练效率.这对发展基于稀疏采样的快速和高质量粒子场计算层析成像提供了一个新的有效方法.The realization of fast and high-quality three-dimensional particle-field image characterization is always highly desired in the areas, such as experimental fluid mechanics and biomedicine, etc., as the micro-particle distribution status in a flow-field can characterize the field properties well. In the particle-field image reconstruction and characterization, a popularly-used approach at present is the computed tomography. The great advantage of the computed tomography for particle-field image reconstruction lies in that the full particle spatial distribution can be obtained and presented due to multi-angle sampling.
Recently, with the development and application of deep learning techniques in the computed tomography, the image quality is greatly improved by means of the powerful learning ability of a deep learning network. In addition, the deep learning application also makes it possible to speed up the computed tomographic imaging process from sparse-sampling due to the strong image feature extraction ability of the network. However, sparse-sampling would lead to insufficient acquirement of the object information during sampling for the computed tomography. Therefore, a sort of artifact noise would emerge and accompany with the reconstructed images, and thus severely affect the image quality. As there is no universal network approach that can be applicable to all types of objects in the suppression of artifact noise, it is still a challenge in removing the sparse-sampling-induced artifact noise in the computed tomography by now.
Therefore, we propose and develop a specific lightweight residual and enhanced convergence neural network (LREC-net) approach for suppressing the artifact noise in the particle-field computed tomography here. In this method, the network input dataset is also optimized in signal-to-noise ratio (SNR) to reduce the input noise and ensure the effective particle image feature extraction of the network during the imaging process.
In the LREC-net architecture design, a five layers of lightweight and dual-residual down-sampling are constructed on the basis of typical U-net and Resnet50 to make the LREC-net to be more suitable for the particle-field image reconstruction. Moreover, a fast feature convergence module for rapid particle-field feature acquirement is added to up-sampling process of the network to further promote the network processing efficiency. Apart from the design of LREC-net network itself, the optimization of network input dataset in SNR of images is achieved by finding a fit image reconstruction algorithm that can produce higher-SNR particle images in the computed tomography. This achievement reduces the input noise as much as possible and ensure effective particle-field feature extraction by the network.
The simulation analysis and experimental test verify effectiveness of the proposed LREC-net method, which involve the evaluations of SNR changes of the input-output images through the network, the proportion of residual artifact noise as ghost-particles (GPP) in the reconstructed images, and the valid-particle loss proportion (PLP). In contrast to the performances of U-net and Resnet50 under the same imaging conditions, all the data in SNR, GPP and PLP show the great improvement of the image quality due to the application of LREC-net method. Meanwhile, the designed LREC-net method also enhances the network running efficiency to a large extent due to the remarkable reduction of training time. Therefore, this work provides a new and effective approach for developing sparse-sampling-based fast and high-quality particle-field computed tomography.-
Keywords:
- Particle field imaging /
- Computed tomography /
- Deep learning /
- Noise suppression
-
[1] Yang L, Qiu Z, Alan H, Lu W 2012 IEEE T. Bio-Med. Eng. 59 7
[2] Nayak A R, Malkiel Ed, McFarland M N, Twardowski M S, Sullivan J M 2021 Front. Mar. Sci. 7
[3] Healy S, Bakuzis A F, Goodwill P W, Attaluri A, Bulte J M, Ivkov R 2022 Wires. Nanomed. Nanobi. 14, e1779
[4] Gao Q, Wang H, Shen G 2013 Chinese Sci. Bull. 58 36
[5] Oudheusden B W V 2013 Meas. Sci. Technol. 24 032001
[6] Sun Z, Yang L, Wu H, Wu X 2020 J. Environ. Sci. 89
[7] Arhatari B D, Riessen G V, Peele A 2012 Opt. Express 20 21
[8] Vainiger A, Schechner Y Y, Treibitz T, Avin A, Timor D S 2019 Opt. Express 27 12
[9] Cernuschi F, Rothleitner C, Clausen S, Neuschaefer-Rube U, Illemann J, Lorenzoni L, Guardamagna C, Larsen H E 2017 Powder Technol. 318
[10] Wang H, Gao Q, Wei R, Wang J 2016 Exp. Fluids 57 87
[11] Kahnt M, Beche J, Brückner D, Fam Y, Sheppard T, Weissenberger T, Wittwer F, Grunwaldt J, Schwieger W, Schroer C G 2019 Optica 6 10
[12] Zhou X, Dai N, Cheng X, Thompson A, Leach R 2022 Powder Technol. 397 117018
[13] Lell M M, Kachelrieß M 2020 Invest. Radiol. 55 1
[14] Chen H, Zhang Y, Zhang W, Liao P, Li K, Zhou J, Wang G 2017 Biomed. Opt. Express 8 2
[15] Qian K, Wang Y, Shi Y, Zhu X X 2022 IEEE Trans. Geosci. Remote Sens. 60 4706116
[16] Wei C, Schwarm K K, Pineda D I, Spearrin R 2021 Opt. Express 29 14
[17] Zhang Z, Liang X, Dong X, Xie Y, Cao G 2018 IEEE T. Med. Imaging 37 6
[18] Jin K H, McCann M T, Froustey E, Unser M 2017 IEEE T. Image Process. 26 9
[19] Han Y, Ye J C 2018 IEEE T. Med. Imaging 37 6
[20] Gao Q, Pan S, Wang H, Wei R, Wang J 2021 Advances in Aerodynamics 3 28
[21] Wu D, Kim K, Fakhri G EI, Li Q 2017 IEEE T. Med. Imaging 36 12
[22] Liang J, Cai S, Xu C, Chu J 2020 IET Cyber-Syst Robot 2 1
[23] Wu W, Hu D, Niu C, Yu H, Vardhanabhuti V, Wang G 2021 IEEE T. Med. Imaging 40 11.
[24] Xia W, Yang Z, Zhou Q, Lu Z, Wang Z, Zhang Y 2022 Medical Image Computing and Computer Assisted Intervention 13436
[25] Zhang C, Li Y, Chen G 2021 Med. Phys. 48 10
[26] Cheslerean-Boghiu T, Hofmann F C, Schultheiß M, Pfeiffer F, Pfeiffer D, Lasser T 2023 IEEE T. Comput. Imag. 9
[27] Gmitro A F, Tresp V, Gindi G R 1990 IEEE T. Med. Imaging 9 4
[28] Horn B K P 1979 Proc. IEEE 67 12
[29] Chen G H 2003 Med. Phys. 30 6
[30] Chen G H, Tokalkanahalli R, Zhuang T, Nett B E, Hsieh J 2006 Med. Phys. 33 2
[31] Feldkamp L A, Davis L C, Kress J W 1984 J. Opt. Soc. Am. A 1 6
[32] Yang H, Liang K, Kang K, Xing Y 2019 Nucl. Sci. Tech. 30 59
[33] Katsevich A 2002 Phys. Med. Biol. 47 15
[34] Zeng G L 2010 Medical image reconstruction: a conceptual tutorial Berlin Springer
[35] Lechuga L, Weidlich G A 2016 Cureus 8 9
[36] Schmidt-Hieber J 2020 Ann. Statist. 48 4
[37] Ioffe S, Szegedy C 2015 32nd International Conference on Machine Learning Lile France 37
[38] Ronneberger O, Fischer P, Brox T 2015 Medical Image Computing and Computer-Assisted Intervention 9351
[39] He K, Zhang X, Ren S, Sun J 2016 IEEE Conference on Computer Vision and Pattern Recognition Las Vegas 770
[40] Ramachandran G N, Lakshminarayanan A V, 1971 Proceedings of the National Academy of Sciences of the United States of America 68 9
[41] Kingma D P, Ba J L 2015 arXiv:1412.6980v9
[42] Bougourzi F, Dornaika F, Taleb-Ahmed A 2022 Knowl-Based Syst. 242
计量
- 文章访问数: 102
- PDF下载量: 3
- 被引次数: 0