Ptychographic phase retrieval via a deep-learning-assisted iterative algorithm

被引：0

作者：

Yamada, Koki ^{[1
]}

Akaishi, Natsuki ^{[1
]}

Yatabe, Kohei ^{[1
]}

Takayama, Yuki ^{[2
,3
,4
,5
]}

机构：

[1] Department of Electrical Engineering and Computer Science, Tokyo University of Agriculture and Technology, 2-24-16 Naka-cho, Koganei, Tokyo, Japan

[2] International Center for Synchrotron Radiation Innovation Smart, Tohoku University, 468-1 Aoba-ku, Sendai, Japan

[3] Graduate School of Agricultural Science, Tohoku University, 468-1 Aoba-ku, Sendai, Japan

[4] Research Center for Green X-Tech, Green Goals Initiative, Tohoku University, 6-6 Aoba-ku, Sendai, Japan

[5] RIKEN SPring-8 Center, 1-1-1 Kohto, Sayo, Sayo-gun, Hyogo, Japan

来源：

Journal of Applied Crystallography | 1600年 / 57卷

关键词：

Ptychography is a powerful computational imaging technique with microscopic imaging capability and adaptability to various specimens. To obtain an imaging result; it requires a phase-retrieval algorithm whose performance directly determines the imaging quality. Recently; deep neural network (DNN)-based phase retrieval has been proposed to improve the imaging quality from the ordinary model-based iterative algorithms. However; the DNN-based methods have some limitations because of the sensitivity to changes in experimental conditions and the difficulty of collecting enough measured specimen images for training the DNN. To overcome these limitations; a ptychographic phase-retrieval algorithm that combines model-based and DNN-based approaches is proposed. This method exploits a DNN-based denoiser to assist an iterative algorithm like ePIE in finding better reconstruction images. This combination of DNN and iterative algorithms allows the measurement model to be explicitly incorporated into the DNN-based approach; improving its robustness to changes in experimental conditions. Furthermore; to circumvent the difficulty of collecting the training data; it is proposed that the DNN-based denoiser be trained without using actual measured specimen images but using a formula-driven supervised approach that systemically generates synthetic images. In experiments using simulation based on a hard X-ray ptychographic measurement system; the imaging capability of the proposed method was evaluated by comparing it with ePIE and rPIE. These results demonstrated that the proposed method was able to reconstruct higher-spatial-resolution images with half the number of iterations required by ePIE and rPIE; even for data with low illumination intensity. Also; the proposed method was shown to be robust to its hyperparameters. In addition; the proposed method was applied to ptychographic datasets of a Simens star chart and ink toner particles measured at SPring-8 BL24XU; which confirmed that it can successfully reconstruct images from measurement scans with a lower overlap ratio of the illumination regions than is required by ePIE and rPIE. © Koki Yamada et al. 2024;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Journal article (JA)

引用

页码：1323 / 1335

共 50 条

[41] Learning spectral initialization for phase retrieval via deep neural networks
Morales, David
Jerez, Andres
Arguello, Henry
APPLIED OPTICS, 2022, 61 (09) : F25 - F33
[42] Deep learning colorful ptychographic iterative engine lens-less diffraction microscopy
Bian, Yinxu
Jiang, Yannan
Wang, Jiaxiong
Yang, Shenmin
Deng, Weijie
Yang, Xiaofei
Shen, Renbing
Shen, Hua
Kuang, Cuifang
OPTICS AND LASERS IN ENGINEERING, 2022, 150
[43] Deep learning colorful ptychographic iterative engine lens-less diffraction microscopy
Bian, Yinxu
Jiang, Yannan
Wang, Jiaxiong
Yang, Shenmin
Deng, Weijie
Yang, Xiaofei
Shen, Renbing
Shen, Hua
Kuang, Cuifang
Optics and Lasers in Engineering, 2022, 150
[44] A Deep-Learning-Assisted On-Mask Sensor Network for Adaptive Respiratory Monitoring
Fang, Yunsheng
Xu, Jing
Xiao, Xiao
Zou, Yongjiu
Zhao, Xun
Zhou, Yihao
Chen, Jun
ADVANCED MATERIALS, 2022, 34 (24)
[45] Deep-Learning-Assisted Single-Molecule Tracking on a Live Cell Membrane
Wang, Qian
He, Hua
Zhang, Qian
Feng, Zhenzhen
Li, Jiqiang
Chen, Xiaoliang
Liu, Lihua
Wang, Xiaojuan
Ge, Baosheng
Yu, Daoyong
Ren, Hao
Huang, Fang
ANALYTICAL CHEMISTRY, 2021, 93 (25) : 8810 - 8816
[46] Deep-learning-assisted design of multi-degree-of-freedom metamaterial absorber
Wang, Shuqin
Ma, Qiongxiong
Wei, Zhongchao
Wu, Ruihuan
Ding, Wen
Guo, Jianping
PHYSICA SCRIPTA, 2024, 99 (05)
[47] Blind Ptychographic Phase Retrieval via Convergent Alternating Direction Method of Multipliers
Chang, Huibin
Enfedaque, Pablo
Marchesin, Stefano
SIAM JOURNAL ON IMAGING SCIENCES, 2019, 12 (01): : 153 - 185
[48] Deep-Learning-Assisted Topology Identification and Sensor Placement for Active Distribution Network
Hong, Juhua
Zhang, Linyao
Yan, Yufei
Wang, Zeqi
Ren, Pengzhe
MATHEMATICAL PROBLEMS IN ENGINEERING, 2021, 2021
[49] Deep-learning-assisted Fourier transform imaging spectroscopy for hyperspectral fluorescence imaging
Juntunen, Cory
Woller, Isabel M.
Abramczyk, Andrew R.
Sung, Yongjin
SCIENTIFIC REPORTS, 2022, 12 (01)
[50] Deep-learning-assisted designing chiral terahertz metamaterials with asymmetric transmission properties
Gao, Feng
Zhang, Zhen
Xu, Yafei
Zhang, Liuyang
Yan, Ruqiang
Chen, Xuefeng
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA B-OPTICAL PHYSICS, 2022, 39 (06) : 1511 - 1519

← 1 2 3 4 5 →