Deep-learning-based image registration for nano-resolution tomographic reconstruction

被引:11
|
作者
Fu, Tianyu [1 ,2 ]
Zhang, Kai [1 ]
Wang, Yan [1 ]
Li, Jizhou [3 ]
Zhang, Jin [1 ,2 ,3 ]
Yao, Chunxia [1 ,2 ]
He, Qili [1 ,2 ]
Wang, Shanfeng [1 ]
Huang, Wanxia [1 ]
Yuan, Qingxi [1 ]
Pianetta, Piero [3 ]
Liu, Yijin [3 ]
机构
[1] Chinese Acad Sci, Inst High Energy Phys, Xray Opt & Technol Lab, Beijing Synchrotron Radiat Facil, Yuquan Rd, Beijing 100043, Peoples R China
[2] Univ Chinese Acad Sci, Yuquan Rd, Beijing 100043, Peoples R China
[3] SLAC Natl Accelerator Lab, Stanford Synchrotron Radiat Lightsource, Menlo Pk, CA 94025 USA
基金
中国国家自然科学基金;
关键词
full-field transmission X-ray microscopy; nano-tomography; image registration; deep learning; residual neural network; X-RAY MICROSCOPY; SPATIAL-RESOLUTION; TILT SERIES; ALIGNMENT; NANOTOMOGRAPHY;
D O I
10.1107/S1600577521008481
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
Nano-resolution full-field transmission X-ray microscopy has been successfully applied to a wide range of research fields thanks to its capability of non-destructively reconstructing the 3D structure with high resolution. Due to constraints in the practical implementations, the nano-tomography data is often associated with a random image jitter, resulting from imperfections in the hardware setup. Without a proper image registration process prior to the reconstruction, the quality of the result will be compromised. Here a deep-learning-based image jitter correction method is presented, which registers the projective images with high efficiency and accuracy, facilitating a high-quality tomographic reconstruction. This development is demonstrated and validated using synthetic and experimental datasets. The method is effective and readily applicable to a broad range of applications. Together with this paper, the source code is published and adoptions and improvements from our colleagues in this field are welcomed.
引用
收藏
页码:1909 / 1915
页数:7
相关论文
共 50 条
  • [1] Deep-learning-based ring artifact correction for tomographic reconstruction
    Fu, Tianyu
    Wang, Yan
    Zhang, Kai
    Zhang, Jin
    Wang, Shanfeng
    Huang, Wanxia
    Wang, Yaling
    Yao, Chunxia
    Zhou, Chenpeng
    Yuan, Qingxi
    JOURNAL OF SYNCHROTRON RADIATION, 2023, 30 (Pt 3) : 620 - 626
  • [2] Deep learning for tomographic image reconstruction
    Wang, Ge
    Ye, Jong Chul
    De Man, Bruno
    NATURE MACHINE INTELLIGENCE, 2020, 2 (12) : 737 - 748
  • [3] Deep learning for tomographic image reconstruction
    Ge Wang
    Jong Chul Ye
    Bruno De Man
    Nature Machine Intelligence, 2020, 2 : 737 - 748
  • [4] Deep-Learning-Based Image Reconstruction and Enhancement in Optical Microscopy
    de Haan, Kevin
    Rivenson, Yair
    Wu, Yichen
    Ozcan, Aydogan
    PROCEEDINGS OF THE IEEE, 2020, 108 (01) : 30 - 50
  • [5] Deep-learning-based image reconstruction for compressed ultrafast photography
    Ma, Yayao
    Feng, Xiaohua
    Gao, Liang
    OPTICS LETTERS, 2020, 45 (16) : 4400 - 4403
  • [6] Deep Learning-Based Dictionary Learning and Tomographic Image Reconstruction
    Rudzusika, Jevgenija
    Koehler, Thomas
    Oktem, Ozan
    SIAM JOURNAL ON IMAGING SCIENCES, 2022, 15 (04): : 1729 - 1764
  • [7] Improving image quality with super-resolution deep-learning-based reconstruction in coronary CT angiography
    Nagayama, Yasunori
    Emoto, Takafumi
    Kato, Yuki
    Kidoh, Masafumi
    Oda, Seitaro
    Sakabe, Daisuke
    Funama, Yoshinori
    Nakaura, Takeshi
    Hayashi, Hidetaka
    Takada, Sentaro
    Uchimura, Ryutaro
    Hatemura, Masahiro
    Tsujita, Kenichi
    Hirai, Toshinori
    EUROPEAN RADIOLOGY, 2023, 33 (12) : 8488 - 8500
  • [8] Improving image quality with super-resolution deep-learning-based reconstruction in coronary CT angiography
    Yasunori Nagayama
    Takafumi Emoto
    Yuki Kato
    Masafumi Kidoh
    Seitaro Oda
    Daisuke Sakabe
    Yoshinori Funama
    Takeshi Nakaura
    Hidetaka Hayashi
    Sentaro Takada
    Ryutaro Uchimura
    Masahiro Hatemura
    Kenichi Tsujita
    Toshinori Hirai
    European Radiology, 2023, 33 : 8488 - 8500
  • [9] Deep-learning-based deformable image registration of head CT and MRI scans
    Ratke, Alexander
    Darsht, Elena
    Heinzelmann, Feline
    Kroeninger, Kevin
    Timmermann, Beate
    Baeumer, Christian
    FRONTIERS IN PHYSICS, 2023, 11
  • [10] High-resolution bathymetry by deep-learning-based image superresolution
    Sonogashira, Motoharu
    Shonai, Michihiro
    Iiyama, Masaaki
    PLOS ONE, 2020, 15 (07):