Deep-learning-based ring artifact correction for tomographic reconstruction

被引:9
|
作者
Fu, Tianyu [1 ,2 ]
Wang, Yan [1 ]
Zhang, Kai [1 ,2 ]
Zhang, Jin [1 ]
Wang, Shanfeng [1 ]
Huang, Wanxia [1 ]
Wang, Yaling [3 ,4 ]
Yao, Chunxia [1 ]
Zhou, Chenpeng [1 ,2 ]
Yuan, Qingxi [1 ]
机构
[1] Chinese Acad Sci, Beijing Synchrotron Radiat Facil, Inst High Energy Phys, Xray Opt & Technol Lab, Yuquan Rd, Beijing 010000, Peoples R China
[2] Univ Chinese Acad Sci, Yuquan Rd, Beijing 010000, Peoples R China
[3] Natl Ctr Nanosci & Technol China, CAS Key Lab Biomed Effects Nanomed & Nanosafety, Beijing 100190, Peoples R China
[4] Natl Ctr Nanosci & Technol China, CAS Ctr Excellence Nanosci, Beijing 100190, Peoples R China
基金
中国国家自然科学基金;
关键词
ring artifact correction; X-ray tomography; deep learning; residual neural network; RAY; NETWORK;
D O I
10.1107/S1600577523000917
中图分类号
TH7 [仪器、仪表];
学科分类号
0804 ; 080401 ; 081102 ;
摘要
X-ray tomography has been widely used in various research fields thanks to its capability of observing 3D structures with high resolution non-destructively. However, due to the nonlinearity and inconsistency of detector pixels, ring artifacts usually appear in tomographic reconstruction, which may compromise image quality and cause nonuniform bias. This study proposes a new ring artifact correction method based on the residual neural network (ResNet) for X-ray tomography. The artifact correction network uses complementary information of each wavelet coefficient and a residual mechanism of the residual block to obtain high-precision artifacts through low operation costs. In addition, a regularization term is used to accurately extract stripe artifacts in sinograms, so that the network can better preserve image details while accurately separating artifacts. When applied to simulation and experimental data, the proposed method shows a good suppression of ring artifacts. To solve the problem of insufficient training data, ResNet is trained through the transfer learning strategy, which brings advantages of robustness, versatility and low computing cost.
引用
收藏
页码:620 / 626
页数:7
相关论文
共 50 条
  • [21] Deep-learning-based motion correction in optical coherence tomography angiography
    Li, Ang
    Du, Congwu
    Pan, Yingtian
    JOURNAL OF BIOPHOTONICS, 2021, 14 (12)
  • [22] Ring artifacts correction in compressed sensing tomographic reconstruction
    Paleo, Pierre
    Mirone, Alessandro
    JOURNAL OF SYNCHROTRON RADIATION, 2015, 22 : 1268 - 1278
  • [23] Deep-learning-based motion artifact reduction for photon-counting spectral cardiac CT
    Huang, Ruihan
    Larsson, Karin
    Persson, Mats U.
    MEDICAL IMAGING 2024: PHYSICS OF MEDICAL IMAGING, PT 1, 2024, 12925
  • [24] Potential of Metal Artifact Reduction (MAR) and Deep Learning-based Reconstruction (DLR) algorithms integration in CT Metal Artifact Correction: A review
    Njiti, M. M.
    Osman, N. D.
    Mansor, M. S.
    Rabaiee, N. A.
    Aziz, M. Z. Abdul
    RADIATION PHYSICS AND CHEMISTRY, 2024, 218
  • [25] Deep-learning-based porous media microstructure quantitative characterization and reconstruction method
    Huang, Yubo
    Xiang, Zhong
    Qian, Miao
    PHYSICAL REVIEW E, 2022, 105 (01)
  • [26] Deep-Learning-Based Multi-Modal Fusion for Fast MR Reconstruction
    Xiang, Lei
    Chen, Yong
    Chang, Weitang
    Zhan, Yiqiang
    Lin, Weili
    Wang, Qian
    Shen, Dinggang
    IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2019, 66 (07) : 2105 - 2114
  • [27] Deep-Learning-Based Framework for PET Image Reconstruction from Sinogram Domain
    Liu, Zhiyuan
    Ye, Huihui
    Liu, Huafeng
    APPLIED SCIENCES-BASEL, 2022, 12 (16):
  • [28] A Deep-Learning-Based Error-Correction Method for Atmospheric Motion Vectors
    Cao, Hang
    Leng, Hongze
    Zhao, Jun
    Zhao, Yanlai
    Zhao, Chengwu
    Li, Baoxu
    REMOTE SENSING, 2024, 16 (09)
  • [30] A Review of Deep-Learning-Based Approaches for Attenuation Correction in Positron Emission Tomography
    Lee, Jae Sung
    IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 2021, 5 (02) : 160 - 184