Limited-Angle CT Reconstruction with Generative Adversarial Network Sinogram Inpainting and Unsupervised Artifact Removal

被引:5
作者
Xie, En [1 ]
Ni, Peijun [2 ]
Zhang, Rongfan [2 ]
Li, Xiongbing [1 ]
机构
[1] Cent South Univ, Sch Traff & Transportat Engn, Changsha 410075, Peoples R China
[2] Inner Mongolia Met Mat Res Inst, Ningbo 315103, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 12期
基金
中国国家自然科学基金;
关键词
sinogram inpainting; generative adversarial network; limited-angle CT reconstruction; image reconstruction; artificial intelligence; machine learning; IMAGE-RECONSTRUCTION; TV;
D O I
10.3390/app12126268
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
High-quality limited-angle computed tomography (CT) reconstruction is in high demand in the medical field. Being unlimited by the pairing of sinogram and the reconstructed image, unsupervised methods have attracted wide attention from researchers. The reconstruction limit of the existing unsupervised reconstruction methods, however, is to use [0 degrees, 120 degrees] of projection data, and the quality of the reconstruction still has room for improvement. In this paper, we propose a limited-angle CT reconstruction generative adversarial network based on sinogram inpainting and unsupervised artifact removal to further reduce the angle range limit and to improve the image quality. We collected a large number of CT lung and head images and Radon transformed them into missing sinograms. Sinogram inpainting network is developed to complete missing sinograms, based on which the filtered back projection algorithm can output images with most artifacts removed; then, these images are mapped to artifact-free images by using artifact removal network. Finally, we generated reconstruction results sized 512x512 that are comparable to full-scan reconstruction using only [0 degrees, 90 degrees] of limited sinogram projection data. Compared with the current unsupervised methods, the proposed method can reconstruct images of higher quality.
引用
收藏
页数:15
相关论文
共 29 条
  • [1] Edge guided image reconstruction in linear scan CT by weighted alternating direction TV minimization
    Cai, Ailong
    Wang, Linyuan
    Zhang, Hanming
    Yan, Bin
    Li, Lei
    Xi, Xiaoqi
    Li, Jianxin
    [J]. JOURNAL OF X-RAY SCIENCE AND TECHNOLOGY, 2014, 22 (03) : 335 - 349
  • [2] Globally convergent edge-preserving regularized reconstruction: An application to limited-angle tomography
    Delaney, AH
    Bresler, Y
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 1998, 7 (02) : 204 - 221
  • [3] Characterization and reduction of artifacts in limited angle tomography
    Frikel, Juergen
    Quinto, Eric Todd
    [J]. INVERSE PROBLEMS, 2013, 29 (12)
  • [4] A NEW FRAMEWORK FOR SPARSE REGULARIZATION IN LIMITED ANGLE X-RAY TOMOGRAPHY
    Frikel, Juergen
    [J]. 2010 7TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2010, : 824 - 827
  • [5] Artifacts in Digital Breast Tomosynthesis
    Geiser, William R.
    Einstein, Samuel A.
    Yang, Wei-Tse
    [J]. AMERICAN JOURNAL OF ROENTGENOLOGY, 2018, 211 (04) : 926 - 932
  • [6] Half-scan artifact correction using generative adversarial network for dental CT
    Hegazy, Mohamed A. A.
    Cho, Myung Hye
    Lee, Soo Yeol
    [J]. COMPUTERS IN BIOLOGY AND MEDICINE, 2021, 132
  • [7] Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics
    Higaki, Toru
    Nakamura, Yuko
    Zhou, Jian
    Yu, Zhou
    Nemoto, Takuya
    Tatsugami, Fuminari
    Awai, Kazuo
    [J]. ACADEMIC RADIOLOGY, 2020, 27 (01) : 82 - 87
  • [8] Improvement of image quality at CT and MRI using deep learning
    Higaki, Toru
    Nakamura, Yuko
    Tatsugami, Fuminari
    Nakaura, Takeshi
    Awai, Kazuo
    [J]. JAPANESE JOURNAL OF RADIOLOGY, 2019, 37 (01) : 73 - 80
  • [9] SHANNON SAMPLING THEOREM - ITS VARIOUS EXTENSIONS AND APPLICATIONS - TUTORIAL REVIEW
    JERRI, AJ
    [J]. PROCEEDINGS OF THE IEEE, 1977, 65 (11) : 1565 - 1596
  • [10] Development of Limited-Angle Iterative Reconstruction Algorithms with Context Encoder-Based Sinogram Completion for Micro-CT Applications
    Jin, Shih-Chun
    Hsieh, Chia-Jui
    Chen, Jyh-Cheng
    Tu, Shih-Huan
    Chen, Ya-Chen
    Hsiao, Tzu-Chien
    Liu, Angela
    Chou, Wen-Hsiang
    Chu, Woei-Chyn
    Kuo, Chih-Wei
    [J]. SENSORS, 2018, 18 (12)