Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Acta Optica Sinica, Volume. 41, Issue 9, 0911005(2021)

Low-Dose CT 3D Reconstruction Using Convolutional Sparse Coding and Gradient L0-Norm

Yanqin Kang1,2, Jin Liu1,2、*, Yong Wang1, Jun Qiang1, Yunbo Gu2,3, and Yang Chen2,3
Author Affiliations
  • 1College of Computer and Information, Anhui Polytechnic University, Wuhu, Anhui 241000, China
  • 2Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing, Jiangsu 210096, China
  • 3Laboratory of Image Science and Technology, Southeast University, Nanjing, Jiangsu 210096, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (12)
    Equations (0)
    References (23)
    Cited By (6)
    Tools
    Paper Information
    Topics
    Figures & Tables(12)
    Multi-scale online convolutional sparse coding and gradient L0 norm LDCT 3D reconstruction algorithm flow

    Fig. 1. Multi-scale online convolutional sparse coding and gradient L0 norm LDCT 3D reconstruction algorithm flow

    Download full size
    3D schematic of filter sets of different sizes after iterative convergence. (a) 8×8×4; (b) 12×12×6; (c) 16×16×8

    Fig. 2. 3D schematic of filter sets of different sizes after iterative convergence. (a) 8×8×4; (b) 12×12×6; (c) 16×16×8

    Download full size
    Reconstruction results of data A under different algorithms. (a) RD-FBP algorithm; (b) LD-FBP algorithm; (c) LD-FCR algorithm; (d) LD-WCSC algorithm; (e) LD-MOCSC algorithm; (f) LD-L0MOCSC algorithm

    Fig. 3. Reconstruction results of data A under different algorithms. (a) RD-FBP algorithm; (b) LD-FBP algorithm; (c) LD-FCR algorithm; (d) LD-WCSC algorithm; (e) LD-MOCSC algorithm; (f) LD-L0MOCSC algorithm

    Download full size
    Reconstruction results of data B under different algorithms. (a) RD-FBP algorithm; (b) LD-FBP algorithm; (c) LD-FCR algorithm; (d) LD-WCSC algorithm; (e) LD-MOCSC algorithm; (f) LD-L0MOCSC algorithm

    Fig. 4. Reconstruction results of data B under different algorithms. (a) RD-FBP algorithm; (b) LD-FBP algorithm; (c) LD-FCR algorithm; (d) LD-WCSC algorithm; (e) LD-MOCSC algorithm; (f) LD-L0MOCSC algorithm

    Download full size
    NPS of reconstruction results by different algorithms. (a) LD-FBP algorithm; (b) LD-FCR algorithm; (c) LD-WCSC algorithm; (d) LD-MOCSC algorithm; (e) LD-L0MOCSC algorithm

    Fig. 5. NPS of reconstruction results by different algorithms. (a) LD-FBP algorithm; (b) LD-FCR algorithm; (c) LD-WCSC algorithm; (d) LD-MOCSC algorithm; (e) LD-L0MOCSC algorithm

    Download full size
    Reconstruction results of data C under different algorithms. (a) LD-FBP algorithm; (b) LD-FCR algorithm; (c) LD-WCSC algorithm; (d) LD-MOCSC algorithm; (e) LD-L0MOCSC algorithm

    Fig. 6. Reconstruction results of data C under different algorithms. (a) LD-FBP algorithm; (b) LD-FCR algorithm; (c) LD-WCSC algorithm; (d) LD-MOCSC algorithm; (e) LD-L0MOCSC algorithm

    Download full size
    CNR quantification results in different regions of data C reconstructed image. (a) Cross-axial slice #120; (b) coronal slice #23

    Fig. 7. CNR quantification results in different regions of data C reconstructed image. (a) Cross-axial slice #120; (b) coronal slice #23

    Download full size
    Influence of simulated data on performance of L0MOCSC algorithm under different parameters. (a) Number of different filters; (b) size of different filters

    Fig. 8. Influence of simulated data on performance of L0MOCSC algorithm under different parameters. (a) Number of different filters; (b) size of different filters

    Download full size
    Reconstruction results of different regularization parameters. (a) λ; (b) β; (c) η; (d) γ

    Fig. 9. Reconstruction results of different regularization parameters. (a) λ; (b) β; (c) η; (d) γ

    Download full size
    Performance iteration curves of different algorithms under different indexes. (a) PSNR; (b) SSIM

    Fig. 10. Performance iteration curves of different algorithms under different indexes. (a) PSNR; (b) SSIM

    Download full size

    • Table 1. Quantitative results of different algorithms

      View table

      Table 1. Quantitative results of different algorithms

      AlgorithmPSNR /dBSSIM
      Data AData BData AData B
      FBP33.49±2.5636.24±1.200.8016±0.06560.8705±0.0260
      FCR37.65±1.0036.69±0.740.9066±0.02800.8775±0.0208
      WCSC37.84±0.5139.66±0.680.9085±0.02130.8912±0.0206
      MOCSC37.60±0.7839.31±0.610.9217±0.02410.9360±0.0101
      L0MOCSC38.32±0.6740.69±0.740.9288±0.01540.9416±0.0056

    • Table 2. Calculation time and benefits different algorithms

      View table

      Table 2. Calculation time and benefits different algorithms

      Algorithmdata Adata C
      Time per iteration /sPSNR /dBTime per iteration /sCNR
      FCR187±8.54.11224±7.30.22
      WCSC144±6.14.34179±6.50.25
      MOCSC216±5.44.37291±6.40.32
      L0MOCSC278±5.64.96364±6.80.36
    Tools

    Get Citation

    Copy Citation Text

    Yanqin Kang, Jin Liu, Yong Wang, Jun Qiang, Yunbo Gu, Yang Chen. Low-Dose CT 3D Reconstruction Using Convolutional Sparse Coding and Gradient L0-Norm[J]. Acta Optica Sinica, 2021, 41(9): 0911005

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Imaging Systems

    Received: Nov. 3, 2020

    Accepted: Dec. 8, 2020

    Published Online: May. 10, 2021

    The Author Email: Liu Jin (liujin@ahpu.edu.cn)

    DOI:10.3788/AOS202141.0911005

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology