Development of Limited-Angle Iterative Reconstruction Algorithms with Context Encoder-Based Sinogram Completion for Micro-CT Applications

被引:10
作者
Jin, Shih-Chun [1 ]
Hsieh, Chia-Jui [2 ]
Chen, Jyh-Cheng [1 ]
Tu, Shih-Huan [3 ]
Chen, Ya-Chen [4 ]
Hsiao, Tzu-Chien [3 ,5 ]
Liu, Angela [6 ]
Chou, Wen-Hsiang [1 ]
Chu, Woei-Chyn [2 ]
Kuo, Chih-Wei [7 ]
机构
[1] Natl Yang Ming Univ, Dept Biomed Imaging & Radiol Sci, Taipei 11221, Taiwan
[2] Natl Yang Ming Univ, Dept Biomed Engn, Taipei 11221, Taiwan
[3] Natl Chiao Tung Univ, Inst Biomed Engn, Hsinchu 30010, Taiwan
[4] Natl Chiao Tung Univ, Inst Comp Sci & Engn, Hsinchu 30010, Taiwan
[5] Natl Chiao Tung Univ, Dept Comp Sci & Engn, Hsinchu 30010, Taiwan
[6] Univ Texas Austin, Dept Biomed Engn, Austin, TX 78712 USA
[7] Natl Chung Shan Inst Sci Technol, Mat Electroopt Res Div, Taoyuan 32599, Taiwan
关键词
context encoder (CE); limited-angle iterative reconstruction (LAIR); generative adversarial network (GAN); IMAGE-RECONSTRUCTION; COMPUTED-TOMOGRAPHY;
D O I
10.3390/s18124458
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
Limited-angle iterative reconstruction (LAIR) reduces the radiation dose required for computed tomography (CT) imaging by decreasing the range of the projection angle. We developed an image-quality-based stopping-criteria method with a flexible and innovative instrument design that, when combined with LAIR, provides the image quality of a conventional CT system. This study describes the construction of different scan acquisition protocols for micro-CT system applications. Fully-sampled Feldkamp (FDK)-reconstructed images were used as references for comparison to assess the image quality produced by these tested protocols. The insufficient portions of a sinogram were inpainted by applying a context encoder (CE), a type of generative adversarial network, to the LAIR process. The context image was passed through an encoder to identify features that were connected to the decoder using a channel-wise fully-connected layer. Our results evidence the excellent performance of this novel approach. Even when we reduce the radiation dose by 1/4, the iterative-based LAIR improved the full-width half-maximum, contrast-to-noise and signal-to-noise ratios by 20% to 40% compared to a fully-sampled FDK-based reconstruction. Our data support that this CE-based sinogram completion method enhances the efficacy and efficiency of LAIR and that would allow feasibility of limited angle reconstruction.
引用
收藏
页数:18
相关论文
共 27 条
  • [1] Solving ill-posed inverse problems using iterative deep neural networks
    Adler, Jonas
    Oktem, Ozan
    [J]. INVERSE PROBLEMS, 2017, 33 (12)
  • [2] [Anonymous], 2015, ARXIV PREPRINT ARXIV
  • [3] [Anonymous], 2017, ARXIV170900584
  • [4] Evaluation of sparse-view reconstruction from flat-panel-detector cone-beam CT
    Bian, Junguo
    Siewerdsen, Jeffrey H.
    Han, Xiao
    Sidky, Emil Y.
    Prince, Jerry L.
    Pelizzari, Charles A.
    Pan, Xiaochuan
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2010, 55 (22) : 6575 - 6599
  • [5] Micro-CT Based Experimental Liver Imaging Using a Nanoparticulate Contrast Agent: A Longitudinal Study in Mice
    Boll, Hanne
    Nittka, Stefanie
    Doyon, Fabian
    Neumaier, Michael
    Marx, Alexander
    Kramer, Martin
    Groden, Christoph
    Brockmann, Marc A.
    [J]. PLOS ONE, 2011, 6 (09):
  • [6] High-Speed Single-Breath-Hold Micro-Computed Tomography of Thoracic and Abdominal Structures in Mice Using a Simplified Method for Intubation
    Boll, Hanne
    Bag, Simona
    Schambach, Sebastian J.
    Doyon, Fabian
    Nittka, Stefanie
    Kramer, Martin
    Groden, Christoph
    Brockmann, Marc A.
    [J]. JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 2010, 34 (05) : 783 - 790
  • [7] Candès EJ, 2008, IEEE SIGNAL PROC MAG, V25, P21, DOI 10.1109/MSP.2007.914731
  • [8] Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network
    Chen, Hu
    Zhang, Yi
    Kalra, Mannudeep K.
    Lin, Feng
    Chen, Yang
    Liao, Peixi
    Zhou, Jiliu
    Wang, Ge
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (12) : 2524 - 2535
  • [9] A limited-angle CT reconstruction method based on anisotropic TV minimization
    Chen, Zhiqiang
    Jin, Xin
    Li, Liang
    Wang, Ge
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2013, 58 (07) : 2119 - 2141
  • [10] LIMITED TOMOGRAPHY RECONSTRUCTION VIA TIGHT FRAME AND SIMULTANEOUS SINOGRAM EXTRAPOLATION
    Choi, Jae Kyu
    Dong, Bin
    Zhang, Xiaoqun
    [J]. JOURNAL OF COMPUTATIONAL MATHEMATICS, 2016, 34 (06) : 575 - 589