Stable Learning for Neural Network Tomography by Using Back Projected Image

  • Masaru TeranishiEmail author
  • Keita Oka
  • Masahiro Aramoto
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 290)


This paper presents a stable learning method of the neural network tomography, in case of asymmetrical few view projection. The neural network collocation method (NNCM) is one of effective reconstruction tools for symmetrical few view tomography. But in case of asymmetrical few view, the NNCM tends to unstable and fails to reconstruct appropriate tomographic images. We solve the unstable problem by introducing the back projected image in the early learning stage of NNCM. The numerical simulation with an assumed tomographic image show the effectiveness of the proposed method.


Few view tomography neural network back propagation collocation method inverse problem ill-posed problem model fitting 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Natterer, F.: The Mathematics of Computerized Tomography. Wiley/B. G. Teubner, New York (1986)zbMATHGoogle Scholar
  2. 2.
    Ma, X.F., Fukuhara, M., Takeda, T.: Neural network CT image reconstruction method for small amount of projection data. Nucl. Instrum. Methods in Phys. Res. A 449, 366–377 (2000)CrossRefGoogle Scholar
  3. 3.
    Takeda, T., Ma, X.F.: Ionospheric Tomography by Neural Network Collocation Method. Plasma and Fusion Research 2, S015-1–6 (2007)Google Scholar
  4. 4.
    Nagayama, Y.: Tomography of m = 1 mode in tokamak plasma using least-squares-fitting method and Fourier-Bessel expansions. J. Appl. Phys. 62, 2702 (1987)CrossRefGoogle Scholar
  5. 5.
    Rumelhart, D.E., McClelland, J.L.: PDP Research Group: Parallel Distributed Processing. MIT Press, Cambridge (1986)Google Scholar
  6. 6.
    Liu, Y., Peterson, B.J., Iwama, N., Konoshima, S.: LHD Experiment Group, JT-60 team: Application of Tomographic Imaging to Multi-pixel Bolometric Measurements. Plasma and Fusion Research 2, S1124-1–4 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of Information Systems and Management, Faculty of Applied Information ScienceHiroshima Institute of TechnologyHiroshimaJapan

Personalised recommendations