ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Neural Network Image Reconstruction for Magnetic Particle Imaging

  • Received : 2017.04.13
  • Accepted : 2017.10.10
  • Published : 2017.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

We investigate neural network image reconstruction for magnetic particle imaging. The network performance strongly depends on the convolution effects of the spectrum input data. The larger convolution effect appearing at a relatively smaller nanoparticle size obstructs the network training. The trained single-layer network reveals the weighting matrix consisting of a basis vector in the form of Chebyshev polynomials of the second kind. The weighting matrix corresponds to an inverse system matrix, where an incoherency of basis vectors due to low convolution effects, as well as a nonlinear activation function, plays a key role in retrieving the matrix elements. Test images are well reconstructed through trained networks having an inverse kernel matrix. We also confirm that a multi-layer network with one hidden layer improves the performance. Based on the results, a neural network architecture overcoming the low incoherence of the inverse kernel through the classification property is expected to become a better tool for image reconstruction.

Keywords

References

  1. B. Gleich and J. Weizenecker, "Tomographic Imaging Using the Nonlinear Response of Magnetic Particles," Nature, vol. 435, no. 7046, June 2005, pp. 1214-1217. https://doi.org/10.1038/nature03808
  2. J. Weizenecker, J. Borgert, and B. Gleich, "A Simulation Study on the Resolution and Sensitivity of Magnetic Particle Imaging," Phy. Med. Biol., vol. 52, 2007, pp. 6363-6374. https://doi.org/10.1088/0031-9155/52/21/001
  3. T.M. Buzug et al., "Magnetic Particle Imaging: Introduction to Imaging and Hardware Realization," Zeitschrift f€ur Medizinische Physik, vol. 22, no. 4, Dec. 2012, pp. 323-334. https://doi.org/10.1016/j.zemedi.2012.07.004
  4. T. Knopp and T.M. Buzug, Magnetic Particle Imaging, Berlin, Germany: Springer-Verlag, 2012.
  5. P.W. Goodwill et al., "Narrowband Magnetic Particle Imaging," IEEE Trans. Med. Imag., vol. 28, no. 8, Aug. 2009, pp. 1231-1237. https://doi.org/10.1109/TMI.2009.2013849
  6. J. Rahmer et al., "Signal Encoding in Magnetic Particle Imaging: Properties of the System Function," BMC Med. Imag., vol. 9, no. 1, Apr. 2009, p. 4. https://doi.org/10.1186/1471-2342-9-4
  7. T. Knopp et al., "Model-Based Reconstruction for Magnetic Particle Imaging," IEEE Trans. Med. Imag., vol. 29, no. 1, Jan. 2010, pp. 12-18. https://doi.org/10.1109/TMI.2009.2021612
  8. T. Sattel et al., "Single-Sided Device for Magnetic Particle Imaging," J. Phys. D: Appl. Phys., vol. 42, no. 1, 2009, pp. 1-5.
  9. K. Grafe et al., "System Matrix Recording and Phantom Measurements with a Single Sided Magnetic Particle Imaging Device," IEEE Trans. Magn., vol. 51, no. 2, 2015, pp. 6502303:1-6502303:3.
  10. K. Grafe et al., "2D Images Recorded with a Single-Sided Magnetic Particle Imaging Scanner," IEEE Trans. Med. Imag., vol. 35, no. 4, Apr. 2016, pp. 1056-1065. https://doi.org/10.1109/TMI.2015.2507187
  11. T. Knopp et al., "Weighted Iterative Reconstruction for Magnetic Particle Imaging," Phys. Med. Biol., vol. 55, no. 6, 2010, pp. 1577-1589. https://doi.org/10.1088/0031-9155/55/6/003
  12. D. Boublil et al., "Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks," IEEE Trans. Med. Imag., vol. 34, no. 7, July 2015, pp. 1474-1485. https://doi.org/10.1109/TMI.2015.2401131
  13. R. Cierniak, "A 2D Approach to Tomographic Image Reconstruction Using a Hopfield-Type Neural Network," Artif. Intell. Med., vol. 43, no. 2, June 2008, pp. 113-125. https://doi.org/10.1016/j.artmed.2008.03.003
  14. C.E. Floyd et al., "An Artificial Neural Network for SPECT Image Reconstruction," IEEE Trans. Med. Imag., vol. 10, no. 3, Sept. 1991, pp. 485-487. https://doi.org/10.1109/42.97600
  15. J.P. Kerr and E.B. Bartlett, "A Statistically Tailored Neural Network Approach to Tomographic Image Reconstruction," Med. Phys., vol. 22, no. 5, 1995, pp. 601-610. https://doi.org/10.1118/1.597586
  16. D.C. Durairaj, M.C. Krishna, and R. Murugesan, "A Neural Network Approach for Image Reconstruction in Electron Magnetic Resonance Tomography," Comput. Biol. Med., vol. 37, no. 10, Oct. 2007, pp. 1492-1501. https://doi.org/10.1016/j.compbiomed.2007.01.010
  17. T. Hatsuda et al., "A Basic Study of Image Reconstruction Method Using Neural Networks with Additional Learning for Magnetic Particle Imaging," Int. J. Magn. Partic. Imag., vol. 2, no. 2, Nov. 2016, pp. 1-5.
  18. C.M. Bishop, Neural Networks for Pattern Recognition, New York, USA: Oxford University Press, 1995.
  19. D.E. Rumelhart, G.E. Hinton, and R.J. Williams, "Learning Representations by Back-Propagating Errors," Nature, vol. 323, Oct. 1986, pp. 533-536. https://doi.org/10.1038/323533a0
  20. T. Knop and A. Weber, "Sparse Reconstruction of the Magnetic Particle Imaging System Matrix," IEEE Trans. Med. Imag., vol. 32, no. 8, Aug. 2013, pp. 1473-1480. https://doi.org/10.1109/TMI.2013.2258029
  21. B.G. Chae and S. Lee, "Sparse-View CT Image Recovery Using Two-Step Iterative Shrinkage-Thresholding Algorithm," ETRI J., vol. 37, no. 6, Dec. 2015, pp. 1251-1258. https://doi.org/10.4218/etrij.15.0115.0401
  22. D. Donoho, "Compressed Sensing," IEEE Trans. Inform. Theory, vol. 52, no. 4, 2006, pp. 1289-1306. https://doi.org/10.1109/TIT.2006.871582

Cited by

  1. 무인기 탑재 다중 센서 기반 국지 산불 감시 및 상황 대응 플랫폼 설계 및 구현 vol.10, pp.6, 2017, https://doi.org/10.17661/jkiiect.2017.10.6.626
  2. Efficient Texture Creation Based on Random Patches in Database and Guided Filter vol.ed101, pp.11, 2017, https://doi.org/10.1587/transinf.2018edl8143
  3. The Reconstruction of Magnetic Particle Imaging: Current Approaches Based on the System Matrix vol.11, pp.5, 2021, https://doi.org/10.3390/diagnostics11050773