Abstract

This paper presents an algorithm for reducing speckle noise from optical coherence tomography (OCT) images using an artificial neural network (ANN) algorithm. The noise is modeled using Rayleigh distribution with a noise parameter, sigma, estimated by the ANN. The input to the ANN is a set of intensity and wavelet features computed from the image to be processed, and the output is an estimated sigma value. This is then used along with a numerical method to solve the inverse Rayleigh function to reduce the noise in the image. The algorithm is tested successfully on OCT images of Drosophila larvae. It is demonstrated that the signal-to-noise ratio and the contrast-to-noise ratio of the processed images are increased by the application of the ANN algorithm in comparison with the respective values of the original images.

© 2013 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. A. G. Podoleanu, “Optical coherence tomography,” Br. J. Radiol. 78, 976–988 (2005).
    [CrossRef]
  2. A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).
  3. M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
    [CrossRef]
  4. J. W. Goodman, Speckle Phenomena in Optics: Theory and Applications (Roberts & Co, 2006).
  5. J. C. Dainty, Laser Speckle and Related Phenomena (Springer-Verlag, 1975), Vol. 9, p. 298.
  6. M. R. N. Avanaki and A. Hojjatoleslami, “Speckle reduction with attenuation compensation for skin OCT images enhancement,” in Proceeding of Medical Image Understanding and Analysis (MIUA), Kingston University, London, 14–15 July, 2009, pp. 179–183.
  7. A. M. Schmitt, “Principles and application of optical coherent tomography in dermatology,” Dermatology 217, 12 (2008).
    [CrossRef]
  8. M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
    [CrossRef]
  9. M. E. Anderson and G. E. Trahey, “A seminar on k-space applied to medical ultrasound,” Tech. Rep. (Department of Biomedical Engineering of Duke University, 2000).
  10. M. Hughes, M. Spring, and A. Podoleanu, “Speckle noise reduction in optical coherence tomography of paint layers,” Appl. Opt. 49, 99–107 (2010).
    [CrossRef]
  11. P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).
  12. T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
    [CrossRef]
  13. N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
    [CrossRef]
  14. H. L. Resnikoff and R. O. Wells, Wavelet Analysis: The Scalable Structure of Information: With 92 Figures (Springer-Verlag, 1998).
  15. R. K. Wang, “Reduction of speckle noise for optical coherence tomography by the use of nonlinear anisotropic diffusion,” Proc. SPIE 5690, 380–385 (2005).
    [CrossRef]
  16. M. Bashkansky and J. Reintjes, “Statistics and reduction of speckle in optical coherence tomography,” Opt. Lett. 25, 545–547 (2000).
    [CrossRef]
  17. J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
    [CrossRef]
  18. P. Puvanathasan and K. Bizheva, “Speckle noise reduction algorithm for optical coherence tomography based on interval type II fuzzy set,” Opt. Express 15, 15747–15758 (2007).
    [CrossRef]
  19. J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
    [CrossRef]
  20. D. A. Nix and A. S. Weigend, “Estimating the mean and variance of the target probability distribution,” in Proceedings of the IEEE International Conference on Neural Networks (IEEE-ICNN’94)Orlando, FL (IEEE, 1994), pp. 55–60.
  21. H. Schioler and P. Kulczycki, “Neural network for estimating conditional distributions,” IEEE Trans. Neural Netw. 8, 1015–1025 (1997).
    [CrossRef]
  22. P. M. Williams, “Using neural networks to model conditional multivariate densities,” Neural Comput. 8, 843–854 (1996).
    [CrossRef]
  23. H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).
  24. M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.
  25. D. C. Adler, T. H. Ko, and J. G. Fujimoto, “Speckle reduction in optical coherence tomography images by use of a spatially adaptive wavelet filter,” Opt. Lett. 29, 2878–2880 (2004).
    [CrossRef]
  26. B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).
  27. R. Hecht-Nielsen, “Theory of the backpropagation neural network,” in International Joint Conference on Neural Networks, 1989, Washington, DC (IEEE, 1989), pp. 593–605.
  28. K. Hornik and M. Stinchombe, “Multilayer feed-forward networks are universal approximators,” in Artificial Neural Networks: Approximation and Learning Theory, H. White, A. R. Gallant, K. Hornik, and M. Stinchombe, eds. (Blackwell, 1992).
  29. M. Nasiri-Avanaki and R. Ebrahimpour, “In-service video quality measurements in optical fiber links based on neural network,” Neural Network World 17, 457 (2007).
  30. P. M. Buscema, Artificial Neural Network (Massimo Buscema & Semeion Group, 2004).
  31. C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
    [CrossRef]
  32. M. Hughes, “High lateral resolution imaging with dynamic focus,” Ph.D. dissertation (University of Kent, 2010).
  33. MathWorks, “Rayleigh probability density function: the language of technical computing,” http://www.mathworks.com .
  34. A. Graps, “An introduction to wavelets,” IEEE Comput. Sci. Eng. 2, 50–61 (1995).
    [CrossRef]
  35. M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).
  36. Michelson Diagnostics, “How breakthrough multi-beam OCT imaging works,” http://www.md-ltd.co.uk/our-technology.html .
  37. W. Duch and N. Jankowski, “Survey of neural transfer functions,” Neural Comput. Surv. 2, 163–212 (1999).
  38. L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
    [CrossRef]
  39. J. Jan and R. J. Kubak, “Speckle reduction by averaging of ultrasonograms diversified by scanhead displacements,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century, Seattle, WA, November9–12 (IEEE, 1989), pp. 407–408.
  40. A. Hojjatoleslami and M. R. Nasiriavanaki, “OCT skin image enhancement through attenuation compensation,” Appl. Opt. 51, 4927–4935 (2012).
    [CrossRef]
  41. J. S. Lim, Two-dimensional Signal and Image Processing (Prentice-Hall, 1990), pp. 469–476.

2012 (1)

2011 (1)

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

2010 (2)

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

M. Hughes, M. Spring, and A. Podoleanu, “Speckle noise reduction in optical coherence tomography of paint layers,” Appl. Opt. 49, 99–107 (2010).
[CrossRef]

2008 (3)

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

A. M. Schmitt, “Principles and application of optical coherent tomography in dermatology,” Dermatology 217, 12 (2008).
[CrossRef]

2007 (5)

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

P. Puvanathasan and K. Bizheva, “Speckle noise reduction algorithm for optical coherence tomography based on interval type II fuzzy set,” Opt. Express 15, 15747–15758 (2007).
[CrossRef]

M. Nasiri-Avanaki and R. Ebrahimpour, “In-service video quality measurements in optical fiber links based on neural network,” Neural Network World 17, 457 (2007).

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

2005 (3)

A. G. Podoleanu, “Optical coherence tomography,” Br. J. Radiol. 78, 976–988 (2005).
[CrossRef]

R. K. Wang, “Reduction of speckle noise for optical coherence tomography by the use of nonlinear anisotropic diffusion,” Proc. SPIE 5690, 380–385 (2005).
[CrossRef]

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

2004 (1)

2003 (1)

N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
[CrossRef]

2000 (2)

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

M. Bashkansky and J. Reintjes, “Statistics and reduction of speckle in optical coherence tomography,” Opt. Lett. 25, 545–547 (2000).
[CrossRef]

1999 (1)

W. Duch and N. Jankowski, “Survey of neural transfer functions,” Neural Comput. Surv. 2, 163–212 (1999).

1997 (1)

H. Schioler and P. Kulczycki, “Neural network for estimating conditional distributions,” IEEE Trans. Neural Netw. 8, 1015–1025 (1997).
[CrossRef]

1996 (1)

P. M. Williams, “Using neural networks to model conditional multivariate densities,” Neural Comput. 8, 843–854 (1996).
[CrossRef]

1995 (1)

A. Graps, “An introduction to wavelets,” IEEE Comput. Sci. Eng. 2, 50–61 (1995).
[CrossRef]

1994 (1)

J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
[CrossRef]

1988 (1)

M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
[CrossRef]

1982 (1)

P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).

Adler, D. C.

Andersen, P. E.

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

Anderson, M. E.

M. E. Anderson and G. E. Trahey, “A seminar on k-space applied to medical ultrasound,” Tech. Rep. (Department of Biomedical Engineering of Duke University, 2000).

Arnfield, M.

M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
[CrossRef]

Avanaki, M. R. N.

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

M. R. N. Avanaki and A. Hojjatoleslami, “Speckle reduction with attenuation compensation for skin OCT images enhancement,” in Proceeding of Medical Image Understanding and Analysis (MIUA), Kingston University, London, 14–15 July, 2009, pp. 179–183.

Balabuc, C.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Bashkansky, M.

Belmont, M.

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

Bic, M. L. H.

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

Bilenca, A.

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

Bizheva, K.

Bloor, J. W.

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

Bouma, B. E.

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
[CrossRef]

Bradu, A.

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Brezinski, M.

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

Buscema, P. M.

P. M. Buscema, Artificial Neural Network (Massimo Buscema & Semeion Group, 2004).

Dainty, J. C.

J. C. Dainty, Laser Speckle and Related Phenomena (Springer-Verlag, 1975), Vol. 9, p. 298.

Desjardins, A. E.

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

Duch, W.

W. Duch and N. Jankowski, “Survey of neural transfer functions,” Neural Comput. Surv. 2, 163–212 (1999).

Ebrahimpour, R.

M. Nasiri-Avanaki and R. Ebrahimpour, “In-service video quality measurements in optical fiber links based on neural network,” Neural Network World 17, 457 (2007).

Elmaghraby, A.

M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.

Filip, L.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Fujimoto, J. G.

Goodman, J. W.

J. W. Goodman, Speckle Phenomena in Optics: Theory and Applications (Roberts & Co, 2006).

Graps, A.

A. Graps, “An introduction to wavelets,” IEEE Comput. Sci. Eng. 2, 50–61 (1995).
[CrossRef]

Hecht-Nielsen, R.

R. Hecht-Nielsen, “Theory of the backpropagation neural network,” in International Joint Conference on Neural Networks, 1989, Washington, DC (IEEE, 1989), pp. 593–605.

Hojjatoleslami, A.

A. Hojjatoleslami and M. R. Nasiriavanaki, “OCT skin image enhancement through attenuation compensation,” Appl. Opt. 51, 4927–4935 (2012).
[CrossRef]

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

M. R. N. Avanaki and A. Hojjatoleslami, “Speckle reduction with attenuation compensation for skin OCT images enhancement,” in Proceeding of Medical Image Understanding and Analysis (MIUA), Kingston University, London, 14–15 July, 2009, pp. 179–183.

Hornik, K.

K. Hornik and M. Stinchombe, “Multilayer feed-forward networks are universal approximators,” in Artificial Neural Networks: Approximation and Learning Theory, H. White, A. R. Gallant, K. Hornik, and M. Stinchombe, eds. (Blackwell, 1992).

Hougaard, J.

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Hughes, M.

M. Hughes, M. Spring, and A. Podoleanu, “Speckle noise reduction in optical coherence tomography of paint layers,” Appl. Opt. 49, 99–107 (2010).
[CrossRef]

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

M. Hughes, “High lateral resolution imaging with dynamic focus,” Ph.D. dissertation (University of Kent, 2010).

Hwang, J. N.

J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
[CrossRef]

Iftimia, N.

N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
[CrossRef]

Jan, J.

J. Jan and R. J. Kubak, “Speckle reduction by averaging of ultrasonograms diversified by scanhead displacements,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century, Seattle, WA, November9–12 (IEEE, 1989), pp. 407–408.

Jankowski, N.

W. Duch and N. Jankowski, “Survey of neural transfer functions,” Neural Comput. Surv. 2, 163–212 (1999).

Jorgensen, T.

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Jorgensen, T. M.

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

Ko, T. H.

Kubak, R. J.

J. Jan and R. J. Kubak, “Speckle reduction by averaging of ultrasonograms diversified by scanhead displacements,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century, Seattle, WA, November9–12 (IEEE, 1989), pp. 407–408.

Kulczycki, P.

H. Schioler and P. Kulczycki, “Neural network for estimating conditional distributions,” IEEE Trans. Neural Netw. 8, 1015–1025 (1997).
[CrossRef]

Laissue, P. P.

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

Larsen, M.

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Lay, S. R.

J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
[CrossRef]

Lim, J. S.

J. S. Lim, Two-dimensional Signal and Image Processing (Prentice-Hall, 1990), pp. 469–476.

Lippman, A.

J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
[CrossRef]

Ma, L.

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

Magnin, P. A.

P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).

McPhee, M.

M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
[CrossRef]

Miyazaki, R.

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

Mogensen, M.

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

Nasiriavanaki, M. R.

Nasiri-Avanaki, M.

M. Nasiri-Avanaki and R. Ebrahimpour, “In-service video quality measurements in optical fiber links based on neural network,” Neural Network World 17, 457 (2007).

Negrutiu, M. L.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Nishimura, T.

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

Nix, D. A.

D. A. Nix and A. S. Weigend, “Estimating the mean and variance of the target probability distribution,” in Proceedings of the IEEE International Conference on Neural Networks (IEEE-ICNN’94)Orlando, FL (IEEE, 1994), pp. 55–60.

Ozcan, A.

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

Park, H.

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

Pedersen, F.

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

Podoleanu, A.

Podoleanu, A. G.

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

A. G. Podoleanu, “Optical coherence tomography,” Br. J. Radiol. 78, 976–988 (2005).
[CrossRef]

Puvanathasan, P.

Reintjes, J.

Resnikoff, H. L.

H. L. Resnikoff and R. O. Wells, Wavelet Analysis: The Scalable Structure of Information: With 92 Figures (Springer-Verlag, 1998).

Rogowska, J.

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

Rominu, R.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Sander, B.

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Schioler, H.

H. Schioler and P. Kulczycki, “Neural network for estimating conditional distributions,” IEEE Trans. Neural Netw. 8, 1015–1025 (1997).
[CrossRef]

Schmitt, A. M.

A. M. Schmitt, “Principles and application of optical coherent tomography in dermatology,” Dermatology 217, 12 (2008).
[CrossRef]

Sinescu, C.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Smolikova, R.

M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.

Spring, M.

Stinchombe, M.

K. Hornik and M. Stinchombe, “Multilayer feed-forward networks are universal approximators,” in Artificial Neural Networks: Approximation and Learning Theory, H. White, A. R. Gallant, K. Hornik, and M. Stinchombe, eds. (Blackwell, 1992).

Tamaki, Y.

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

Tearney, G. J.

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
[CrossRef]

Thrane, L.

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Thurstone, F. L.

P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).

Todea, C.

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

Trahey, G. E.

M. E. Anderson and G. E. Trahey, “A seminar on k-space applied to medical ultrasound,” Tech. Rep. (Department of Biomedical Engineering of Duke University, 2000).

Tulip, J.

M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
[CrossRef]

von Ramm, O. T.

P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).

Wachowiak, M.

M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.

Wang, R. K.

R. K. Wang, “Reduction of speckle noise for optical coherence tomography by the use of nonlinear anisotropic diffusion,” Proc. SPIE 5690, 380–385 (2005).
[CrossRef]

Weigend, A. S.

D. A. Nix and A. S. Weigend, “Estimating the mean and variance of the target probability distribution,” in Proceedings of the IEEE International Conference on Neural Networks (IEEE-ICNN’94)Orlando, FL (IEEE, 1994), pp. 55–60.

Wells, R. O.

H. L. Resnikoff and R. O. Wells, Wavelet Analysis: The Scalable Structure of Information: With 92 Figures (Springer-Verlag, 1998).

Williams, P. M.

P. M. Williams, “Using neural networks to model conditional multivariate densities,” Neural Comput. 8, 843–854 (1996).
[CrossRef]

Zurada, J.

M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.

Appl. Opt. (2)

Br. J. Radiol. (1)

A. G. Podoleanu, “Optical coherence tomography,” Br. J. Radiol. 78, 976–988 (2005).
[CrossRef]

Br. Med. J. (1)

B. Sander, M. Larsen, L. Thrane, J. Hougaard, and T. Jorgensen, “Enhanced optical coherence tomography imaging by multiple scan averaging,” Br. Med. J. 89, 207–212 (2005).

Dermatology (1)

A. M. Schmitt, “Principles and application of optical coherent tomography in dermatology,” Dermatology 217, 12 (2008).
[CrossRef]

IEEE Comput. Sci. Eng. (1)

A. Graps, “An introduction to wavelets,” IEEE Comput. Sci. Eng. 2, 50–61 (1995).
[CrossRef]

IEEE Trans. Biomed. Eng. (1)

M. Arnfield, J. Tulip, and M. McPhee, “Optical propagation in tissue with anisotropic scattering,” IEEE Trans. Biomed. Eng. 35, 372–381 (1988).
[CrossRef]

IEEE Trans. Med. Imaging (1)

J. Rogowska, M. Brezinski, M. L. H. Bic, and M. Belmont, “Evaluation of the adaptive speckle suppression filter for coronary optical coherence tomography imaging,” IEEE Trans. Med. Imaging 19, 1261–1266 (2000).
[CrossRef]

IEEE Trans. Neural Netw. (1)

H. Schioler and P. Kulczycki, “Neural network for estimating conditional distributions,” IEEE Trans. Neural Netw. 8, 1015–1025 (1997).
[CrossRef]

IEEE Trans. Signal Process. (1)

J. N. Hwang, S. R. Lay, and A. Lippman, “Nonparametric multivariate density estimation: a comparative study,” IEEE Trans. Signal Process. 42, 2795–2810 (1994).
[CrossRef]

IEEJ Trans. Electron. Inf. Syst. (1)

H. Park, R. Miyazaki, T. Nishimura, and Y. Tamaki, “The speckle noise reduction and the boundary enhancement on medical ultrasound images using the cellular neural networks,” IEEJ Trans. Electron. Inf. Syst. 127, 1726–1731 (2007).

Int. J. Graphics Bioinfo. Med. Eng. (1)

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Evaluation of wavelet mother functions for speckle noise suppression in OCT images,” Int. J. Graphics Bioinfo. Med. Eng. 11, 1–5 (2011).

J. Biomed. Opt. (2)

C. Sinescu, M. L. Negrutiu, C. Todea, C. Balabuc, L. Filip, R. Rominu, A. Bradu, M. Hughes, and A. G. Podoleanu, “Quality assessment of dental treatments using en-face optical coherence tomography,” J. Biomed. Opt. 13, 054065 (2008).
[CrossRef]

N. Iftimia, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography by path length encoded angular compounding,” J. Biomed. Opt. 8, 260–263 (2003).
[CrossRef]

Neural Comput. (1)

P. M. Williams, “Using neural networks to model conditional multivariate densities,” Neural Comput. 8, 843–854 (1996).
[CrossRef]

Neural Comput. Surv. (1)

W. Duch and N. Jankowski, “Survey of neural transfer functions,” Neural Comput. Surv. 2, 163–212 (1999).

Neural Network World (1)

M. Nasiri-Avanaki and R. Ebrahimpour, “In-service video quality measurements in optical fiber links based on neural network,” Neural Network World 17, 457 (2007).

Opt. Express (1)

Opt. Lett. (2)

PLoS ONE (1)

L. Ma, A. Bradu, A. G. Podoleanu, and J. W. Bloor, “Arrhythmia caused by a Drosophila tropomyosin mutation is revealed using a novel optical coherence tomography instrument,” PLoS ONE 5, e14348 (2010).
[CrossRef]

Proc. SPIE (3)

T. M. Jorgensen, L. Thrane, M. Mogensen, F. Pedersen, and P. E. Andersen, “Speckle reduction in optical coherence tomography images of human skin by a spatial diversity method,” Proc. SPIE 6627, 66270P (2007).
[CrossRef]

M. R. N. Avanaki, P. P. Laissue, A. G. Podoleanu, and A. Hojjatoleslami, “Denoising based on noise parameter estimation in speckled OCT images using artificial neural network,” Proc. SPIE 7139, 71390E (2008).
[CrossRef]

R. K. Wang, “Reduction of speckle noise for optical coherence tomography by the use of nonlinear anisotropic diffusion,” Proc. SPIE 5690, 380–385 (2005).
[CrossRef]

Scanning (1)

A. Ozcan, A. Bilenca, A. E. Desjardins, B. E. Bouma, and G. J. Tearney, “Speckle reduction in optical coherence tomography images using digital filtering,” Scanning 20, 27–30 (2007).

Ultrason. Imag. (1)

P. A. Magnin, O. T. von Ramm, and F. L. Thurstone, “Frequency compounding for speckle contrast reduction in phased array images,” Ultrason. Imag. 4, 267–281 (1982).

Other (15)

H. L. Resnikoff and R. O. Wells, Wavelet Analysis: The Scalable Structure of Information: With 92 Figures (Springer-Verlag, 1998).

D. A. Nix and A. S. Weigend, “Estimating the mean and variance of the target probability distribution,” in Proceedings of the IEEE International Conference on Neural Networks (IEEE-ICNN’94)Orlando, FL (IEEE, 1994), pp. 55–60.

M. E. Anderson and G. E. Trahey, “A seminar on k-space applied to medical ultrasound,” Tech. Rep. (Department of Biomedical Engineering of Duke University, 2000).

J. W. Goodman, Speckle Phenomena in Optics: Theory and Applications (Roberts & Co, 2006).

J. C. Dainty, Laser Speckle and Related Phenomena (Springer-Verlag, 1975), Vol. 9, p. 298.

M. R. N. Avanaki and A. Hojjatoleslami, “Speckle reduction with attenuation compensation for skin OCT images enhancement,” in Proceeding of Medical Image Understanding and Analysis (MIUA), Kingston University, London, 14–15 July, 2009, pp. 179–183.

J. Jan and R. J. Kubak, “Speckle reduction by averaging of ultrasonograms diversified by scanhead displacements,” in Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century, Seattle, WA, November9–12 (IEEE, 1989), pp. 407–408.

Michelson Diagnostics, “How breakthrough multi-beam OCT imaging works,” http://www.md-ltd.co.uk/our-technology.html .

J. S. Lim, Two-dimensional Signal and Image Processing (Prentice-Hall, 1990), pp. 469–476.

P. M. Buscema, Artificial Neural Network (Massimo Buscema & Semeion Group, 2004).

M. Hughes, “High lateral resolution imaging with dynamic focus,” Ph.D. dissertation (University of Kent, 2010).

MathWorks, “Rayleigh probability density function: the language of technical computing,” http://www.mathworks.com .

M. Wachowiak, A. Elmaghraby, R. Smolikova, and J. Zurada, “Classification and estimation of ultrasound speckle noise with neural networks,” in IEEE International Symposium on Bio-Informatics and Biomedical Engineering, 2000, Arlington, VA, November8–10 (IEEE, 2002), pp. 245–252.

R. Hecht-Nielsen, “Theory of the backpropagation neural network,” in International Joint Conference on Neural Networks, 1989, Washington, DC (IEEE, 1989), pp. 593–605.

K. Hornik and M. Stinchombe, “Multilayer feed-forward networks are universal approximators,” in Artificial Neural Networks: Approximation and Learning Theory, H. White, A. R. Gallant, K. Hornik, and M. Stinchombe, eds. (Blackwell, 1992).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (9)

Fig. 1.
Fig. 1.

Schematic of the time-domain en face OCT system for microscopy operating at 1300 nm. Demod=demodulationdemodulation electronics, TS=motorized translation stage, L1=lens (f=4cm), GS=galvanometer scanning xy head, PC=polarization controller [32].

Fig. 2.
Fig. 2.

Rayleigh distribution curves generated using raylpdf for three sigma values, 20, 70, and 120. Pixel values in the images are between 1 and 255.

Fig. 3.
Fig. 3.

Transfer functions: (a) radial basis (radbas) and (b) linear [37].

Fig. 4.
Fig. 4.

Schematic diagram of the noise parameter estimator algorithm (the processes in dotted boxes were used only during the training stage).

Fig. 5.
Fig. 5.

Estimated sigma (black) versus expected sigma (red). Each sigma value was estimated as the average of 100 independent runs with different random initial weights.

Fig. 6.
Fig. 6.

Block diagram of image denoising using ANN algorithm. The blocks in the dotted box are used for sigma estimation.

Fig. 7.
Fig. 7.

Demonstration of the three stages of denoising applied to a C-scan image of Drosophila: (a) original image, (b) noise model image, and (c) denoised image. The image was acquired at a depth of 300 μm, and the size of the image is 1.5mm×1mm.

Fig. 8.
Fig. 8.

Comparative presentation of four original OCT test images (a1), (b1), (c1), (d1) and of their denoised images (a2), (b2), (c2), (d2): (a) C-scan image of Drosophila at a depth of 300 μm, size 1.5mm×1mm; (b) C-scan image of Drosophila at a depth of 100 μm, size 1.5mm×1mm; (c) C-scan image of Drosophila at a depth of 450 μm, size 700μm×500μm; (d) C-scan image of Drosophila at a depth of 350 μm, size 700μm×500μm.

Fig. 9.
Fig. 9.

Numerical assessment of the proposed denoising algorithm using SNR and CNR metrics applied to image sets of C-scan images of Drosophila. The wide hatched bars show the minimum SNR and the minimum CNR for the original image and the denoised image. The black narrow lines show the range of values of the SNR and CNR calculated for 10 images in each image set. The red dot shows the median value of the calculated SNR and CNR in one image set.

Tables (2)

Tables Icon

Table 1. SNR and CNR Computed for Different Despeckling Methods on the Image in Fig. 7(a)a

Tables Icon

Table 2. Estimated Sigma Values for the Images Shown in Fig. 8

Equations (9)

Equations on this page are rendered with MathJax. Learn more.

f(xi,j)=xi,jexi,j22σ2σ2,
f(i,j)=s(i,j)n(i,j)+na(i,j),
fL(i,j)=sL(i,j)+nL(i,j),
μ=1MN·iMjNxi,j,
σ=1MNi=1Mj=1N(xi,jμ)2,
κ=MNi=1Mj=1N(xi,jμ)4(i=1Mj=1N(xi,jμ)2)2,
m=(sm+sm+1)/2,
SNR=10log10(max(I2)σb2),
CNR=1R(r=1R(μrμb)σr2+σb2),

Metrics