Abstract

Segmentation of retinal layers from OCT images is fundamental to diagnose the progress of retinal diseases. In this study we show that the retinal layers can be automatically and/or interactively located with good accuracy with the aid of local coherence information of the retinal structure. OCT images are processed using the ideas of texture analysis by means of the structure tensor combined with complex diffusion filtering. Experimental results indicate that our proposed novel approach has good performance in speckle noise removal, enhancement and segmentation of the various cellular layers of the retina using the STRATUSOCT system.

© 2005 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |

  1. D. Huang, E. A. Swanson, C. P. Lin, J. S. Schumann, W. G. Stinson, W. Chang, M. R. Hee, T. Flotte, K. Gregory, C. A. Puliafito, and J. G. Fujimoto, "Optical coherence tomography," Science 254, 1178-1181 (1991).
    [CrossRef] [PubMed]
  2. J. M. Schmitt, S. H. Xiang, and K. M. Yung, "Speckle in optical coherence tomography," J. Biomed. Optics 4, 95, (1999).
    [CrossRef]
  3. E. R. Ritenour, T. R. Nelson, and U. Raff, "Application of median filtering to digital radiographic images," in Proc. 7th Int. Conf. Acoust. Speech, Signal Processing, 1984, 23.1.1-23.1.4.
  4. A. Loannidis, D. Kazakos, D. D. Watson, "Application of median filtering on nuclear medicine scintigrams images," in Proc. 7th Conf. Pattern Recognition, 1984, 33-36
  5. S. H. Xiang, L. Zhou, and J. M. Schmitt, "Speckle noise reduction for optical coherence tomography, in Optical and Imaging Techniques for Biomonitoring III , H.-J. Foth, R. Marchesini, and H. Podbielska, eds.", Proc. SPIE 3196, 79, (1997).
    [CrossRef]
  6. K. M. Yung, S. L. Lee, and J. M. Schmitt, "Phase-domain processing of optical coherence tomography images," J. Biomed. Optics 4, 125 (1999).
    [CrossRef]
  7. P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
    [CrossRef]
  8. D. Cabrera Fernández, and H. M. Salinas, "Evaluation of a non-linear diffusion process for segmentation and quantification of lesions in Optical Coherence Tomography images," in Proc. SPIE Int. Soc. Opt. Eng. 5747, 1834 (2005).
  9. G. Gregori, and R. W. Knighton, "A robust algorithm for retinal thickness measurements using optical coherence tomography (Stratus OCT)," Invest. Ophthalmol. Visual Sci. 45: E-Abstract 3007 (2004).
  10. . D. Cabrera Fernández , "Delineating fluid-filled region boundaries in optical coherence tomography images of the retina," IEEE Trans. Med. Imaging 24, 929-945 (2005).
    [CrossRef]
  11. L. Alvarez, F. Guichard, P. L. Lions, and J. M. Morel, "Axioms and fundamental equations of image processing," Arch. Ration. Mech. Anal. 23, 199-257 (1993).
    [CrossRef]
  12. G. Aubert, P. Kornprobst, Mathematical Problems in Image Processing, Applied Mathematical Sciences 147 (Springer-Verlag, New-York, 2002).
  13. D. Cabrera Fernández, and R. W. Knighton, "Active contour models for assessing lesion shape and area in OCT images of the retina," Invest. Ophthalmol. Visual Sci. 44: E-Abstract 1770 (2003).
  14. D. Koozekanani, K. Boyer, and C. Roberts, "Retinal thickness measurements from optical coherence tomography using a Markov boundary model," IEEE Trans. Med. Imaging 20, 900 - 916, (2001).
    [CrossRef] [PubMed]
  15. J. Weickert, "Anisotropic diffusion filters for image processing based quality control," A. Fasano, M. Primicerio eds., in Proc. Seventh European Conf. on Mathematics in Industry, (Teubner, Stuttgart, 1994), 355-362.
  16. R. Deriche, "Using canny criteria to derive a recursively implemented optimal edge detector," Int. J. Comput. Vision 1, 167-187 (1987).
    [CrossRef]
  17. J. Weickert, "Foundations and applications of nonlinear anisotropic diffusion filtering," Z. Angew. Math. Mech. 76, 283-286 (1996).
  18. H. Ishikawa, D. M. Stein, G. Wollstein, S. Beaton, J. G. Fujimoto, and J. S. Schuman , "Macular segmentation with optical coherence tomography," Invest. Ophthalmol. Vis. Sci. 46: 2012-2017. (2005).
    [CrossRef] [PubMed]
  19. G. Gilboa, N. Sochen, and Y. Y .Zeevi, "Image enhancement and denoising by complex diffusion process," IEEE Trans. PAMI 25 (8), 1020-1036, (2004).
    [CrossRef]
  20. J. Weickert, "Coherence-enhancing diffusion filtering," Int. J. Comput. Vision 31, 111-127, (1999).
    [CrossRef]
  21. G. H. Cottet, ans L. Germain, "Image processing through reaction combined with nonlinear diffusion," Math. Comp. 61, 659-673 (1993).
    [CrossRef]
  22. M. Nitzberg, T. Shiota, "Nonlinear image filtering with edge and corner enhancement," IEEE Trans. PAMI 14, 826-833 (1992).
    [CrossRef]
  23. D. Cabrera Fernández, and H. M. Salinas, "Extracting subretinal layers on stratus OCT images via a structure tensor approach combined with a nonlinear diffusion process," Invest. Ophthalmol. Visual. Sci. 46: E-Abstract 2575 (2005).
  24. H. M. Salinas, and D. Cabrera Fernández, "Comparison of PDE-based nonlinear anisotropic diffusion approaches for image enhancement and denoising in Optical Coherence Tomography," submitted to IEEE Trans. Med. Imaging (2005).
  25. O. Tan, Y. Li, and D. Huang, "Measurement of Ganglion cell layer and inner plexiform layer thickness with Optical Coherence Tomography," Invest. Ophthalmol. Visual. Sci. 44: E-Abstract 4926 (2003).
  26. R. W. Knighton, Bascom Palmer Eye Institute, School of Medicine, University of Miami 1638 NW. 10th Ave, Miami, FL, 33136 (personal communication, 2005).

7th Conf. Pattern Recognition (1)

A. Loannidis, D. Kazakos, D. D. Watson, "Application of median filtering on nuclear medicine scintigrams images," in Proc. 7th Conf. Pattern Recognition, 1984, 33-36

7th Int. Conf. Acoust (1)

E. R. Ritenour, T. R. Nelson, and U. Raff, "Application of median filtering to digital radiographic images," in Proc. 7th Int. Conf. Acoust. Speech, Signal Processing, 1984, 23.1.1-23.1.4.

Applied Mathematical Sciences (1)

G. Aubert, P. Kornprobst, Mathematical Problems in Image Processing, Applied Mathematical Sciences 147 (Springer-Verlag, New-York, 2002).

Arch. Ration. Mech. Anal. (1)

L. Alvarez, F. Guichard, P. L. Lions, and J. M. Morel, "Axioms and fundamental equations of image processing," Arch. Ration. Mech. Anal. 23, 199-257 (1993).
[CrossRef]

IEEE Trans. Med. Imaging (3)

H. M. Salinas, and D. Cabrera Fernández, "Comparison of PDE-based nonlinear anisotropic diffusion approaches for image enhancement and denoising in Optical Coherence Tomography," submitted to IEEE Trans. Med. Imaging (2005).

. D. Cabrera Fernández , "Delineating fluid-filled region boundaries in optical coherence tomography images of the retina," IEEE Trans. Med. Imaging 24, 929-945 (2005).
[CrossRef]

D. Koozekanani, K. Boyer, and C. Roberts, "Retinal thickness measurements from optical coherence tomography using a Markov boundary model," IEEE Trans. Med. Imaging 20, 900 - 916, (2001).
[CrossRef] [PubMed]

IEEE Trans. PAMI (2)

M. Nitzberg, T. Shiota, "Nonlinear image filtering with edge and corner enhancement," IEEE Trans. PAMI 14, 826-833 (1992).
[CrossRef]

G. Gilboa, N. Sochen, and Y. Y .Zeevi, "Image enhancement and denoising by complex diffusion process," IEEE Trans. PAMI 25 (8), 1020-1036, (2004).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Trans. Pattern Anal. Mach. Intell. 12, 629-639 (1990).
[CrossRef]

in Proc. Seventh European Conf. (1)

J. Weickert, "Anisotropic diffusion filters for image processing based quality control," A. Fasano, M. Primicerio eds., in Proc. Seventh European Conf. on Mathematics in Industry, (Teubner, Stuttgart, 1994), 355-362.

Int. J. Comput. Vision (2)

R. Deriche, "Using canny criteria to derive a recursively implemented optimal edge detector," Int. J. Comput. Vision 1, 167-187 (1987).
[CrossRef]

J. Weickert, "Coherence-enhancing diffusion filtering," Int. J. Comput. Vision 31, 111-127, (1999).
[CrossRef]

Invest. Ophthalmol. Vis. Sci. (1)

H. Ishikawa, D. M. Stein, G. Wollstein, S. Beaton, J. G. Fujimoto, and J. S. Schuman , "Macular segmentation with optical coherence tomography," Invest. Ophthalmol. Vis. Sci. 46: 2012-2017. (2005).
[CrossRef] [PubMed]

Invest. Ophthalmol. Visual Sci. (2)

G. Gregori, and R. W. Knighton, "A robust algorithm for retinal thickness measurements using optical coherence tomography (Stratus OCT)," Invest. Ophthalmol. Visual Sci. 45: E-Abstract 3007 (2004).

D. Cabrera Fernández, and R. W. Knighton, "Active contour models for assessing lesion shape and area in OCT images of the retina," Invest. Ophthalmol. Visual Sci. 44: E-Abstract 1770 (2003).

Invest. Ophthalmol. Visual. Sci (1)

D. Cabrera Fernández, and H. M. Salinas, "Extracting subretinal layers on stratus OCT images via a structure tensor approach combined with a nonlinear diffusion process," Invest. Ophthalmol. Visual. Sci. 46: E-Abstract 2575 (2005).

Invest. Ophthalmol. Visual. Sci. (1)

O. Tan, Y. Li, and D. Huang, "Measurement of Ganglion cell layer and inner plexiform layer thickness with Optical Coherence Tomography," Invest. Ophthalmol. Visual. Sci. 44: E-Abstract 4926 (2003).

J. Biomed. Optics (2)

K. M. Yung, S. L. Lee, and J. M. Schmitt, "Phase-domain processing of optical coherence tomography images," J. Biomed. Optics 4, 125 (1999).
[CrossRef]

J. M. Schmitt, S. H. Xiang, and K. M. Yung, "Speckle in optical coherence tomography," J. Biomed. Optics 4, 95, (1999).
[CrossRef]

Math. Comp. (1)

G. H. Cottet, ans L. Germain, "Image processing through reaction combined with nonlinear diffusion," Math. Comp. 61, 659-673 (1993).
[CrossRef]

Math. Mech. (1)

J. Weickert, "Foundations and applications of nonlinear anisotropic diffusion filtering," Z. Angew. Math. Mech. 76, 283-286 (1996).

Proc. SPIE (1)

S. H. Xiang, L. Zhou, and J. M. Schmitt, "Speckle noise reduction for optical coherence tomography, in Optical and Imaging Techniques for Biomonitoring III , H.-J. Foth, R. Marchesini, and H. Podbielska, eds.", Proc. SPIE 3196, 79, (1997).
[CrossRef]

Proc. SPIE Int. Soc. Opt. Eng. (1)

D. Cabrera Fernández, and H. M. Salinas, "Evaluation of a non-linear diffusion process for segmentation and quantification of lesions in Optical Coherence Tomography images," in Proc. SPIE Int. Soc. Opt. Eng. 5747, 1834 (2005).

Science (1)

D. Huang, E. A. Swanson, C. P. Lin, J. S. Schumann, W. G. Stinson, W. Chang, M. R. Hee, T. Flotte, K. Gregory, C. A. Puliafito, and J. G. Fujimoto, "Optical coherence tomography," Science 254, 1178-1181 (1991).
[CrossRef] [PubMed]

Other (1)

R. W. Knighton, Bascom Palmer Eye Institute, School of Medicine, University of Miami 1638 NW. 10th Ave, Miami, FL, 33136 (personal communication, 2005).

Supplementary Material (1)

» Media 1: JPG (33 KB)     

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 (10)

Fig. 1.
Fig. 1.

Flowchart of the methodology illustrating the corresponding main processing steps that need to be performed to automatically extract the cellular layers of the retina on OCT images.

Fig. 2.
Fig. 2.

Optimal choice of the threshold value (κ) and iteration number (N) using small values of θ to obtain the optimal image restoration result. (A) Selection criteria of optimal stopping time. The iteration should be stopped after 40-50 iterations to avoid redundancy computation (κ= 10, with θ = π/30, σ= 1 and Δt=0.24). (B) Measured S/MSE improvement of a typical OCT image as κ is varied from 1 to 20 (N= 50, with θ = π/30,σ= 1 and Δt= 0.24).

Fig. 3.
Fig. 3.

Denoising results for a sample OCT scan. (A) Original OCT image. [Media 1](B) Image denoised (real part) using the nonlinear complex diffusion filter (κ=10, θ=π/30, σ =1, N=50, and Δt=0.24). (C) Imaginary part of the original OCT image after nonlinear complex diffusion filtering (κ = 10, θ = π/30, σ= 1, N=50, and Δt=0.24). (D) Image obtained after a coherence-enhanced diffusion filtering (α=4, σ=5, ρ =2, m=8, and Δt=0.24) is applied to the denoised image (real part shown in B) obtained after nonlinear complex diffusion filtering. (E) Image denoised (real part) using the nonlinear complex diffusion filter (κ= 60, θ= π/30, σ =1, N=50, and Δt=0.24). (F) Imaginary part of the original OCT image after nonlinear complex diffusion filtering (κ = 60, θ = π/30, σ= 1, N=50, and Δt=0.24). (G) Image obtained after a coherence-enhanced diffusion filtering is applied to the denoised image (real part shown in E) obtained after nonlinear complex diffusion filtering. (H) Edge map obtained calculating the first derivative of the structure coherence matrix of the denoised image shown in E. The OCT images displayed are grayscale representations of the actual interference signal intensities.

Fig. 4.
Fig. 4.

Local coherence and orientation in a sample OCT scan. Top: Structure tensor coherence. Bottom: Structure tensor orientation (in degrees).

Fig. 5.
Fig. 5.

Segmentation of an A-scan line based on the coherence structure information extracted from the OCT signal intensity after enhancing diffusion filtering.

Fig. 6.
Fig. 6.

Automated segmentation results. Top: Original OCT image with overlaid retinal boundaries. The segmented retinal layers are, from top to bottom, retinal nerve fiber layer (RNFL), ganglion cell layer (GCL) along with the inner plexiform layer (IPL), inner nuclear layer (INL), outer plexiform layer (OPL), outer nuclear layer (ONL) and the photoreceptor inner/outer segment junction (IS/OS). The retinal pigment epithelium (RPE) along with the choriocapillaries (ChCap) and choroid layer appear below the bottom boundary line. Bottom: A small section of the original OCT image containing 100 A-scans and the single axial scan shown on Fig. 3. The tomogram is composed of 512 A-scans. We note that the sublayer labeled as the ONL is actually enclosing the external limiting membrane (ELM) but in the standard 10-15μm resolution OCT image this thin intraretinal layer cannot be visualized clearly. Thus this layer classification is our assumption and does not reflect the actual anatomic structure.

Fig. 7.
Fig. 7.

Automated and semi-automated segmentation results. The boundaries detected are superimposed on the original OCT image shown in Fig. 3(a). Note that we have assumed a constant thickness for the layers obtained with the semi-automated approach (i.e. for the IS/OS junction and ChCap layer).

Fig. 8.
Fig. 8.

Thickness segmentation mapping obtained for the same normal subject shown in Fig. 1 after automatic segmentation of the retinal layers (see Fig. 4). (a) Whole macular thickness map. (b) RNFL thickness map. (c) GCL + IPL thickness map. (d) INL thickness map. (e) OPL thickness map. (f) ONL thickness map. Note that the scale of the color scheme in the maps is adjusted for the thickness range of each extracted layer. Thickness values are in microns.

Fig. 9.
Fig. 9.

Automatic segmentation results for two pathologic human eyes. Top: Glaucomatous subject. Bottom: Subject with a small subfoveal cyst.

Fig. 10.
Fig. 10.

Automatic segmentation results for two more pathologic human eyes showing a higher perturbation in the retinal structure. Top: Chorioretinitis. Bottom: Macular edema.

Equations (7)

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

t I = . ( d ( Im ( I ) ) I )
d ( Im ( I ) ) = exp ( i θ ) 1 + ( Im ( I ) k θ ) 2
t I = . ( d ( I ) I )
J ρ ( I σ ) = G ρ * ( I σ I σ ) = G ρ * ( I σ I σ T )
J ρ = ν 1 ν 2 M ν 1 ν 2 T = ν 1 ν 2 ( μ 1 0 0 μ 2 ) ν 1 ν 2 T
λ 1 = α ,
λ 2 = { α if μ 1 = μ 2 α + ( 1 α ) exp [ C ( μ 1 μ 2 ) 2 m ] else , }

Metrics