## Automated segmentation of retinal blood vessels in spectral domain optical coherence tomography scans |

Biomedical Optics Express, Vol. 3, Issue 7, pp. 1478-1491 (2012)

http://dx.doi.org/10.1364/BOE.3.001478

Acrobat PDF (1347 KB)

### Abstract

The correct segmentation of blood vessels in optical coherence tomography (OCT) images may be an important requirement for the analysis of intra-retinal layer thickness in human retinal diseases. We developed a shape model based procedure for the automatic segmentation of retinal blood vessels in spectral domain (SD)-OCT scans acquired with the Spectralis OCT system. The segmentation procedure is based on a statistical shape model that has been created through manual segmentation of vessels in a training phase. The actual segmentation procedure is performed after the approximate vessel position has been defined by a shadowgraph that assigns the lateral vessel positions. The active shape model method is subsequently used to segment blood vessel contours in axial direction. The automated segmentation results were validated against the manual segmentation of the same vessels by three expert readers. Manual and automated segmentations of 168 blood vessels from 34 B-scans were analyzed with respect to the deviations in the mean Euclidean distance and surface area. The mean Euclidean distance between the automatically and manually segmented contours (on average 4.0 pixels respectively 20 µm against all three experts) was within the range of the manually marked contours among the three readers (approximately 3.8 pixels respectively 18 µm for all experts). The area deviations between the automated and manual segmentation also lie within the range of the area deviations among the 3 clinical experts. Intra reader variability for the experts was between 0.9 and 0.94. We conclude that the automated segmentation approach is able to segment blood vessels with comparable accuracy as expert readers and will provide a useful tool in vessel analysis of whole C-scans, and in particular in multicenter trials.

© 2012 OSA

## 1. Introduction

1. W. Geitzenauer, C. K. Hitzenberger, and U. M. Schmidt-Erfurth, “Retinal optical coherence tomography: past, present and future perspectives,” Br. J. Ophthalmol. **95**(2), 171–177 (2011). [CrossRef] [PubMed]

2. A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,” IEEE Trans. Med. Imaging **19**(3), 203–210 (2000). [CrossRef] [PubMed]

4. C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,” Br. J. Ophthalmol. **83**(8), 902–910 (1999). [CrossRef] [PubMed]

5. M. Niemeijer, M. K. Garvin, B. van Ginneken, M. Sonka, and M. D. Abràmoff, “Vessel segmentation in 3D spectral OCT scans of the retina,” Proc. SPIE **6914**, 69141R, 69141R-8 (2008). [CrossRef]

*i.e.*all images that were not used for training) by classification. Again, an axial segmentation of the blood vessels is not performed.

## 2. Materials and methods

### 2.1. Speckle noise reduction

8. D. C. Fernández, “Delineating fluid-filled region boundaries in optical coherence tomography images of the retina,” IEEE Trans. Med. Imaging **24**(8), 929–945 (2005). [CrossRef] [PubMed]

9. P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell. **12**(7), 629–639 (1990). [CrossRef]

10. V. Kajić, B. Považay, B. Hermann, B. Hofer, D. Marshall, P. L. Rosin, and W. Drexler, “Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis,” Opt. Express **18**(14), 14730–14744 (2010). [CrossRef] [PubMed]

11. I. W. Selesnick, R. G. Baraniuk, and N. G. Kingsbury, “The dual-tree complex wavelet transform,” IEEE Signal Process. Mag. **22**(6), 123–151 (2005). [CrossRef]

12. A. Wong, A. Mishra, K. Bizheva, and D. A. Clausi, “General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery,” Opt. Express **18**(8), 8338–8352 (2010). [CrossRef] [PubMed]

### 2.2. Statistical shape model creation

13. T. Cootes, C. Taylor, D. Cooper, and J. Graham, “Active shape models—their training and application,” Comput. Vis. Image Underst. **61**(1), 38–59 (1995). [CrossRef]

*n*landmarks

_{x=(x1,y1,x2,y2,...,xn,yn)}, in which the number of landmarks must be the same for all objects of the sample. Corresponding landmarks of the manual segmentations are aligned by performing translation, rotation and scaling using a Procrustes analysis.

_{x¯}represents the mean object shape of the sample with

*s*elements, where the landmarks of all objects are averaged by Eq. (1):

*d*

*x**from the mean shape is calculated by Eq. (2) and the covariance matrix is calculated by Eq. (3):*

_{t}

*p**(eigenvectors) and the corresponding variances*

_{l}*λ*(eigenvalues) of

_{l}**. The matrix**

*S***is built from each eigenvector ordered in descending order of the eigenvalues**

*P**λ*in Eq. (4):

_{l}*t*modes of variation are chosen until the accumulated variance

*λ*reaches a certain ratio. Here the common ratio of 0.98 was chosen, and the retinal blood vessel model includes 98% of the training set shape variations.

_{l}**of the training set is then approximated by Eq. (5):**

*x***within suitable limits in order to position the population of landmarks between three times the standard deviation in Eq. (6):**

*b*_{M(s,θ)[]}is a scaling by

*s*and a rotation by

*θ*, and

_{XC}defines the center position.

### 2.3. Grey-level appearance model creation

*i*of each image

*I**the grey-level profile*

_{j}

*g**of*

_{ij}*n*pixel length is sampled on the normal to the boundary (see Fig. 4 ). We used a profile length of 25 pixels. The

_{p}*k*th grey-level element of the profile is sampled by Eq. (8):

### 2.4. Search for objects in unseen images

*n*). The model profile is compared to the sampled profile to find the best position. We used the Mahalanobis distance to calculate the optimal fit position between the grey-level profile of the object in the new image and the model profile for each landmark

_{p}*i*by Eq. (12):

*h**(d)*is a sub-interval of the model profile length

*n*of the sampled profile (length >

_{p}*n*) centered at

_{p}*d*[14]. Therefore, for each shape model landmark a vector with position movements results in Eq. (13):

**should be moved to the best new locations (**

*X*

*X**+ d*

**), which need to be within conformable possible object shape variations. This is achieved by finding the deviations in translation (**

*X**dX*), rotation

_{c}, dY_{c}*dθ*and scale

*ds*that fit best the current instance to the new positions (

*X**+ d*

**). This is done by the Procrustes analysis. The residual adjustments**

*X**d*

**in the local model coordinate frame is given by Eq. (14):**

*x*_{y=M(s,θ)[x]+dX−dXC}. To adjust the model points as closely to

*d*

**as possible, the changes of the shape coefficients**

*x**d*

**is defined by Eq. (16):**

*b*### 2.5. Initialization

15. A. Kelemen, G. Székely, and G. Gerig, “Elastic model-based segmentation of 3-D neuroradiological data sets,” IEEE Trans. Med. Imaging **18**(10), 828–839 (1999). [CrossRef] [PubMed]

16. H. Lamecker, M. Seebaß, H.-C. Hege, and P. Deuflhard, “A 3D statistical shape model of the pelvic bone for segmentation,” Proc. SPIE **5370**, 1341–1351 (2004). [CrossRef]

22. A. Hill and C. Taylor, “Model-based image interpretation using genetic algorithms,” Image Vis. Comput. **10**(5), 295–300 (1992). [CrossRef]

23. H. Wehbe, M. Ruggeri, S. Jiao, G. Gregori, C. A. Puliafito, and W. Zhao, “Automatic retinal blood flow calculation using spectral domain optical coherence tomography,” Opt. Express **15**(23), 15193–15206 (2007). [CrossRef] [PubMed]

*x*Eq. (17):

*h*is the height of the B-scan image. Figure 6a shows the switch from a non-vessel A-scan to an A-scan with blood vessel and the effect on the grey-level center, and Fig. 6b shows the center positions for all A-scans of the image marked as green line. In A-scans with blood vessels, the peaks of the grey-level center are strong, which means that the lateral position and the width of the blood vessel shadows were determined by thresholding.

## 3. Results

9. P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell. **12**(7), 629–639 (1990). [CrossRef]

### 3.1. Mean Euclidian distance comparison

**(in this case**

*A***is the set of automated landmarks) and a second set**

*A***(in this case**

*M***is the set of expert’s landmarks) is calculated by Eq. (18):**

*M**n*is the number of landmarks within the set

**and**

*M**b*within the set

**.**

*A***(**

*A**a*) and

**(**

*M**m*) represent the coordinate vector of the

*a*th and

*m*th landmark.

_{d¯(A,M)≠d¯(M,A)}. To get a symmetric definition, Eq. (19) is calculated:

### 3.2. Contour Area Comparison

^{2}for the segmentations of expert 3 and the maximal surface area is 13969 ± 9461 µm

^{2}for the segmentations of expert 2. The automated segmentations were well within the range of the minimal and maximal surface areas (12435 ± 8738 µm

^{2}).

24. J. M. Bland and D. G. Altman, “Statistical methods for assessing agreement between two methods of clinical measurement,” Lancet **327**(8476), 307–310 (1986). [CrossRef] [PubMed]

^{2}(2×SD) for expert 1, while the biggest discrepancy is a mean area deviation of 1397 ± 9214 µm

^{2}(2×SD) for expert 3. Similarly, the smallest discrepancy among the experts is between expert 1 and expert 2 with a mean area deviation of −1153 ± 10856 µm

^{2}(2×SD), while the biggest discrepancy is between the segmentations of expert 2 and expert 3 with a mean area deviation of 3008 ± 9402 µm

^{2}(2×SD).

## 4. Discussion

10. V. Kajić, B. Považay, B. Hermann, B. Hofer, D. Marshall, P. L. Rosin, and W. Drexler, “Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis,” Opt. Express **18**(14), 14730–14744 (2010). [CrossRef] [PubMed]

23. H. Wehbe, M. Ruggeri, S. Jiao, G. Gregori, C. A. Puliafito, and W. Zhao, “Automatic retinal blood flow calculation using spectral domain optical coherence tomography,” Opt. Express **15**(23), 15193–15206 (2007). [CrossRef] [PubMed]

## Acknowledgment

## References and links

1. | W. Geitzenauer, C. K. Hitzenberger, and U. M. Schmidt-Erfurth, “Retinal optical coherence tomography: past, present and future perspectives,” Br. J. Ophthalmol. |

2. | A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,” IEEE Trans. Med. Imaging |

3. | A. Budai, G. Michelson, and J. Hornegger, “Multiscale Blood Vessel Segmentation in Retinal Fundus Images,” in |

4. | C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,” Br. J. Ophthalmol. |

5. | M. Niemeijer, M. K. Garvin, B. van Ginneken, M. Sonka, and M. D. Abràmoff, “Vessel segmentation in 3D spectral OCT scans of the retina,” Proc. SPIE |

6. | J. Xu, D. Tolliver, H. Ishikawa, C. Wollstein, and J. Schuman, “Blood vessel segmentation with three-dimensional spectral domain optical coherence tomography,” International Patent no. WO/2010/138645 (Feb. 12, 2010). |

7. | K. Lee, “Segmentations of the intraretinal surfaces, optic disc and retinal blood vessels in 3D-OCT scans,” Ph.D. dissertation (University of Iowa, 2009), pp. 57–69. |

8. | D. C. Fernández, “Delineating fluid-filled region boundaries in optical coherence tomography images of the retina,” IEEE Trans. Med. Imaging |

9. | P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell. |

10. | V. Kajić, B. Považay, B. Hermann, B. Hofer, D. Marshall, P. L. Rosin, and W. Drexler, “Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis,” Opt. Express |

11. | I. W. Selesnick, R. G. Baraniuk, and N. G. Kingsbury, “The dual-tree complex wavelet transform,” IEEE Signal Process. Mag. |

12. | A. Wong, A. Mishra, K. Bizheva, and D. A. Clausi, “General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery,” Opt. Express |

13. | T. Cootes, C. Taylor, D. Cooper, and J. Graham, “Active shape models—their training and application,” Comput. Vis. Image Underst. |

14. | T. Cootes, C. Taylor, A. Lanitis, D. Cooper, and J. Graham, “Building and using flexible models incorporating grey-level information,” in |

15. | A. Kelemen, G. Székely, and G. Gerig, “Elastic model-based segmentation of 3-D neuroradiological data sets,” IEEE Trans. Med. Imaging |

16. | H. Lamecker, M. Seebaß, H.-C. Hege, and P. Deuflhard, “A 3D statistical shape model of the pelvic bone for segmentation,” Proc. SPIE |

17. | J. Hug, C. Brechbühler, and G. Székely, “Model-based Initialisation for Segmentation,” in |

18. | G. Edwards, T. Cootes, and C. Taylor, “Advances in active appearance models,” |

19. | R. Fisker, N. Schultz, N. Duta, and J. Carstensen, “A general scheme for training and optimization of the Grenander deformable template model,” in |

20. | M. Stegmann, R. Fisker, and B. Ersbøll, “Extending and applying active appearance models for automated, high precision segmentation in different image modalities,” in |

21. | D. Goldberg, |

22. | A. Hill and C. Taylor, “Model-based image interpretation using genetic algorithms,” Image Vis. Comput. |

23. | H. Wehbe, M. Ruggeri, S. Jiao, G. Gregori, C. A. Puliafito, and W. Zhao, “Automatic retinal blood flow calculation using spectral domain optical coherence tomography,” Opt. Express |

24. | J. M. Bland and D. G. Altman, “Statistical methods for assessing agreement between two methods of clinical measurement,” Lancet |

25. | H. Fleiss, |

**OCIS Codes**

(100.0100) Image processing : Image processing

(110.6880) Imaging systems : Three-dimensional image acquisition

(170.4500) Medical optics and biotechnology : Optical coherence tomography

(100.3008) Image processing : Image recognition, algorithms and filters

**ToC Category:**

Image Processing

**History**

Original Manuscript: February 24, 2012

Revised Manuscript: May 25, 2012

Manuscript Accepted: May 28, 2012

Published: June 4, 2012

**Citation**

Matthäus Pilch, Yaroslava Wenner, Elisabeth Strohmayr, Markus Preising, Christoph Friedburg, Erdmuthe Meyer zu Bexten, Birgit Lorenz, and Knut Stieger, "Automated segmentation of retinal blood vessels in spectral domain optical coherence tomography scans," Biomed. Opt. Express **3**, 1478-1491 (2012)

http://www.opticsinfobase.org/boe/abstract.cfm?URI=boe-3-7-1478

Sort: Year | Journal | Reset

### References

- W. Geitzenauer, C. K. Hitzenberger, and U. M. Schmidt-Erfurth, “Retinal optical coherence tomography: past, present and future perspectives,” Br. J. Ophthalmol.95(2), 171–177 (2011). [CrossRef] [PubMed]
- A. Hoover, V. Kouznetsova, and M. Goldbaum, “Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response,” IEEE Trans. Med. Imaging19(3), 203–210 (2000). [CrossRef] [PubMed]
- A. Budai, G. Michelson, and J. Hornegger, “Multiscale Blood Vessel Segmentation in Retinal Fundus Images,” in Proceedings of Bildverarbeitung für die Medizin (Springer Verlag, 2010), pp. 261–265.
- C. Sinthanayothin, J. F. Boyce, H. L. Cook, and T. H. Williamson, “Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images,” Br. J. Ophthalmol.83(8), 902–910 (1999). [CrossRef] [PubMed]
- M. Niemeijer, M. K. Garvin, B. van Ginneken, M. Sonka, and M. D. Abràmoff, “Vessel segmentation in 3D spectral OCT scans of the retina,” Proc. SPIE6914, 69141R, 69141R-8 (2008). [CrossRef]
- J. Xu, D. Tolliver, H. Ishikawa, C. Wollstein, and J. Schuman, “Blood vessel segmentation with three-dimensional spectral domain optical coherence tomography,” International Patent no. WO/2010/138645 (Feb. 12, 2010).
- K. Lee, “Segmentations of the intraretinal surfaces, optic disc and retinal blood vessels in 3D-OCT scans,” Ph.D. dissertation (University of Iowa, 2009), pp. 57–69.
- D. C. Fernández, “Delineating fluid-filled region boundaries in optical coherence tomography images of the retina,” IEEE Trans. Med. Imaging24(8), 929–945 (2005). [CrossRef] [PubMed]
- P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell.12(7), 629–639 (1990). [CrossRef]
- V. Kajić, B. Považay, B. Hermann, B. Hofer, D. Marshall, P. L. Rosin, and W. Drexler, “Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis,” Opt. Express18(14), 14730–14744 (2010). [CrossRef] [PubMed]
- I. W. Selesnick, R. G. Baraniuk, and N. G. Kingsbury, “The dual-tree complex wavelet transform,” IEEE Signal Process. Mag.22(6), 123–151 (2005). [CrossRef]
- A. Wong, A. Mishra, K. Bizheva, and D. A. Clausi, “General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery,” Opt. Express18(8), 8338–8352 (2010). [CrossRef] [PubMed]
- T. Cootes, C. Taylor, D. Cooper, and J. Graham, “Active shape models—their training and application,” Comput. Vis. Image Underst.61(1), 38–59 (1995). [CrossRef]
- T. Cootes, C. Taylor, A. Lanitis, D. Cooper, and J. Graham, “Building and using flexible models incorporating grey-level information,” in Fourth International Conference on Computer Vision, 1993. Proceedings (1993), pp. 242–246.
- A. Kelemen, G. Székely, and G. Gerig, “Elastic model-based segmentation of 3-D neuroradiological data sets,” IEEE Trans. Med. Imaging18(10), 828–839 (1999). [CrossRef] [PubMed]
- H. Lamecker, M. Seebaß, H.-C. Hege, and P. Deuflhard, “A 3D statistical shape model of the pelvic bone for segmentation,” Proc. SPIE5370, 1341–1351 (2004). [CrossRef]
- J. Hug, C. Brechbühler, and G. Székely, “Model-based Initialisation for Segmentation,” in Computer Vision—ECCV 2000 (Springer, 2000), pp. 290–306.
- G. Edwards, T. Cootes, and C. Taylor, “Advances in active appearance models,” The Proceedings of the Seventh IEEE International Conference on Computer Vision (IEEE, 1999), Vol. 1, pp. 137–142.
- R. Fisker, N. Schultz, N. Duta, and J. Carstensen, “A general scheme for training and optimization of the Grenander deformable template model,” in IEEE Conference on Computer Vision and Pattern Recognition,2000. Proceedings (IEEE, 2000), pp. 698–705.
- M. Stegmann, R. Fisker, and B. Ersbøll, “Extending and applying active appearance models for automated, high precision segmentation in different image modalities,” in Scandinavian Conference on Image Analysis, (2001), pp. 90–97.
- D. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning (Addison-Wesley, Bonn, 1989).
- A. Hill and C. Taylor, “Model-based image interpretation using genetic algorithms,” Image Vis. Comput.10(5), 295–300 (1992). [CrossRef]
- H. Wehbe, M. Ruggeri, S. Jiao, G. Gregori, C. A. Puliafito, and W. Zhao, “Automatic retinal blood flow calculation using spectral domain optical coherence tomography,” Opt. Express15(23), 15193–15206 (2007). [CrossRef] [PubMed]
- J. M. Bland and D. G. Altman, “Statistical methods for assessing agreement between two methods of clinical measurement,” Lancet327(8476), 307–310 (1986). [CrossRef] [PubMed]
- H. Fleiss, Statistical Methods for Rates and Proportions, 2nd ed. (Wiley New York, 1981).

## Cited By |
Alert me when this paper is cited |

OSA is able to provide readers links to articles that cite this paper by participating in CrossRef's Cited-By Linking service. CrossRef includes content from more than 3000 publishers and societies. In addition to listing OSA journal articles that cite this paper, citing articles from other participating publishers will also be listed.

OSA is a member of CrossRef.