Neural Computing and Applications

, Volume 29, Issue 8, pp 159–180 | Cite as

Noise-estimation-based anisotropic diffusion approach for retinal blood vessel segmentation

  • Mariem Ben Abdallah
  • Ahmad Taher Azar
  • Hichem Guedri
  • Jihene Malek
  • Hafedh Belmabrouk
New Trends in data pre-processing methods for signal and image classification
  • 119 Downloads

Abstract

Recently, numerous research works in retinal-structure analysis have been performed to analyze retinal images for diagnosing and preventing ocular diseases such as diabetic retinopathy, which is the first most common causes of vision loss in the world. In this paper, an algorithm for vessel detection in fundus images is employed. First, a denoising process using the noise-estimation-based anisotropic diffusion technique is applied to restore connected vessel lines in a retinal image and eliminate noisy lines. Next, a multi-scale line-tracking algorithm is implemented to detect all the blood vessels having similar dimensions at a selected scale. An openly available dataset, called “the STARE Project’s dataset,” has been firstly utilized to evaluate the accuracy of the proposed method. Accordingly, our experimental results, performed on the STARE dataset, depict a maximum average accuracy of around 93.88%. Then, an experimental evaluation on another dataset, named DRIVE database, demonstrates a satisfactory performance of the proposed technique, where the maximum average accuracy rate of 93.89% is achieved.

Keywords

Segmentation Filtering RGB noise model Anisotropic diffusion Vessel Retina 

Abbreviations

ANRAD

Adaptive noise-reducing anisotropic diffusion filter

DPAD

Detail preserving anisotropic diffusion

FBAD

Flux-based anisotropic diffusion

NLF

Noise level function

MLE

Maximum likelihood estimator

\({\text{FPR}}\)

False-positive rate

\({\text{MAA}}\)

Maximum average accuracy

\({\text{MSSIM}}\)

Mean structural similarity index measure

PMAD

Anisotropic diffusion of perona and malik

\({\text{SNR}}\)

Signal-to-noise ratio

SRAD

Specle reducing anisotropic diffusion

\({\text{TPR}}\)

True positive rate

List of symbols

x

Image pixel

f

Response function of a camera

L

Irradiance image

I

Image intensity

IN

Noisy image

Ns

Multiplicative noise

Nc

Additive noise

σc2

Variance of additive noise

σs2

Variance of multiplicative noise

Nq

Quantization noise

2

Noise model

IE(.)

Expectation of a random variable

\(\overline{{\sum^{2} }}\)

Mean of principal components

ωη

Eigenvectors of principal components

m

Number of retained eigenvectors

αη

Unknown parameters of noise model

η

Index of unknown parameters of noise model

i, j

Spatial coordinates of current pixel x

wi,j

Window centered at current pixel

c

Instantaneous coefficient of the variation of the image

cn2

Instantaneous coefficient of the variation of the noise

φ

Diffusion function

Var

Local variance

\(\overline{I}^{2}\)

Square of local mean intensity

Δt

Step time

iter

Iteration number of ANRAD filter

Gradient operator

div

Divergence operator

κ

Discretization number

t

Continuous scale parameter

G

Convolution kernel

∂ 

Derivative operator

σmin

Minimal scale

σmax

Maximal scale

Θ

Image orientation

Γσ

Response function at scale σ

Γmulti

Multi-scale response

\(\overrightarrow {d}\)

Unitary vector of direction Θ

\(\overrightarrow {v}_{1}\)

First eigenvector of Hessian matrix

\(\overrightarrow {v}_{2}\)

Second eigenvector of Hessian matrix

λ1

First eigenvalue of Hessian matrix

λ2

Second eigenvalue of Hessian matrix

r

Radius vessel

[tmintmax]

Scale range

\(I^{ '} \,\)

Interpolated image

\(Q_{11} \, , \, Q_{12} \, , \, Q_{21} \, , \, Q_{22}\)

Four nearest pixel values of pixel \(x\)

di

Displacement along i-axis

dj

Displacement along j-axis

Thres

Threshold on norm gradient of image

\(N\)

Iteration number of PMAD method

References

  1. 1.
    Asad AH, Azar AT, Hassaanien AE (2012) Integrated features based on gray-level and hu moment-invariants with ant colony system for retinal blood vessels segmentation. Int J Syst Biol Biomed Technol (IJSBBT) 1(4):60–73Google Scholar
  2. 2.
    Pal NR, Pal SK (1993) A review on image segmentation techniques. Pattern Recogn 26(9):1277–1294CrossRefGoogle Scholar
  3. 3.
    El-Baz AS, Acharya R, Mirmehdi M, Suri JS (2011) Multi modality state-of-the-art medical image segmentation and registration methodologies, vol 1. Springer, New YorkCrossRefGoogle Scholar
  4. 4.
    Kauppi T et al (2010) Eye fundus image analysis for automatic detection of diabetic retinopathy. Lappeenranta University of Technology, LappeenrantaGoogle Scholar
  5. 5.
    Asad AH, Azar AT, Hassanien AE (2013) Ant colony-based system for retinal blood vessels segmentation. In: Proceedings of seventh international conference on bio-inspired computing: theories and applications (BICTA 2012) advances in intelligent systems and computing volume 201, 2013, pp 441–452. doi: 10.1007/978-81-322-1038-237
  6. 6.
    Asad AH, Azar AT, Hassanien AE (2014) A new heuristic function of ant colony system for retinal vessel segmentation. Int J Rough Sets Data Anal 1(2):15–30CrossRefGoogle Scholar
  7. 7.
    Asad AH, Azar AT, Hassanien AE (2014) A comparative study on feature selection for retinal vessel segmentation using ant colony system. Recent Adv Intell Inform Adv Intell Syst Comput 235(2014):1–11. doi: 10.1007/978-3-319-01778-51 Google Scholar
  8. 8.
    Fritzsche K, Can A., Shen H, Tsai C, Turner J, Stewart C, Roysam B (2003) Automated model based segmentation, tracing and analysis of retinal vasculature from digital fundus images. In: Suri JS, Laxminarayan S (eds) State-of-the-art angiography, applications and plaque imaging using MR, CT, ultrasound and X-rays. Academic Press, pp 225–298Google Scholar
  9. 9.
    Cheng J, Liu J, Yanwu X, Yin F, Wong DWK, Tan N-M, Tao D, Cheng Ching-Yu, Aung T, Wong TY (2013) Superpixel classification based optic disc and optic cup segmentation for glaucoma screening. IEEE Trans Med Imaging 32(6):1019–1032CrossRefGoogle Scholar
  10. 10.
    Malek J, Azar AT (2016) 3D Surface Reconstruction of Retinal Vascular Structures. International Journal of Modelling, Identification and Control (IJMIC), Inderscience Publishers, Olney, UK. (in press)Google Scholar
  11. 11.
    Malek J, Azar AT, Tourki R (2015) Impact of retinal vascular tortuosity on retinal circulation. Neural Comput Appl 26(1):25–40. doi: 10.1007/s00521-014-1657-2 CrossRefGoogle Scholar
  12. 12.
    Malek J, Azar AT, Nasralli B, Tekari M, Kamoun H, Tourki R (2015) Computational analysis of blood flow in the retinal arteries and veins using fundus image. Comput Math Appl 69(2):101–116CrossRefMATHGoogle Scholar
  13. 13.
    Malek J, Azar AT (2016) A computational flow model of oxygen transport in really retinal network. International Journal of Modelling, Identification and Control (IJMIC), Inderscience Publishers, Olney, UK. (in press)Google Scholar
  14. 14.
    Sofka M, Stewart CV (2006) Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures. IEEE Trans Med Imaging 25(12):1531–1546CrossRefGoogle Scholar
  15. 15.
    Zhang B, Zhang L, Zhang L, Karray F (2010) Retinal vessel extraction by matched filter with first-order derivative of Gaussian. Comput Biol Med 40(4):438–445CrossRefGoogle Scholar
  16. 16.
    Hutchinson A, McIntosh A, Peters J, O’keeffe C, Khunti K, Baker R, Booth A (2000) Effectiveness of screening and monitoring tests for diabetic retinopathy—a systematic review. Diabet Med 17(7):495–506CrossRefGoogle Scholar
  17. 17.
    Hou Y (2014) Automatic segmentation of retinal blood vessels based on improved multiscale line detection. J Comput Sci Eng 8(2):119–128CrossRefGoogle Scholar
  18. 18.
    Nguyen UT, Bhuiyan A, Park LA, Ramamohanarao K (2013) An effective retinal blood vessel segmentation method using multi-scale line detection. Pattern Recogn 46(3):703–715CrossRefGoogle Scholar
  19. 19.
    Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639CrossRefGoogle Scholar
  20. 20.
    Yu Y, Acton ST (2002) Speckle reducing anisotropic di_usion. IEEE Trans Image Process 11(11):1260–1270. doi: 10.1109/TIP.2002.804276 MathSciNetCrossRefGoogle Scholar
  21. 21.
    Krissian K (2002) Flux-based anisotropic diffusion applied to enhancement of 3-D angiogram. IEEE Trans Med Imaging 21(11):1440–1442CrossRefGoogle Scholar
  22. 22.
    Aja-Fernández S, Vegas-Sánchez-Ferrero G, Martín-Fernández M, Alberola-López C (2009) Automatic noise estimation in images using local statistics. Additive and multiplicative cases. Image Vis Comput 27(6):756–770CrossRefGoogle Scholar
  23. 23.
    Ben Abdallah M, Malek J, Azar AT, Montesinos P, Belmabrouk H, Monreal JE, Krissian K (2015) Automatic extraction of blood vessels in the retinal vascular tree using multiscale medialness. Int J Biomed Imaging 2015:519024-1–519024-16. doi: 10.1155/2015/519024 CrossRefGoogle Scholar
  24. 24.
    Emary E, Zawbaa H, Hassanien AE, Schaefer G, Azar AT (2014b) Retinal vessel segmentation based on possibilistic fuzzy c-means clustering optimised with cuckoo search. In: IEEE 2014 international joint conference on neural networks (IJCNN 2014), July 6–11, Beijing International Convention Center, Beijing, ChinaGoogle Scholar
  25. 25.
    Asad AH, Azar AT, Hassanien AE (2013) An improved ant colony system for retinal vessel segmentation. In: 2013 federated conference on computer science and information systems (FedCSIS), Krakow, Poland, September 8–11, 2013Google Scholar
  26. 26.
    Emary E, Zawbaa H, Hassanien AE, Schaefer G, Azar AT (2014a) Retinal blood vessel segmentation using bee colony optimization and pattern search. In: IEEE 2014 international joint conference on neural networks (IJCNN 2014), July 6–11, Beijing International Convention Center, Beijing, ChinaGoogle Scholar
  27. 27.
    Chaudhuri S, Chateterjee S, Katz N, Nelson M, Goldbaum M (1989) Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imaging 8(3):263–269CrossRefGoogle Scholar
  28. 28.
    Chanwimaluang T, Fan G (2003) An efficient algorithm for extraction of anatomical structures in retinal images. In: Proceedings of ICIP, pp 1193–1196Google Scholar
  29. 29.
    Fraz MM, Barman SA, Remagnino P et al (2012) An approach to localize the retinal blood vessels using bit planes and centerline detection. Comput Methods Programs Biomed 108(2):600616CrossRefGoogle Scholar
  30. 30.
    Zhou L, Rzeszotarski MS, Singerman LJ, Chokreff JM (1994) The detection and quantification of retinopathy using digital angiograms. IEEE Trans Med Imaging 13(4):619–626CrossRefGoogle Scholar
  31. 31.
    Goa X, Bharath A, Stanton A, Hughes A, Chapman N, Thom S (2001) A method of vessel tracking for vessel diameter measurement on retinal images. In: Proceedings ICIP, pp 881–884Google Scholar
  32. 32.
    Chutatape O, Zheng L, Krishnan SM (1998) Retinal blood vessel detection and tracking by matched Gaussian and Kalman filters. In Proceedings 20th annual international conference IEEE engineering in medicine and biology, pp 3144–3149Google Scholar
  33. 33.
    Can A, Shen H, Turner JN, Tanenbaum HL, Roysam B (1999) Rapid automated tracing and feature extraction from retinal fundus images using direct exploratory algorithms. IEEE Trans Inf Technol Biomed 3(2):125–138CrossRefGoogle Scholar
  34. 34.
    Hani AFM, Soomro TA, Faye I, Kamel N, Yahya N (2014) Denoising methods for retinal fundus images. In: 2014 IEEE international conference on intelligent and advanced systems (ICIAS), Kuala Lumpur, 3–5 June, 2014, pp 1–6. doi: 10.1109/ICIAS.2014.6869534
  35. 35.
    Malek J, Tourki R (2013) Inertia-based vessel centerline extraction in retinal image. In: IEEE 2013 international conference on control, decision and information technologies (CoDIT), pp 378–381Google Scholar
  36. 36.
    Healey GE, Kondepudy R (1994) Radiometric CCD camera calibration and noise estimation. IEEE Trans Pattern Anal Mach Intell 16(3):267–276CrossRefGoogle Scholar
  37. 37.
    Irie K, McKinnon AE, Unsworth K, Woodhead IM (2008) A model for measurement of noise in CCD digital-video cameras. Meas Sci Technol 19(4):045207CrossRefGoogle Scholar
  38. 38.
    Liu X, Tanaka M, Okutomi M (2013) Estimation of signal dependent noise parameters from a single image. In: ICIP, pp 79–82Google Scholar
  39. 39.
    Gravel P, Beaudoin G, De Guise JA (2004) A method for modeling noise in medical images. IEEE Trans Med Imaging 23(10):1221–1232CrossRefGoogle Scholar
  40. 40.
    Liu C, Szeliski R, Kang SB, Lawrence Zitnick C, Freeman WT (2008) Automatic estimation and removal of noise from a single image. IEEE Trans Pattern Anal Mach Intell 30(2):299–314CrossRefGoogle Scholar
  41. 41.
    Ben Abdallah M, Malek J, Azar AT, Belmabrouk H, Monreal JE, Krissian K (2016) Adaptive noise-reducing anisotropic diffusion filter. Neural Comput Appl 27(5):1273–1300CrossRefGoogle Scholar
  42. 42.
    Ben Abdallah M, Malek J, Tourki R, Monreal JE, Krissian K (2013) Automatic estimation of the noise model in fundus images. In: IEEE 2013 10th international multi-conference on systems, signals & devices (SSD), pp 1–5Google Scholar
  43. 43.
    Arthur D, Vassilvitskii S (2007) k-means + + : the advantages of careful seeding. In: Proceedings of the eighteenth annual ACMSIAM symposium on discrete algorithms. New Orleans, pp 1027–1035. 7–9. doi: 10.1145/1283383.1283494
  44. 44.
    Wu CH, Agam G, Stanchev P (2007) A general framework for vessel segmentation in retinal images. In: IEEE 2007 International symposium on computational intelligence in robotics and automation CIRA 2007, pp 37–42Google Scholar
  45. 45.
    Hoover A, Kouznetsova V, Goldbaum M (2000) Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging 19(3):203–210CrossRefGoogle Scholar
  46. 46.
    Qian X, Brennan MP, Dione DP, Dobrucki WL, Jackowski MP, Breuer CK, Sinusas AJ, Papademetris X (2009) A non-parametric vessel detection method for complex vascular structures. Med Image Anal 13(1):49–61CrossRefGoogle Scholar
  47. 47.
    Hai TTT, Augustin L (2003) Extraction de Caract´eristiques locales: Crêtes et Pics. Book: RIVFGoogle Scholar
  48. 48.
    Ersoy I, Bunyak F, Mackey MA, Palaniappan K (2008) Cell segmentation using Hessian-based detection and contour evolution with directional derivatives. In: 15th IEEE international conference on image processing, 2008. ICIP 2008Google Scholar
  49. 49.
    Sato Y, Nakajima S, Atsumi H, Koller T, Gerig G, Yoshida S, Kikinis R (1997) 3D multi-scale line filter for segmentation and visualization of curvilinear structures in medical images, CVRMed-MRCAS’97Google Scholar
  50. 50.
    Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering, medical image computing and computer-assisted interventation-MICCAI’98. Springer, New YorkGoogle Scholar
  51. 51.
    Witkin AP (1984) Scale-space filtering: a new approach to multiscale description. In: Acoustics, speech, and signal processing, IEEE international conference on ICASSP’84, vol 9, pp 150–153Google Scholar
  52. 52.
    Koenderink JJ (1984) The structure of images. Biol Cybern 50(5):363–370MathSciNetCrossRefMATHGoogle Scholar
  53. 53.
    Lindeberg T (1994) Scale-space theory: a basic tool for analyzing structures at different scales. J Appl Stat 21(1–2):225–270CrossRefGoogle Scholar
  54. 54.
    Sporring J, Florack L, Nielsen M, Johansen P (1997) Gaussian scale-space theory. Kluwer Academic Publishers, DordrechtCrossRefMATHGoogle Scholar
  55. 55.
    Florack L (1997) Image structure. Kluwer Academic Publishers, DordrechtCrossRefGoogle Scholar
  56. 56.
    Haar Romeny BM (2003) Front-end vision and multi-scale image analysis: multi-scale computer vision theory and applications, written in mathematica, vol 27. Springer, New YorkCrossRefGoogle Scholar
  57. 57.
    Abdallah MB, Malek J, Krissian K, Tourki R (2011) An automated vessel segmentation of retinal images using multiscale vesselness. In: 2011 8th international multi-conference on systems signals and devices (SSD). IEEE, pp 1–6Google Scholar
  58. 58.
    Prajapati A, Naik S, Mehta S (2012) Evaluation of different image interpolation algorithms. Int J Comput Appl 58(12):6–12Google Scholar
  59. 59.
    Zhang M, Wang J, Li Z, Li Y (2010) An adaptive image zooming method with edge enhancement. In: 3rd international conference on advanced computer theory and engineering (ICACTE), pp 608–611Google Scholar
  60. 60.
    Tam WS, Kok CW, Siu WC (2009) A modified edge directed interpolation for images. In: 17th European signal processing conference (ESPC)Google Scholar
  61. 61.
    Hoover A (1995) STARE database. http://www.ces.clemson.edu/ahoover/stare
  62. 62.
    Niemeijer M, Staal J, van Ginneken B, Loog M, Abramoff MD (2004) Comparative study of retinal vessel segmentation methods, on a new publicly available database Medical. Imaging 2004:648–656Google Scholar
  63. 63.
    Niemeijer M, van Ginneken B (2002) Drive database URL www.isi.uu.nl/Research/Databases/DRIVE/results.php
  64. 64.
    Martens JB, Meesters L (1998) Image dissimilarity. Signal Process 70(3):155–176. doi: 10.1016/S0165-1684(98)00123-6 CrossRefMATHGoogle Scholar
  65. 65.
    Aja-Fernandez S, Alberola-Lopez C (2006) On the estimation of the coefficient of variation for anisotropic diffusion speckle filtering. IEEE Trans Image Process 15(9):2694–2701. doi: 10.1109/TIP.2006.877360 CrossRefGoogle Scholar
  66. 66.
    Staal J, Abr`amoff MD, Niemeijer M, Viergever MA, van Ginneken B (2004) Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4):501–509CrossRefGoogle Scholar
  67. 67.
    Soares JVB, Leandro JJG, Cesar RM Jr, Jelinek HF, Cree MJ (2006) Retinal vessel segmentation using the 2-D Gabor wavelet and supervised classification. IEEE Trans Med Imaging 25(9):1214–1222CrossRefGoogle Scholar
  68. 68.
    Soares JVB, Leandro JJG, Cesar RM Jr, Jeline KHF, Cree MJ (2006) Retinal vessel segmen-tation using the 2D Morlet wavelet and supervised classification. IEEE Trans Med Imaging 25(9):1214–1222CrossRefGoogle Scholar
  69. 69.
    Staal JJ, Abramoff MD, Niemeijer M, Viergever MA, van Ginneken B (2004) Ridge based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23(4):501–509CrossRefGoogle Scholar
  70. 70.
    Sinthanayothin C, Boyce J, Williamson CT (1999) Automated localisation of the optic disk, fovea, and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83:902–910CrossRefGoogle Scholar
  71. 71.
    Zhang B, Zhang L, Zhang L, Karray F (2010) Retinal vessel extraction by matched filter with first-order derivative of Gaussian. Comput Biol Med 4(40):438–445CrossRefGoogle Scholar
  72. 72.
    Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaum M (1989) Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imaging 8(3):263–269CrossRefGoogle Scholar
  73. 73.
    Martinez-Perez ME, Hughes AD, Thom SA, Bharath AA, Parker KH (2007) Segmentation of blood vessels from red-free and uorescein retinal images. Med Image Anal 11(1):47–61CrossRefGoogle Scholar
  74. 74.
    Mendonca AM, Campilho A (2006) Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans Med Imaging 25(9):1200–1213CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • Mariem Ben Abdallah
    • 1
    • 2
    • 3
    • 4
  • Ahmad Taher Azar
    • 1
    • 2
    • 3
    • 4
  • Hichem Guedri
    • 1
    • 2
    • 4
  • Jihene Malek
    • 1
    • 2
    • 4
  • Hafedh Belmabrouk
    • 1
    • 2
    • 4
  1. 1.Electronics and Micro-Electronic LaboratoryMonastir UniversityMonastirTunisia
  2. 2.Faculty of Computers and InformationBenha UniversityBenhaEgypt
  3. 3.Nanoelectronics Integrated Systems Center (NISC)Nile UniversityCairoEgypt
  4. 4.Department of Physics, College of Science in ZulfiMajmaah UniversityAl Majma’ahSaudi Arabia

Personalised recommendations