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.
Similar content being viewed by others
Change history
30 December 2021
A Correction to this paper has been published: https://doi.org/10.1007/s00521-021-06819-5
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
- x :
-
Image pixel
- f :
-
Response function of a camera
- L :
-
Irradiance image
- I :
-
Image intensity
- I N :
-
Noisy image
- N s :
-
Multiplicative noise
- N c :
-
Additive noise
- σ 2 c :
-
Variance of additive noise
- σ 2 s :
-
Variance of multiplicative noise
- N q :
-
Quantization noise
- ∑2 :
-
Noise model
- IE(.):
-
Expectation of a random variable
- \(\overline{{\sum^{2} }}\) :
-
Mean of principal components
- ω η :
-
Eigenvectors of principal components
- m :
-
Number of retained eigenvectors
- α η :
-
Unknown parameters of noise model
- η :
-
Index of unknown parameters of noise model
- i, j :
-
Spatial coordinates of current pixel x
- w i,j :
-
Window centered at current pixel
- c :
-
Instantaneous coefficient of the variation of the image
- c 2 n :
-
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
- σ min :
-
Minimal scale
- σ max :
-
Maximal scale
- Θ :
-
Image orientation
- Γ σ :
-
Response function at scale σ
- Γ multi :
-
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
- λ 1 :
-
First eigenvalue of Hessian matrix
- λ 2 :
-
Second eigenvalue of Hessian matrix
- r :
-
Radius vessel
- [t min, t max]:
-
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
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):60–73
Pal NR, Pal SK (1993) A review on image segmentation techniques. Pattern Recogn 26(9):1277–1294
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 York
Kauppi T et al (2010) Eye fundus image analysis for automatic detection of diabetic retinopathy. Lappeenranta University of Technology, Lappeenranta
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
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):15–30
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
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 225–298
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):1019–1032
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)
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
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):101–116
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)
Sofka M, Stewart CV (2006) Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures. IEEE Trans Med Imaging 25(12):1531–1546
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):438–445
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):495–506
Hou Y (2014) Automatic segmentation of retinal blood vessels based on improved multiscale line detection. J Comput Sci Eng 8(2):119–128
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):703–715
Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639
Yu Y, Acton ST (2002) Speckle reducing anisotropic di_usion. IEEE Trans Image Process 11(11):1260–1270. doi:10.1109/TIP.2002.804276
Krissian K (2002) Flux-based anisotropic diffusion applied to enhancement of 3-D angiogram. IEEE Trans Med Imaging 21(11):1440–1442
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):756–770
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
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, China
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, 2013
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, China
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):263–269
Chanwimaluang T, Fan G (2003) An efficient algorithm for extraction of anatomical structures in retinal images. In: Proceedings of ICIP, pp 1193–1196
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):600616
Zhou L, Rzeszotarski MS, Singerman LJ, Chokreff JM (1994) The detection and quantification of retinopathy using digital angiograms. IEEE Trans Med Imaging 13(4):619–626
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 881–884
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 3144–3149
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):125–138
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
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 378–381
Healey GE, Kondepudy R (1994) Radiometric CCD camera calibration and noise estimation. IEEE Trans Pattern Anal Mach Intell 16(3):267–276
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):045207
Liu X, Tanaka M, Okutomi M (2013) Estimation of signal dependent noise parameters from a single image. In: ICIP, pp 79–82
Gravel P, Beaudoin G, De Guise JA (2004) A method for modeling noise in medical images. IEEE Trans Med Imaging 23(10):1221–1232
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):299–314
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):1273–1300
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 1–5
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
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 37–42
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):203–210
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):49–61
Hai TTT, Augustin L (2003) Extraction de Caract´eristiques locales: Crêtes et Pics. Book: RIVF
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 2008
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’97
Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering, medical image computing and computer-assisted interventation-MICCAI’98. Springer, New York
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 150–153
Koenderink JJ (1984) The structure of images. Biol Cybern 50(5):363–370
Lindeberg T (1994) Scale-space theory: a basic tool for analyzing structures at different scales. J Appl Stat 21(1–2):225–270
Sporring J, Florack L, Nielsen M, Johansen P (1997) Gaussian scale-space theory. Kluwer Academic Publishers, Dordrecht
Florack L (1997) Image structure. Kluwer Academic Publishers, Dordrecht
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 York
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 1–6
Prajapati A, Naik S, Mehta S (2012) Evaluation of different image interpolation algorithms. Int J Comput Appl 58(12):6–12
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 608–611
Tam WS, Kok CW, Siu WC (2009) A modified edge directed interpolation for images. In: 17th European signal processing conference (ESPC)
Hoover A (1995) STARE database. http://www.ces.clemson.edu/ahoover/stare
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 2004:648–656
Niemeijer M, van Ginneken B (2002) Drive database URL www.isi.uu.nl/Research/Databases/DRIVE/results.php
Martens JB, Meesters L (1998) Image dissimilarity. Signal Process 70(3):155–176. doi:10.1016/S0165-1684(98)00123-6
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
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):501–509
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):1214–1222
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):1214–1222
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):501–509
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 83:902–910
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):438–445
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):263–269
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):47–61
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):1200–1213
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ben Abdallah, M., Azar, A., Guedri, H. et al. Noise-estimation-based anisotropic diffusion approach for retinal blood vessel segmentation. Neural Comput & Applic 29, 159–180 (2018). https://doi.org/10.1007/s00521-016-2811-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2811-9