Advertisement

A generalized multi-scale line-detection method to boost retinal vessel segmentation sensitivity

  • Mohammad A. U. Khan
  • Tariq M. Khan
  • D. G. Bailey
  • Toufique A. Soomro
Theoretical Advances
  • 126 Downloads

Abstract

Many chronic eye diseases can be conveniently investigated by observing structural changes in retinal blood vessel diameters. However, detecting changes in an accurate manner in face of interfering pathologies is a challenging task. The task is generally performed through an automatic computerized process. The literature shows that powerful methods have already been proposed to identify vessels in retinal images. Though a significant progress has been achieved toward methods to separate blood vessels from the uneven background, the methods still lack the necessary sensitivity to segment fine vessels. Recently, a multi-scale line-detector method proved its worth in segmenting thin vessels. This paper presents modifications to boost the sensitivity of this multi-scale line detector. First, a varying window size with line-detector mask is suggested to detect small vessels. Second, external orientations are fed to steer the multi-scale line detectors into alignment with flow directions. Third, optimal weights are suggested for weighted linear combinations of individual line-detector responses. Fourth, instead of using one global threshold, a hysteresis threshold is proposed to find a connected vessel tree. The overall impact of these modifications is a large improvement in noise removal capability of the conventional multi-scale line-detector method while finding more of the thin vessels. The contrast-sensitive steps are validated using a publicly available database and show considerable promise for the suggested strategy.

Keywords

Retinal segmentation Morphological opening Morphological reconstruction Second-order derivative detector Multi-scale line detector Orientation field 

References

  1. 1.
    Hardarson S, Stefansson E (2010) Oxygen saturation in central retinal vein occlusion. Am J Ophthalmol 150:871–875CrossRefGoogle Scholar
  2. 2.
    Hardarson S, Stefansson E (2012) Retinal oxygen saturation is altered in diabetic retinopathy. Br J Ophthalmol 96:560–563CrossRefGoogle Scholar
  3. 3.
    Olafsdottir O, Hardarson S, Gottfredsdottir M, Harris A, Stefnsson E (2011) Retinal oximetry in primary open-angle glaucoma. Investig Ophthalmol Vis Sci 52:6409–6413CrossRefGoogle Scholar
  4. 4.
    Traustason S, Jensen A, Arvidsson H, Munch I, Sndergaard L, Larsen M (2011) Retinal oxygen saturation in patients with systemic hypoxemia. Investig Ophthalmol Vis Sci 52:5064–5067CrossRefGoogle Scholar
  5. 5.
    Diabetic retinopathy detection. https://www.kaggle.com/c/diabetic-retinopathy-detection (Feb 2015)
  6. 6.
    Patton N, Aslam T, Macgillivray T, Pattie A, Deary IJ (2005) Retinal vascular image analysis as a potential screening tool for cerebrovascular disease: a rationale based on homology between cerebral and retinal microvasculatures. J Anat 206:319–348CrossRefGoogle Scholar
  7. 7.
    Wang JJ, Liew G, Klein R, Rochtchina E, Knudtson MD (2007) Retinal vessel diameter and cardiovascular mortality: pooled data analysis from two older populations. Eur Heart J 28:1984–1992CrossRefGoogle Scholar
  8. 8.
    Hubbard LD, Brothers RJ, King WN, Clegg LX, Klein R (1999) Methods for evaluation of retinal microvascular abnormalities associated with hypertension/sclerosis in the atherosclerosis risk in communities study. Ophthalmology 106:2269–2280CrossRefGoogle Scholar
  9. 9.
    Soomro TA, Gao J, Khan TM, Hani AFM, Khan MAU, Paul M (2017) Computerised approaches for the detection of diabetic retinopathy using retinal fundus images: a survey. Pattern Anal Appl 20(4):927–961MathSciNetCrossRefGoogle Scholar
  10. 10.
    Soomro TA, Khan MAU, Gao J, Khan TM, Paul M (2017) Contrast normalization steps for increased sensitivity of a retinal image segmentation method. SIViP 11(8):1509–1517CrossRefGoogle Scholar
  11. 11.
    Soomro TA, Khan TM, Khan MAU, Gao J, Paul M, Zheng L (2018) Impact of ICA-based image enhancement technique on retinal blood vessels segmentation. IEEE Access.  https://doi.org/10.1109/ACCESS.2018.2794463 Google Scholar
  12. 12.
    Khan MAU, Khan TM, Soomro TA, Mir N, Gao J (2017) Boosting sensitivity of a retinal vessel segmentation algorithm. Pattern Anal Appl.  https://doi.org/10.1007/s10044-017-0661-4
  13. 13.
    Saine PJ, Tyler ME (2002) Ophthalmic photography: retinal photography, angiography, and electronic imaging, 2nd edn. Butterworth-Heinemann, BostonGoogle Scholar
  14. 14.
    Cassin B, Solomon SAB (1996) Dictionary of eye terminology, 2nd edn, Triad Pub CoGoogle Scholar
  15. 15.
    Pakter HM, Ferlin E, Fuchs SC, Maestri MK, Moraes RS (2005) Measuring arteriolar-to-venous ratio in retinal photography of patients with hypertension: development and application of a new semi-automated method. Am J Hypertens 18:417–421CrossRefGoogle Scholar
  16. 16.
    Wong TY, Knudtson MD, Klein R, Klein BEK, Meuer SM (2004) Computer-assisted measurement of retinal vessel diameters in the beaver dam eye study: methodology, correlation between eyes, and effect of refractive errors. Ophthalmology 111:1183–1190CrossRefGoogle Scholar
  17. 17.
    Soares JVB, Leandro JJG, Cesar RM, 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
  18. 18.
    Lindberg T (1990) Scale-space for discrete signals. IEEE Trans Pattern Anal Mach Intell 12:234–254CrossRefGoogle Scholar
  19. 19.
    Maji D, Santara A, Mitra P, Sheet D (2016) Ensemble of deep convolutional neural networks for learning to detect retinal vessels in fundus images. In: EMBC 2016—engineering in medicine and biology society computing research repository (CoRR)Google Scholar
  20. 20.
    Staal J, 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
  21. 21.
    Zana F, Klein J (2001) Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE Trans Image Process 10(7):1010–1019CrossRefzbMATHGoogle Scholar
  22. 22.
    Azzopardia G, Strisciuglio N, Vento M, Petkov N (2015) Trainable COSFIRE filters for vessel delineation with application to retinal images. Med Image Anal 19(1):46–57CrossRefGoogle Scholar
  23. 23.
    Nguyen UTV, Bhuiyan A, Park LAF, Ramamohanarao K (2013) An effective retinal blood vessel segmentation method using multi-scale line detection. Pattern Recognit 46:703–715CrossRefGoogle Scholar
  24. 24.
    Fraz MM, Remagnin P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, Barman SA (2012) Blood vessel segmentation methodologies in retinal images—a survey. Comput Methods Programs Biomed 108:407–433CrossRefGoogle Scholar
  25. 25.
    Chaudhuri S, Chatterjee S, Katz N, Nelson M, Goldbaumi M (1989) Detection of blood vessels in retinal images using two-dimensional matched filters. IEEE Trans Med Imaging 8(3):263–269CrossRefGoogle Scholar
  26. 26.
    Heneghan C, Flynn J, O’Keefe M, Cahill M (2002) Characterization of changes in blood vessel width and tortuosity in retinopathy of prematurity using image analysis. Med Image Anal 6(4):409–429CrossRefGoogle Scholar
  27. 27.
    Zhang B, Zhang L, Zhang L (2011) Retinal vessel extraction by matched filtering with first order Gaussian derivative. Comput Biol Med 40(4):438–445CrossRefGoogle Scholar
  28. 28.
    Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: Wells WM, Colchester A, Delp S (eds) Medical image computing and computer-assisted intervention-MICCAI’98. MICCAI 1998, Lecture notes in computer science, vol 1496, Springer, Berlin, pp 130–137Google Scholar
  29. 29.
    Leontidis G (2014) Retinal vessel segmentation using two-dimensional second-order Gaussian filter and clustering algorithm. Afr Dev Resour Res Inst (ADRRI) J 6(6):14Google Scholar
  30. 30.
    Ricci E, Perfetti R (2007) Retinal blood vessel segmentation using line operators and support vector classification. IEEE Trans Image Process 26(10):1357–1365CrossRefGoogle Scholar
  31. 31.
    Hou Y (2014) Automatic segmentation of retinal blood vessels based on improved multiscale line detection. J Comput Sci Eng 8(2):119–128CrossRefGoogle Scholar
  32. 32.
    Sigursson EM, Valero S, Benediktsson JA, Chanussot J, Talbot H, Stefnsson E (2014) Automatic retinal vessel extraction based on directional mathematical morphology and fuzzy classification. Pattern Recognit Lett 47:164–171CrossRefGoogle Scholar
  33. 33.
    Talbot H, Appleton B (2007) Efficient complete and incomplete path openings and closings. Image Vis Comput 25:416–425CrossRefGoogle Scholar
  34. 34.
    Valero S, Chanussot J, Benediktsson J, Talbot H, Waske B (2010) Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images. Pattern Recognit 31:1120–1127CrossRefGoogle Scholar
  35. 35.
    Valero S, Chanussot J, Benediktsson JA, Talbot H (2009) D’etection automatique du r’eseau vasculaire r’etinien bas’ee sur la morphologie directionnelle et la fusion de d’ecision. XIIe Colloque GRETSIGoogle Scholar
  36. 36.
    Dragut L, Eisank C, Strasser T (2011) Local variance for multi-scale analysis in geomorphometry. Geomorphology 130:162–172CrossRefGoogle Scholar
  37. 37.
    Gottschlich C, Schonlieb C-B (2012) Oriented diffusion filtering for enhancing low-quality fingerprint images. IET Biom 1(2):105–113CrossRefGoogle Scholar
  38. 38.
    Feng X (2003) Analysis and approaches to image local orientation estimations. M.S. thesis, University of California Santa CruzGoogle Scholar
  39. 39.
    Canny JA (1986) Computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698CrossRefGoogle Scholar
  40. 40.
    Kanan C, Cottrell GW (2012) Color-to-grayscale: does the method matter in image recognition? PLOS One 7:1–7CrossRefGoogle Scholar
  41. 41.
    Niemeijer M, Staal J, van Ginneken B, Loog M, Abramoff MD (2004) Comparative study on retinal vessel segmentation methods on a new publicly available database. In: Medical imaging, vol 5370. SPIE , pp 608–656Google Scholar
  42. 42.
    Mendonca AM, Campilho A (2006) Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans Med Imaging 25:1200–1213CrossRefGoogle Scholar
  43. 43.
    Jiang X, Mojon D (2003) Adaptive local thresholding by verificationbased multithreshold probing with application to vessel detection in retinal images. IEEE Trans Pattern Anal Mach Intell 254(1):131–137CrossRefGoogle Scholar
  44. 44.
    Reyes-Aldasoro CC (2009) Retrospective shading correction algorithm based on signal envelope estimation. Electron Lett 45(9):454–456CrossRefGoogle Scholar
  45. 45.
    Sinthanayothin C, Boyce JF, Cook HL, Williamson TH (1999) Automated localisation of the optic disc, fovea and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83:902–910CrossRefGoogle Scholar
  46. 46.
    Pratt WK (2001) Digital image processing. Wiley, New YorkCrossRefzbMATHGoogle Scholar
  47. 47.
    Kass M, Witkin A (1987) Analyzing oriented patterns. Comput Vis Graph Image Process 37(3):362–385CrossRefGoogle Scholar
  48. 48.
    Khan MAU, Khan MK, Khan MA, Rehman T (2004) A decimation free directional filter bank for medical image enhancement. Inf Technol J 3(2):146–149CrossRefGoogle Scholar
  49. 49.
    Khan MAU, Khan MK, Khan MA (2005) Comparative analysis of decimation-free directional filter bank with directional filter bank: in context of image enhancement. In: Proceedings of the 9th international multitopic conference, IEEE INMIC. Karachi, pp 1–8Google Scholar
  50. 50.
    Truc PTH, Khan MAU, Lee YK, Kim TS (2009) Vessel enhancement filter using directional filter bank. Comput Vis Image Underst 113:101–112CrossRefGoogle Scholar
  51. 51.
    Khan TM, Khan MAU, Kong Y (2014) Fingerprint image enhancement using multi-scale DDFB based diffusion filters and modified Hong filters. Opt Int J Light Electron Opt 25:4206–4214CrossRefGoogle Scholar
  52. 52.
    Bamberger RH (1992) The directional filter bank: a multirate filter bank for the directional decomposition of images. Ph.D. thesis, Georgia Institute of Technology, Atlanta, GeorgiaGoogle Scholar
  53. 53.
    Khan MAU, Alhalabi W (2013) Robust multi-scale orientation estimation: spatial domain vs Fourier domain. In: International conference on communications, signal processing, and their applicationsGoogle Scholar
  54. 54.
    Khan MAU, Ullah K, Khan A, Islam IU (2014) Robust multi-scale orientation estimation: directional filter bank based approach. Elsevier J Appl Math Comput 242:814–824CrossRefzbMATHGoogle Scholar
  55. 55.
    Granlund GH (1978) In search of a general picture processing operator. Comput Graph Image Process 8:155–173CrossRefGoogle Scholar
  56. 56.
    Kirk K, Andersen HJ (2006) Noise characterization of weighting schemes for combination of multiple exposures. In: British machine vision conference, 2006, pp 1129–1136Google Scholar
  57. 57.
    Hartung J, Knapp G, Sinha BK (2008) Statistical meta-analysis with applications. Wiley, New YorkCrossRefzbMATHGoogle Scholar
  58. 58.
    Wang Y, Fang B, Pi J, Wu L, Wang P, Wang H (2013) Automatic multi-scale segmentation of intrahepatic vessel in CT images for liver surgery planning. Int J Pattern Recognit Artif Intell 27(1):1357001MathSciNetCrossRefGoogle Scholar
  59. 59.
    Soler L, Delingette H, Malandain G, Montagnat J, Ayache N, Koehl C, Dourthe O, Malassagne B, Smith M, Mutter D, Marescaux J (2001) Fully automatic anatomical, pathological, and functional segmentation from CT scans for hepatic surgery. Comput Aided Surg 6(3):131–142CrossRefGoogle Scholar
  60. 60.
    Dunn ME, Joseph SH (1988) Processing poor quality line drawings by local estimation of noise. In: 4th international conference on pattern recognition, pp 153–162Google Scholar
  61. 61.
    Pridmore TP (2002) Thresholding images of line drawings with hysteresis. In: Fourth international workshop on graphics recognition algorithms and applications, pp 310–319Google Scholar
  62. 62.
    Luu HM, Klink C, Moelker A, Niessen W, van Walsum T (2015) Quantitative evaluation of noise reduction and vesselness filters for liver vessel segmentation on abdominal CTA images. Phys Med Biol 60(10):3905–3926CrossRefGoogle Scholar
  63. 63.
    Digital retinal image for vessel extraction (DRIVE) database. http://www.isi.uu.nl/Research/Databases/DRIVE
  64. 64.
    Structured analysis of the retina (STARE) database. http://cecas.clemson.edu/~ahoover/stare/
  65. 65.
    Martinez-Perez ME, Hughes AD, Thom SA (2007) Segmentation of blood vessels from red-free and fluorescein retinal images. Med Image Anal 11(1):47–61CrossRefGoogle Scholar
  66. 66.
    Vlachos M, Dermatas E (2009) Multi-scale retinal vessel segmentation using line tracking. Comput Med Imaging Graph 34(3):213–227CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  • Mohammad A. U. Khan
    • 1
  • Tariq M. Khan
    • 2
  • D. G. Bailey
    • 3
  • Toufique A. Soomro
    • 4
  1. 1.Department of Electrical Engineering, College of Engineering and ComputingAl-Ghurair UniversityAcademic City, DubaiUAE
  2. 2.Electrical Engineering DepartmentCOMSATS Institute of Information TechnologyIslamabadPakistan
  3. 3.Massey UniversityPalmerston NorthNew Zealand
  4. 4.School of Computing and MathematicsCharles Sturt UniversityBathurstAustralia

Personalised recommendations