Delineation of blood vessels in pediatric retinal images using decision trees-based ensemble classification

  • Muhammad Moazam Fraz
  • Alicja R. Rudnicka
  • Christopher G. Owen
  • Sarah A. Barman
Original Article



Automatic segmentation of the retinal vasculature is a first step in computer-assisted diagnosis and treatment planning. The extraction of retinal vessels in pediatric retinal images is challenging because of comparatively wide arterioles with a light streak running longitudinally along the vessel’s center, the central vessel reflex. A new method for automatic segmentation was developed and tested.


   A supervised method for retinal vessel segmentation in the images of multi-ethnic school children was developed based on ensemble classifier of bootstrapped decision trees. A collection of dual Gaussian, second derivative of Gaussian and Gabor filters, along with the generalized multiscale line strength measure and morphological transformation is used to generate the feature vector. The feature vector encodes information to handle the normal vessels as well as the vessels with the central reflex. The methodology is evaluated on CHASE_DB1, a relatively new public retinal image database of multi-ethnic school children, which is a subset of retinal images from the Child Heart and Health Study in England (CHASE) dataset.


   The segmented retinal images from the CHASE_DB1 database produced best case accuracy, sensitivity and specificity of 0.96, 0.74 and 0.98, respectively, and worst case measures of 0.94, 0.67 and 0.98, respectively.


   A new retinal blood vessel segmentation algorithm was developed and tested with a shared database. The observed accuracy, speed, robustness and simplicity suggest that the algorithm may be a suitable tool for automated retinal image analysis in large population-based studies.


Medical imaging Retinal image analysis Ensemble classification Image segmentation  Boot strapped decision tree 


Conflict of interest

M. Moazam Fraz, Alicja R. Rudnicka, Christopher G. Owen and Sarah A. Barman declare that they have no conflict of interest.


  1. 1.
    Bernardes R, Serranho P, Lobo C (2011) Digital ocular fundus imaging: a review. Ophthalmologica 226(4):161–181PubMedCrossRefGoogle Scholar
  2. 2.
    Abràmoff MD, Garvin MK, Sonka M (2010) Retinal imaging and image analysis. IEEE Rev Biomed Eng 3:169–208. doi: 10.1109/rbme.2010.2084567 PubMedCrossRefGoogle Scholar
  3. 3.
    Owen CG, Rudnicka AR, Nightingale CM, Mullen R, Barman SA, Sattar N, Cook DG, Whincup PH (2011) Retinal arteriolar tortuosity and cardiovascular risk factors in a multi-ethnic population study of 10-year-old children; the child heart and health study in England (CHASE). Arter Thromb Vasc Biol 31(8):1933–1938. doi: 10.1161/ATVBAHA.111.225219 CrossRefGoogle Scholar
  4. 4.
    Owen CG, Rudnicka AR, Mullen R, Barman SA, Monekosso D, Whincup PH, Ng J, Paterson C (2009) Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (CAIAR) program. Investig Ophthalmol Vis Sci 50(5):2004–2010CrossRefGoogle Scholar
  5. 5.
    Wilson CM, Cocker KD, Moseley MJ, Paterson C, Clay ST, Schulenburg WE, Mills MD, Ells AL, Parker KH, Quinn GE, Fielder AR, Ng J (2008) Computerized analysis of retinal vessel width and tortuosity in premature infants. Investig Ophthalmol Vis Sci 49(8):3577–3585. doi: 10.1167/iovs.07-1353 CrossRefGoogle Scholar
  6. 6.
    Fraz MM, Remagnino 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(1):407–433PubMedCrossRefGoogle Scholar
  7. 7.
    DRIVE: Digital Retinal Images for Vessel Extraction (2004)
  8. 8.
    STARE: Structured Analysis of the Retina (2000)
  9. 9.
    Fraz MM (2013) CHASE\_DB1. Kingston University. Accessed May 2013
  10. 10.
    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):263–269PubMedCrossRefGoogle Scholar
  11. 11.
    Hoover AD, 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):203–210PubMedCrossRefGoogle Scholar
  12. 12.
    Xiaoyi J, Mojon D (2003) Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images. IEEE Trans Pattern Anal Mach Intell 25(1):131–137CrossRefGoogle Scholar
  13. 13.
    Al-Rawi M, Karajeh H (2007) Genetic algorithm matched filter optimization for automated detection of blood vessels from digital retinal images. Comput Methods Programs Biomed 87(3):248–253PubMedCrossRefGoogle Scholar
  14. 14.
    Zana F, Klein JC (2001) Segmentation of vessel-like patterns using mathematical morphology and curvature evaluation. IEEE Trans Image Process 10(7):1010–1019PubMedCrossRefGoogle Scholar
  15. 15.
    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):1200–1213PubMedCrossRefGoogle Scholar
  16. 16.
    Fraz MM, Barman SA, Remagnino P, Hoppe A, Basit A, Uyyanonvara B, Rudnicka AR, Owen CG (2012) An approach to localize the retinal blood vessels using bit planes and centerline detection. Comput Methods Programs Biomed 108(2):600–616PubMedCrossRefGoogle Scholar
  17. 17.
    Fraz MM, Basit A, Barman SA (2013) Application of morphological bit planes in retinal blood vessel extraction. J Digit Imaging 26(2):274–286. doi: 10.1007/s10278-012-9513-3 PubMedCrossRefPubMedCentralGoogle Scholar
  18. 18.
    Yin Y, Adel M, Bourennane S (2012) Retinal vessel segmentation using a probabilistic tracking method. Pattern Recognit 45(4):1235–1244. doi: 10.1016/j.patcog.2011.09.019 CrossRefGoogle Scholar
  19. 19.
    Vlachos M, Dermatas E (2009) Multi-scale retinal vessel segmentation using line tracking. Comput Med Imaging Graph 34(3):213–227PubMedCrossRefGoogle Scholar
  20. 20.
    Frangi AF, Niessen WJ, Vincken KL, Viergever MA, William W, Alan C, Scott D (1998) Multiscale vessel enhancement filtering. In: Medical image computing and computer-assisted interventation MICCAI\(^{{\rm TM}}\)98, vol. 1496. Lecture Notes in Computer Science. Springer, Berlin, p 130Google Scholar
  21. 21.
    Sofka M, Stewart CV (2006) Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures. IEEE Trans Med Imaging 25(12):1531–1546PubMedCrossRefGoogle Scholar
  22. 22.
    Vermeer KA, Vos FM, Lemij HG, Vossepoel AM (2004) A model based method for retinal blood vessel detection. Comput Biol Med 34(3):209–219PubMedCrossRefGoogle Scholar
  23. 23.
    Mahadevan V, Narasimha-Iyer H, Roysam B, Tanenbaum HL (2004) Robust model-based vasculature detection in noisy biomedical images. IEEE Trans Inf Technol Biomed 8(3):360–376PubMedCrossRefGoogle Scholar
  24. 24.
    Li W, Bhalerao A, Wilson R (2007) Analysis of retinal vasculature using a multiresolution hermite model. IEEE Trans Med Imaging 26(2):137–152CrossRefGoogle Scholar
  25. 25.
    Lam BSY, Hong Y (2008) A novel vessel segmentation algorithm for pathological retina images based on the divergence of vector fields. IEEE Trans Med Imaging 27(2):237–246PubMedCrossRefGoogle Scholar
  26. 26.
    Lam BSY, Yongsheng G, Liew AWC (2010) General retinal vessel segmentation using regularization-based multiconcavity modeling. IEEE Trans Med Imaging 29(7):1369–1381PubMedCrossRefGoogle Scholar
  27. 27.
    Paulus J, Meier J, Bock R, Hornegger J, Michelson G (2010) Automated quality assessment of retinal fundus photos. Int J CARS 5(6):557–564. doi: 10.1007/s11548-010-0479-7 CrossRefGoogle Scholar
  28. 28.
    Xiaohong G, Bharath A, Stanton A, Hughes A, Chapman N, Thom S (2001) A method of vessel tracking for vessel diameter measurement on retinal images. In: Image processing, 2001. Proceedings. 2001 International conference on, 2001, vol. 882, pp 881–884Google Scholar
  29. 29.
    Fraz MM, Remagnino P, Hoppe A, Rudnicka A, Owen C, Whincup P, Barman SA (2012) A model based approach for vessel caliber measurement in retinal images. In: Signal image technology and internet based systems (SITIS), 2012 eighth international conference on, 25–29 Nov. 2012. pp 129–136. doi: 10.1109/sitis.2012.29
  30. 30.
    Al-Diri B, Hunter A, Steel D (2009) An active contour model for segmenting and measuring retinal vessels. IEEE Trans Med Imaging 28(9):1488–1497PubMedCrossRefGoogle Scholar
  31. 31.
    Sum KW, Cheung PYS (2008) Vessel extraction under non-uniform illumination: a level set approach. IEEE Trans Biomed Eng 55(1):358–360PubMedCrossRefGoogle Scholar
  32. 32.
    Akita K, Kuga H (1982) A computer method of understanding ocular fundus images. Pattern Recognit 15(6):431–443CrossRefGoogle Scholar
  33. 33.
    Marin D, Aquino A, Gegundez-Arias ME, Bravo JM (2011) A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE Trans Med Imaging 30(1):146–158PubMedCrossRefGoogle Scholar
  34. 34.
    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. British J Ophthalmol 83(8):902–910CrossRefGoogle Scholar
  35. 35.
    Niemeijer M, Staal J, van Ginneken B, Loog, M, Abramoff D (2004) Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Fitzpatrick JM, Sonka M (eds) SPIE Medical Imaging, 2004. SPIE, pp 648–656Google Scholar
  36. 36.
    Staal J, Abràmoff 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):501–509PubMedCrossRefGoogle Scholar
  37. 37.
    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):1214–1222PubMedCrossRefGoogle Scholar
  38. 38.
    Ricci E, Perfetti R (2007) Retinal blood vessel segmentation using line operators and support vector classification. IEEE Trans Med Imaging 26(10):1357–1365PubMedCrossRefGoogle Scholar
  39. 39.
    Lupascu CA, Tegolo D, Trucco E (2010) FABC: Retinal vessel segmentation using AdaBoost. IEEE Trans Inf Technol Biomed 14(5):1267–1274PubMedCrossRefGoogle Scholar
  40. 40.
    You X, Peng Q, Yuan Y, Lei J (2011) Segmentation of retinal blood vessels using the radial projection and semi-supervised approach. Pattern Recognit 44(10–11):2314–2324. doi: 10.1016/j.patcog.2011.01.007 CrossRefGoogle Scholar
  41. 41.
    Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, Barman SA (2012) An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans Biomed Eng 59(9):2538–2548. doi: 10.1109/tbme.2012.2205687 PubMedCrossRefGoogle Scholar
  42. 42.
    Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka A, Owen C, Barman S (2012) Ensemble classification system applied for retinal vessel segmentation on child images containing various vessel profiles. In: Campilho A, Kamel M (eds) Image analysis and recognition, vol. 7325. Lecture Notes in Computer Science. Springer, Berlin, pp 380–389. doi: 10.1007/978-3-642-31298-4_45
  43. 43.
    Gang L, Chutatape O, Krishnan SM (2002) Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter. IEEE Trans Biomed Eng 49(2):168–172 Google Scholar
  44. 44.
    Zwiggelaar R, Astley SM, Boggis CRM, Taylor CJ (2004) Linear structures in mammographic images: detection and classification. IEEE Trans Med Imaging 23(9):1077–1086PubMedCrossRefGoogle Scholar
  45. 45.
    Nguyen UTV, Bhuiyan A, Park LAF, Ramamohanarao K (2012) An effective retinal blood vessel segmentation method using multi-scale line detection. Pattern Recognit (0). doi: 10.1016/j.patcog.2012.08.009
  46. 46.
    Movellan JR (2008) Tutorial on gabor filters. Tutorial paper
  47. 47.
    Niemeijer M, van Ginneken B, Staal J, Suttorp-Schulten MSA, Abramoff MD (2005) Automatic detection of red lesions in digital color fundus photographs. IEEE Trans Med Imaging 24(5):584–592. doi: 10.1109/tmi.2005.843738 PubMedCrossRefGoogle Scholar
  48. 48.
    Walter T, Massin P, Erginay A, Ordonez R, Jeulin C, Klein J-C (2007) Automatic detection of microaneurysms in color fundus images. Med Image Anal 11(6):555–566PubMedCrossRefGoogle Scholar
  49. 49.
    Foracchia M, Grisan E, Ruggeri A (2005) Luminosity and contrast normalization in retinal images. Med Image Anal 9(3):179–190. doi: 10.1016/ PubMedCrossRefGoogle Scholar
  50. 50.
    Onkaew D, Turior R, Uyyanonvara B, Kondo T (2011) Automatic extraction of retinal vessels based on gradient orientation analysis. In: Computer science and software engineering (JCSSE), 2011 eighth international joint conference on, 11–13 May 2011. pp 102–107. doi: 10.1109/JCSSE.2011.5930102
  51. 51.
    Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21–45 doi: 10.1109/MCAS.2006.1688199 Google Scholar
  52. 52.
    Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140. doi: Google Scholar
  53. 53.
    Owen CG, Nightingale CM, Rudnicka AR, Cook DG, Ekelund U, Whincup PH (2009) Ethnic and gender differences in physical activity levels among 9–10-year-old children of white European, South Asian and African-Caribbean origin: the Child Heart Health Study in England (CHASE Study). Int J Epidemiol 38(4):1082–1093PubMedCrossRefPubMedCentralGoogle Scholar
  54. 54.
    Owen CG, Rudnicka AR, Nightingale CM, Mullen R, Barman SA, Sattar N, Cook DG, Whincup PH (2011) Retinal arteriolar tortuosity and cardiovascular risk factors in a multi-ethnic population study of 10-year-old children; the Child Heart and Health Study in England (CHASE). Arterioscler Thromb Vasc Biol 31(8):1933–1938. doi: 10.1161/ATVBAHA.111.225219

Copyright information

© CARS 2013

Authors and Affiliations

  • Muhammad Moazam Fraz
    • 1
  • Alicja R. Rudnicka
    • 2
  • Christopher G. Owen
    • 2
  • Sarah A. Barman
    • 1
  1. 1.School of Computing and Information Systems, Faculty of Science Engineering and ComputingKingston University LondonLondonUK
  2. 2.Division of Population Health Sciences and EducationSt. George’s, University of LondonLondonUK

Personalised recommendations