• Temitope Mapayi University of KwaZulu-Natal
  • Jules-Raymond Tapamo University of KwaZulu-Natal
  • Serestina Viriri University of KwaZulu-Natal
  • Adedayo Adio University of Port Harcourt



clustering, difference image, k-means, retinal vessel, segmentation, tortuosity


As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents study on the combination of difference image and K-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed K-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth.


Adio AO, Ugwu RO, Nwokocha CG, Eneh AU

(2014). Retinopathy of prematurity in port

harcourt, nigeria. ISRN ophthalmology .

Akram MU, Khan SA (2013). Multilayered

thresholding-based blood vessel segmentation for

screening of diabetic retinopathy. Engineering

with computers 29:165–73.

Atlas ID (2013). 6th edn. International Diabetes

Federation Brussels Belgium :160.

Azegrouz H, Trucco E, Dhillon B, MacGillivray T,

MacCormick I (2006). Thickness dependent

tortuosity estimation for retinal blood vessels. In:

Engineering in Medicine and Biology Society,

EMBS’06. 28th Annual International

Conference of the IEEE. IEEE.

Bedell AJ (1945). Retinal vessel proliferation

in diabetes. Transactions of the American

Ophthalmological Society 43:271.

Bribiesca E (2013). A measure of tortuosity based on

chain coding. Pattern Recognition 46:716–24.

Bullitt E, Gerig G, Pizer SM, Lin W, Aylward SR

(2003). Measuring tortuosity of the intracerebral

vasculature from mra images. Medical Imaging

IEEE Transactions on 22:1163–71.

Capowski JJ, Kylstra JA, Freedman SF (1995). A

numeric index based on spatial frequency for the

tortuosity of retinal vessels and its application to

plus disease in retinopathy of prematurity. Retina


Chakraborti T, Jha DK, Chowdhury AS, Jiang X

(2014). A self-adaptive matched filter for retinal

blood vessel detection. Machine Vision and

Applications 26:55–68.

Chakravarty A, Sivaswamy J (2013). A novel approach

for quantification of retinal vessel tortuosity using

quadratic polynomial decomposition. In: Medical

Informatics and Telemedicine (ICMIT), 2013

Indian Conference on. IEEE.

Chanwimaluang T, Fan G (2003). An efficient

blood vessel detection algorithm for retinal images

using local entropy thresholding. In: Circuits

and Systems, 2003. ISCAS’03. Proceedings of the

International Symposium on, vol. 5. IEEE.

Chaudhuri S, Chatterjee S, Katz N, Nelson M,

Goldbaum M (1989). Detection of blood vessels

in retinal images using two-dimensional matched

filters. IEEE Transactions on medical imaging


Chen Y, Li X, Yin H, Gilbert C, Liang J, Jiang Y,

Zhao M (2008). Risk factors for retinopathy of

prematurity in six neonatal intensive care units in

beijing, china. British Journal of Ophthalmology


Cinsdikici MG, Aydın D (2009). Detection of blood

vessels in ophthalmoscope images using mf/ant

(matched filter/ant colony) algorithm. Computer

methods and programs in biomedicine 96:85–95.

Condurache AP, Aach T (2006). Vessel segmentation

in 2d-projection images using a supervised linear

hysteresis classifier. In: Pattern Recognition, 2006.

ICPR 2006. 18th International Conference on,

vol. 1. IEEE.

Cornforth D, Jelinek HJ, Leandro J, Soares J,

Cesar Jr R, Cree MJ, Mitchell P, Bossomaier

T (2005). Development of retinal blood

vessel segmentation methodology using wavelet

transforms for assessment of diabetic retinopathy

Davitt BV, Wallace DK (2009). Plus disease. Survey

of ophthalmology 54:663–70.

Dougherty G, Johnson MJ, Wiers MD (2010).

Measurement of retinal vascular tortuosity and

its application to retinal pathologies. Medical

biological engineering computing 48:87–95.

Dougherty G, Varro J (2000). A quantitative index for

the measurement of the tortuosity of blood vessels.

Medical engineering physics 22:567–74.

DRIVE (2004). Research section, digital retinal image

for vessel extraction (drive) database. utrecht,

the netherlands, univ. med. center utrecht, image

sci. inst. [online]. available: http://www.isi.

Foody GM (2009). Classification accuracy

comparison: hypothesis tests and the use of

confidence intervals in evaluations of difference,

equivalence and non-inferiority. Remote Sensing

of Environment 113:1658–63.

Fraz MM, Barman S, Remagnino P, Hoppe A, Basit

A, Uyyanonvara B, Rudnicka AR, Owen CG

(2012a). An approach to localize the retinal blood

vessels using bit planes and centerline detection.

Computer methods and programs in biomedicine


Fraz MM, Remagnino P, Hoppe A, Uyyanonvara

B, Owen CG, Rudnicka AR, Barman S

(2011). Retinal vessel extraction using firstorder

derivative of gaussian and morphological

processing. In: Advances in Visual Computing.

Springer, 410–20.

Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B,

Rudnicka AR, Owen CG, Barman SA (2012b).

Blood vessel segmentation methodologies in

retinal images–a survey. Computer methods and

programs in biomedicine 108:407–33.

Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B,

Rudnicka AR, Owen CG, Barman SA (2012c). An

ensemble classification-based approach applied to

retinal blood vessel segmentation. Biomedical

Engineering IEEE Transactions on 59:2538–48.

Fraz MM, Rudnicka AR, Owen CG, Barman SA

(2013). Delineation of blood vessels in pediatric

retinal images using decision trees-based ensemble

classification. International journal of computer

assisted radiology and surgery :1–17.

Gergely K, Gerinec A (2009). Retinopathy

of prematurity–epidemics, incidence, prevalence,

blindness. Bratislavske lekarske listy 111:514–7.

Grisan E, Foracchia M, Ruggeri A (2003). A novel

method for the automatic evaluation of retinal

vessel tortuosity. In: Engineering in Medicine

and Biology Society, 2003. Proceedings of the

th Annual International Conference of the IEEE,

vol. 1. IEEE.

Grisan E, Foracchia M, Ruggeri A (2008). A novel

method for the automatic grading of retinal vessel

tortuosity. Medical Imaging IEEE Transactions on


Grisan E, Pesce A, Giani A, Foracchia M, Ruggeri

A (2004). A new tracking system for the

robust extraction of retinal vessel structure. In:

Engineering in Medicine and Biology Society,

IEMBS’04. 26th Annual International

Conference of the IEEE, vol. 1. IEEE.

Hakeem AH, Mohamed GB, Othman MF (2012).

Retinopathy of prematurity: a study of prevalence

and risk factors. Middle East African journal of

ophthalmology 19:289.

Hart WE, Goldbaum M, Cote B, Kube P, Nelson

MR (1997). Automated measurement of retinal

vascular tortuosity. In: Proceedings of the AMIA

Annual Fall Symposium. American Medical

Informatics Association.

Hart WE, Goldbaum M, Cˆot´e B, Kube P, Nelson

MR (1999). Measurement and classification of

retinal vascular tortuosity. International journal of

medical informatics 53:239–52.

Heneghan C, Flynn J, OKeefe M, Cahill M (2002).

Characterization of changes in blood vessel width

and tortuosity in retinopathy of prematurity using

image analysis. Medical image analysis 6:407–29.

Hoover A, Kouznetsova V, Goldbaum M (2000).

Locating blood vessels in retinal images by

piecewise threshold probing of a matched filter

response. Medical Imaging IEEE Transactions on


Jiang X, Mojon D (2003). Adaptive local thresholding

by verification-based multithreshold probing withapplication to vessel detection in retinal images.

Pattern Analysis and Machine Intelligence IEEE

Transactions on 25:131–7.

Jimenez S, Alemany P, Fond´on I, Foncubierta A,

Acha B, Serrano C (2010). Automatic detection

of vessels in color fundus images. Archivos de

la Sociedad Espanola de Oftalmologia English

Edition 85:103–9.

Joshi GD, Sivaswamy J (2008). Colour retinal image

enhancement based on domain knowledge. In:

Computer Vision, Graphics & Image Processing,

ICVGIP’08. Sixth Indian Conference on.


Kande GB, Subbaiah PV, Savithri TS (2010).

Unsupervised fuzzy based vessel segmentation in

pathological digital fundus images. Journal of

Medical Systems 34:849–58.

Klonoff DC, Schwartz DM (2000). An economic

analysis of interventions for diabetes. Diabetes

care 23:390–404.

Kristinsson JK, Gottfredsd´ottir MS, Stef´ansson E

(1997). Retinal vessel dilatation and elongation

precedes diabetic macular oedema. British journal

of ophthalmology 81:274–8.

Kylstra J, Wierzbicki T, Wolbarsht M, Landers III

M, Stefansson E (1986). The relationship

between retinal vessel tortuosity, diameter, and

transmural pressure. Graefes archive for clinical

and experimental ophthalmology 224:477–80.

Li B, Li HK (2013). Automated analysis of

diabetic retinopathy images: Principles, recent

developments, and emerging trends. Current

diabetes reports 13:453–9.

Li Q, You J, Zhang D (2012). Vessel segmentation and

width estimation in retinal images using multiscale

production of matched filter responses. Expert

Systems with Applications 39:7600–10.

Li Q, You J, Zhang D, Bhattacharya P (2006). A

multiscale approach to retinal vessel segmentation

using gabor filters and scale multiplication. In:

Systems, Man and Cybernetics, 2006. SMC’06.

IEEE International Conference on, vol. 4. IEEE.

Lim LS, Cheung CY, Lin X, Mitchell P,Wong TY, Saw

SM (2010). Influence of refractive error and axial

length on retinal vessel geometric characteristics.

Investigative ophthalmology visual science :iovs–10.

Lisowska A, Annunziata R, Loh GK, Karl D, Trucco E

(2014). An experimental assessment of five indices

of retinal vessel tortuosity with the ret-tort public

dataset. In: Engineering in Medicine and Biology

Society (EMBC), 2014 36th Annual International

Conference of the IEEE. IEEE.

Lotmar W, Freiburghaus A, Bracher D (1979).

Measurement of vessel tortuosity on fundus

photographs. Albrecht von Graefes Archiv

fur klinische und experimentelle Ophthalmologie


Lupas¸cu CA, Tegolo D (2011a). Automatic

unsupervised segmentation of retinal vessels using

self-organizing maps and k-means clustering.

In: Computational Intelligence Methods for

Bioinformatics and Biostatistics. Springer, 263–74.

Lupas¸cu CA, Tegolo D (2011b). Stable automatic

unsupervised segmentation of retinal vessels

using self-organizing maps and a modified fuzzy

c-means clustering. In: Fuzzy Logic and

Applications. Springer, 244–52.

Lupascu CA, Tegolo D, Trucco E (2010). Fabc: retinal

vessel segmentation using adaboost. Information

Technology in Biomedicine IEEE Transactions on


Mapayi T, Viriri S, Tapamo JR (2014). A

new adaptive thresholding technique for retinal

vessel segmentation based on local homogeneity

information. In: Image and Signal Processing.

Springer, 558–67.

Mapayi T, Viriri S, Tapamo JR (2015). Comparative

study of retinal vessel segmentation based on

global thresholding techniques. Computational

and Mathematical Methods in Medicine 2015.

Marın D, Aquino A, Geg´undez-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. Medical

Imaging IEEE Transactions on 30:146–58.

Martınez-P´erez ME, Hughes AD, Stanton AV, Thom

SA, Bharath AA, Parker KH (1999). Retinal

blood vessel segmentation by means of scale-space

analysis and region growing. In: Medical Image

Computing and Computer-Assisted Intervention–

MICCAI99. Springer.

Martinez-Perez ME, Hughes AD, Stanton AV, Thom

SA, Chapman N, Bharath AA, Parker KH

(2002). Retinal vascular tree morphology: a semiautomatic

quantification. IEEE transactions on bio

medical engineering 49:912–7.

Mendonca AM, Campilho A (2006). Segmentation of

retinal blood vessels by combining the detection

of centerlines and morphological reconstruction.

Medical Imaging IEEE Transactions on 25:1200–

Miri MS, Mahloojifar A (2011). Retinal

image analysis using curvelet transform

and multistructure elements morphology by

reconstruction. Biomedical Engineering IEEE

Transactions on 58:1183–92.

Nekovei R, Sun Y (1995). Back-propagation network

and its configuration for blood vessel detection in

angiograms. Neural Networks IEEE Transactions

on 6:64–72.

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. In: Medical

Imaging 2004. International Society for Optics and


Onkaew D, Turior R, Uyyanonvara B, Akinori N,

Sinthanayothin C (2011). Automatic retinal

vessel tortuosity measurement using curvature of

improved chain code. In: Electrical, Control

and Computer Engineering (INECCE), 2011

International Conference on. IEEE.

Osareh A, Shadgar B (2009). Automatic blood vessel

segmentation in color images of retina. Iran J Sci

Technol Trans B Engineering 33:191–206.

O’Sullivan J, Gilbert C, Foster A (1997). The causes

of childhood blindness in south africa. South

African medical journal Suid Afrikaanse tydskrif

vir geneeskunde 87:1691–5.

Owen CG, Newsom RS, Rudnicka AR, Barman SA,

Woodward EG, Ellis TJ (2008). Diabetes and

the tortuosity of vessels of the bulbar conjunctiva.

Ophthalmology 115:e27–e32.

Patasius M, Marozas V, Lukosevicius A, Jegelevicius

D (2007). Model based investigation of retinal

vessel tortuosity as a function of blood pressure:

preliminary results. In: Engineering in Medicine

and Biology Society, 2007. EMBS 2007. 29th

Annual International Conference of the IEEE.


Poletti E, Fiorin D, Grisan E, Ruggeri A (2011).

Automatic vessel segmentation in wide-field retina

images of infants with retinopathy of prematurity.

In: Engineering in Medicine and Biology Society,

EMBC, 2011 Annual International Conference of


Poletti E, Grisan E (2014). Learning optimal

matched filters for retinal vessel segmentation with

ada-boost. In: XIII Mediterranean Conference

on Medical and Biological Engineering and

Computing 2013. Springer.

Poletti E, Ruggeri A (2012). Segmentation of

vessels through supervised classification in widefield

retina images of infants with retinopathy of

prematurity. In: Computer-Based Medical Systems

(CBMS), 2012 25th International Symposium on.


Rechtman E, Harris A, Garzozi HJ, Ciulla TA

(2007). Pharmacologic therapies for diabetic

retinopathy and diabetic macular edema. Clinical

ophthalmology Auckland NZ 1:383.

Ricci E, Perfetti R (2007). Retinal blood vessel

segmentation using line operators and support

vector classification. Medical Imaging IEEE

Transactions on 26:1357–65.

Saffarzadeh VM, Osareh A, Shadgar B (2014). Vessel

segmentation in retinal images using multi-scale

line operator and k-means clustering. Journal of

medical signals and sensors 4:122.

Sasongko MB, Wang JJ, Donaghue KC, Cheung

N, Benitez-Aguirre P, Jenkins A, Hsu W, Lee

ML, Wong TY (2010). Alterations in retinal

microvascular geometry in young type 1 diabetes.

Diabetes Care 33:1331–6.

Scheie HG (1953). Evaluation of ophthalmoscopic

changes of hypertension and arteriolar sclerosis.

AMA archives of ophthalmology 49:117–38.

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 Journal of Ophthalmology


Sinthanayothin C, Panitsuk P, Uyyanonvara B (2010).

Automatic retinal vessel tortuosity measurement.

In: Electrical Engineering/Electronics Computer

Telecommunications and Information Technology

(ECTI-CON), 2010 International Conference on.


Soares JV, Leandro JJ, Cesar RM, Jelinek HF, Cree

MJ (2006). Retinal vessel segmentation using the

-d gabor wavelet and supervised classification.

Medical Imaging IEEE Transactions on 25:1214–

Staal J, Abr`amoff MD, Niemeijer M, Viergever

MA, van Ginneken B (2004). Ridge-based

vessel segmentation in color images of the retina.

Medical Imaging IEEE Transactions on 23:501–9.

STARE (2000). Stare (structured analysis of

the retina) projectwebsite. clemson, sc, clemson

univ. [online], available: http://www.ces.˜ahoover/stare/.

Sun K, Chen Z, Jiang S, Wang Y (2011).

Morphological multiscale enhancement, fuzzy

filter and watershed for vascular tree extraction

in angiogram. Journal of medical systems


Sussman EJ, Tsiaras WG, Soper KA (1982). Diagnosis

of diabetic eye disease. Jama 247:3231–4.

Szpak ZL, Tapamo JR (2008). Automatic and

interactive retinal vessel segmentation: pattern

recognition special edition. South African

Computer Journal 40:23–30.

Taarnhøj N, Munch I, Sander B, Kessel L, Hougaard

J, Kyvik K, Sørensen TI, Larsen M (2008).

Straight versus tortuous retinal arteries in relation

to blood pressure and genetics. British Journal of

Ophthalmology 92:1055–60.

Tolias YA, Panas SM (1998). A fuzzy vessel tracking

algorithm for retinal images based on fuzzy

clustering. Medical Imaging IEEE Transactions on


Varughese S, Gilbert C, Pieper C, Cook C (2008).

Retinopathy of prematurity in south africa: an

assessment of needs, resources and requirements

for screening programmes. British Journal of

Ophthalmology 92:879–82.

Verma L, Prakash G, Tewari HK (2002). Diabetic

retinopathy: time for action. no complacency



Vlachos M, Dermatas E (2010). Multi-scale

retinal vessel segmentation using line tracking.

Computerized Medical Imaging and Graphics


Wang Y, Ji G, Lin P, Trucco E, et al. (2013). Retinal

vessel segmentation using multiwavelet kernels

and multiscale hierarchical decomposition. Pattern

Recognition 46:2117–33.

Wasan B, Cerutti A, Ford S, Marsh R (1995). Vascular

network changes in the retina with age and

hypertension. Journal of hypertension 13:1724–8.

WHO (2010). Action plan for the prevention of

avoidable blindness and visual impairment, 2009-

World Health Organization.

Wilson CM, Cocker KD, Moseley MJ, Paterson C,

Clay ST, Schulenburg WE, Mills MD, Ells AL,

Parker KH, Quinn GE, et al. (2008). Computerized

analysis of retinal vessel width and tortuosity in

premature infants. Investigative ophthalmology

visual science 49:3577–85.

Wolffsohn JS, Napper GA, Ho SM, Jaworski A,

Pollard TL (2001). Improving the description of

the retinal vasculature and patient history taking

for monitoring systemic hypertension. Ophthalmic

and Physiological Optics 21:441–9.

Xiao Z, Adel M, Bourennane S (2013). Bayesian

method with spatial constraint for retinal vessel

segmentation. Computational and mathematical

methods in medicine 2013.

Yang Y, Huang S, Rao N (2008). An automatic

hybrid method for retinal blood vessel extraction.

International Journal of Applied Mathematics and

Computer Science 18:399–407.

Yin Y, Adel M, Bourennane S (2013). Automatic

segmentation and measurement of vasculature

in retinal fundus images using probabilistic

formulation. Computational and mathematical

methods in medicine 2013.

You X, Peng Q, Yuan Y, Cheung Ym, Lei J (2011).

Segmentation of retinal blood vessels using the

radial projection and semi-supervised approach.

Pattern Recognition 44:2314–24.

Zana F, Klein JC (2001). Segmentation of vessellike

patterns using mathematical morphology and

curvature evaluation. Image Processing IEEE

Transactions on 10:1010–9.

Zhang B, Zhang L, Zhang L, Karray F (2010). Retinal

vessel extraction by matched filter with first-order

derivative of gaussian. Computers in biology and

medicine 40:438–45.




How to Cite

Mapayi, T., Tapamo, J.-R., Viriri, S., & Adio, A. (2016). AUTOMATIC RETINAL VESSEL DETECTION AND TORTUOSITY MEASUREMENT. Image Analysis and Stereology, 35(2), 117–135.



Original Research Paper