Advertisement

A Comparative Study on Feature Selection for Retinal Vessel Segmentation Using Ant Colony System

  • Ahmed H. Asad
  • Ahmad Taher Azar
  • Aboul Ella Otifey Hassaanien
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 235)

Abstract

The diabetic retinopathy disease spreads diabetes on the retina vessels thus they lose blood supply that causes blindness in short time, so early detection of diabetes prevents blindness in more than 50% of cases. The early detection can be achieved by automatic segmentation of retinal blood vessels which is two-class classification problem. Features selection is an essential step in successful data classification since it reduces the data dimensionality by removing redundant features, thus minimizing the classification complexity, time and maximizes its accuracy. In this paper, comparative study on four features selection heuristics is performed to select the best relevant features set from features vector consists of fourteen features that are computed for each pixel in the field of view of retinal image in the DRIVE database. The comparison is assessed in terms of sensitivity, specificity and accuracy of the recommended features set by each heuristic when used with the ant colony system algorithm. The results indicated that the recommended features set by the relief heuristic gives the best performance with sensitivity of 75.84%, specificity of 93.88% and accuracy of 91.55%.

Keywords

Retinal Blood Vessels Feature selection Segmentation Features Extraction Ant Colony System computer aided diagnosis (CAD) 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Assad, A., Azar, A.T., Hassaanien, A.E.: Ant Colony-based System for Retinal Blood Vessels Segmentation. In: Seventh International Conference on Bio-Inspired Computing: Theories and Application, 2012 (BIC-TA 2012), Gwalior, India, December 14 - 16 (2012)Google Scholar
  2. Bloomgarden, Z.T.: Screening for and managing diabetic retinopathy: current approaches. Am. J. Health Syst. Pharm. 64 (17 suppl. 12), S8–S14 (2007)Google Scholar
  3. Blum, A., Langley, P.: Selection of relevant features and examples in machine learning. Artificial Intelligence 97(1-2), 245–271 (1997)MathSciNetCrossRefMATHGoogle Scholar
  4. Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth & Brooks/Cole Advanced Books & Software, CA, USA (1984)MATHGoogle Scholar
  5. Chew, E.Y.: Screening options for diabetic retinopathy. Curr. Opin. Ophthalmol 17(6), 519–522 (2006)MathSciNetCrossRefGoogle Scholar
  6. Dorigo, M., Gambardella, L.M.: Ant colony system: a cooperative learning ap-proach to the traveling salesman problem. IEEE Trans. Evol. Comput. 1(1), 53–66 (1997)CrossRefGoogle Scholar
  7. Fraz, M.M., Remagnino, P., Hoppe, A., Uyyanonvara, B., Rudnicka, A.R., Owen, C.G., Bar-man, S.A.: Blood vessel segmentation methodologies in retinal images–a survey. Comput. Methods Programs Biomed. 108(1), 407–433 (2012), doi:10.1016/j.cmpb.2012.03.009.CrossRefGoogle Scholar
  8. Farley, T.F., Mandava, N., Prall, F.R., Carsky, C.: Accuracy of primary care clinicians in screening for diabetic retinopathy using single-image retinal photography. Ann. Fam Med. 6(5), 428–434 (2008)CrossRefGoogle Scholar
  9. Foracchia, M., Grisan, E., Ruggeri, A.: Extraction and quantitative description of vessel features in hypertensive retinopathy fundus images. In: Book Abstracts 2nd International Workshop on Computer Assisted Fundus Image Analysis (2001)Google Scholar
  10. Goatman, K., Charnley, A., Webster, L., Nussey, S.: Assessment of auto-mated disease detection in diabetic retinopathy screening using two-field photography. PLoS One 6(12), e27524 (2011)Google Scholar
  11. Hall, M.A., Smith, L.A.: Feature Selection for Machine Learning: Comparing a Correlation-Based Filter Approach to the Wrapper. In: FLAIRS Conference, pp. 235–239 (1999)Google Scholar
  12. Hall, M.A.: Correlation-based Feature Selection for Discrete and Numeric Class Machine Learning. In: ICML, pp. 359–366 (2000)Google Scholar
  13. Hall, M., Holmes, G.: Benchmarking attribute selection techniques for discrete class data mining. IEEE Transact. Knowl. Data Eng. 15(6), 1437–1447 (2003)CrossRefGoogle Scholar
  14. Hua, J.P., Tembe, W.D., Dougherty, E.R.: Performance of feature-selection methods in the classification of high-dimension data. Pattern Recognition 42(3), 409–424 (2009)CrossRefMATHGoogle Scholar
  15. Hu, M.K.: Visual Pattern Recognition by Moment Invariants. IRE Trans. Inform. Theory. 8(2), 179–187 (1962)CrossRefMATHGoogle Scholar
  16. Jin, X., Guangshu, H., Tianna, H., Houbin, H., Bin, C.: The Multifocal ERG in Early Detection of Diabetic Retinopathy. Conf. Proc. IEEE Eng. Med. Biol. Soc. 7, 7762–7765 (2005)Google Scholar
  17. Jones, S., Edwards, R.T.: Diabetic retinopathy screening: a systematic review of the economic evidence. Diabet. Med. 27(3), 249–256 (2010)CrossRefGoogle Scholar
  18. Khan, M.I., Shaikh, H., Mansuri, A.M.: A Review of Retinal Vessel Segmentation Techniques and Algorithms. Int. J. Comp. Tech. Appl. 2(5), 1140–1144 (2011)Google Scholar
  19. Kira, K., Rendell, L.A.: A practical approach to feature selection. In: The Proceedings of Ninth International Conference on Machine Learning, Aberdeen, Scotland, pp. 249–256. Morgan Kaufmann, Los Altos (1992)Google Scholar
  20. Kohavi, R., John, G.H.: Wrappers for feature subset selection. Artificial Intelligence 97(1-2), 273–324 (1997)CrossRefMATHGoogle Scholar
  21. Kononenko, I.: Estimating attributes: analysis and extensions of relief. In: Bergadano, F. (ed.) Proceedings of the Seventh European Conference on Machine Learning, vol. 784, pp. 171–182. Springer, Berlin (1994)Google Scholar
  22. Leung, H., Wang, J.J., Rochtchina, E., Wong, T.Y., Klein, R., Mitchell, P.: Impact of current and past blood pressure on retinal arteriolar diameter in an older population. J. Hypertens 22(8), 1543–1549 (2004)CrossRefGoogle Scholar
  23. Marin, D., Aquino, A., Gegundez-Arias, M.E., Bravo, J.M.: A New Supervised Method for Blood Vessel Segmentation in Retinal Images by Using Grey-Level and Moment Invariants-Based Features. IEEE Trans. Med. Imaging 30(1), 146–158 (2011)CrossRefGoogle Scholar
  24. Mendonca, A.M., Campilho, A.: Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans. Med. Imaging 25(9), 1200–1213 (2006)CrossRefGoogle Scholar
  25. Mitchell, P., Leung, H., Wang, J.J., Rochtchina, E., Lee, A.J., Wong, T.Y., Klein, R.: Retinal vessel diameter and open-angle glaucoma: the Blue Mountains Eye Study. Ophthalmology 112(2), 245–250 (2005)CrossRefGoogle Scholar
  26. Morello, C.M.: Etiology and natural history of diabetic retinopathy: an overview. Am. J. Health Syst. Pharm. 64 (17 suppl. 12), S3–S7 (2007)Google Scholar
  27. Rodgers, M., Hodges, R., Hawkins, J., Hollingworth, W., Duffy, S., McKib-bin, M., Mans-field, M., Harbord, R., Sterne, J., Glasziou, P., Whiting, P., Westwood, M.: Colour vi-sion testing for diabetic retinopathy: a systematic review of diagnostic accuracy and economic evaluation. Health Technol. Assess. 13(60), 1–160 (2009)Google Scholar
  28. Serrarbassa, P.D., Dias, A.F., Vieira, M.F.: New concepts on diabetic retinopathy: neural versus vascular damage. Arq Bras Oftalmol. 71(3), 459–463 (2008)CrossRefGoogle Scholar
  29. Sinclair, S.H.: Diabetic retinopathy: the unmet needs for screening and a review of potential solutions. Expert Rev. Med. Devices 3(3), 301–313 (2006)MathSciNetCrossRefGoogle Scholar
  30. Soares, J.V., Leandro, J.J., Cesar Júnior, R.M., Jelinek, H.F., Cree, M.: Retinal vessel segmen-tation using the 2-D Gabor wavelet and supervised classification. IEEE Trans. Med. Imaging 25(9), 1214–1222 (2006)CrossRefGoogle Scholar
  31. Staal, J.J., Abramoff, M.D., Niemeijer, M., Viergever, M.A., van Ginneken, B.: Ridge based vessel segmentation in color images of the retina. IEEE Transactions on Medical Imaging 23(4), 501–509 (2004)CrossRefGoogle Scholar
  32. Talavera, L.: An evaluation of filter and wrapper methods for feature selection in categorical clustering. In: Proceeding of 6th International Symposium on Intelligent Data Analysis, Madrid, Spain, pp. 440–451 (2005)Google Scholar
  33. Verma, K., Deep, P., Ramakrishnan, A.G.: Detection and classification of diabetic retinopathy using retinal images. In: Annual IEEE India Conference (INDICON), pp. 1–6 (2011), doi:10.1109/INDCON.2011.6139346Google Scholar
  34. Vijayakumari, V., Suriyanarayanan, N.: Survey on the Detection Methods of Blood Vessel in Retinal Images. Eur. J. Sci. Res. 68(1), 83–92 (2012)Google Scholar
  35. Wang, J.J., Taylor, B., Wong, T.Y., Chua, B., Rochtchina, E., Klein, R., Mitchell, P.: Retinal vessel diameters and obesity: a population-based study in older persons. Obesity (Silver Spring) 14(2), 206–214 (2006)CrossRefGoogle Scholar
  36. Xu, J., Hu, G., Huang, T., Huang, H., Chen, B.: Using multifocal ERG re-sponses to discriminate diabetic retinopathy. Doc. Ophthalmol. 112(3), 201–207 (2006)CrossRefGoogle Scholar
  37. You, X., Peng, Q., Yuan, Y., Cheung, Y., Lei, J.: Segmentation of retinal blood ves-sels using the radial projection and semi-supervised approach. Pattern Recognition 44(10-11), 2314–2324 (2011)CrossRefGoogle Scholar
  38. Lupascu, C.A., Tegolo, D., Trucco, E.: A comparative study on feature selec-tion for retinal vessel segmentation using FABC. In: Proc 13th International Conference on Computer Analysis of Images and Patterns (CAIP), pp. 655–662 (September 2009)Google Scholar
  39. Lupascu, C.A., Tegolo, D., Trucco, E.: FABC: Retinal vessel segmentation using adaboost. IEEE Trans. Inf. Technol. Biomed. 14(5), 1267–1274 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Ahmed H. Asad
    • 1
  • Ahmad Taher Azar
    • 2
  • Aboul Ella Otifey Hassaanien
    • 3
  1. 1.Institute of Statistical Studies and Researches, CS DepartmentCairo UniversityGizaEgypt
  2. 2.Faculty of computers and information, Scientific Research Group in Egypt (SRGE)Benha UniversityQalyubiaEgypt
  3. 3.Faculty of Computer and Information, IT DepartmentCairo UniversityGizaEgypt

Personalised recommendations