Feature Selection for SVM-Based Vascular Anomaly Detection

  • Maria A. Zuluaga
  • Edgar J. F. Delgado Leyton
  • Marcela Hernández Hoyos
  • Maciej Orkisz
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6533)

Abstract

This work explores feature selection to improve the performance in the vascular anomaly detection domain. Starting from a previously defined classification framework based on Support Vector Machines (SVM), we attempt to determine features that improve classification performance and to define guidelines for feature selection. Three different strategies were used in the feature selection stage, while a Density Level Detection-SVM (DLD-SVM) was used to validate the performance of the selected features over testing data. Results show that a careful feature selection results in a good classification performance. DLD-SVM shows a poor performance when using all the features together, owing to the curse of dimensionality.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Breiman, L.: Random forests. Mach. Learning 45(1), 5–32 (2001)CrossRefMATHGoogle Scholar
  2. 2.
    Florin, C., Paragios, N., Williams, J.: Particle Filters, a Quasi-Monte Carlo solution for segmentation of coronaries. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 246–253. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  4. 4.
    Fridman, Y., Pizer, S.M., Aylward, S., Bullitt, E.: Segmenting 3D Branching Tubular Structures Using Cores. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2879, pp. 570–577. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  5. 5.
    Guyon, I., Weston, J., Barnhil, S., Vapnik, V.: Gene Selection for Cancer Classification using Support Vector Machines. Mach. Learning 46(1-3), 389–422 (2002)CrossRefMATHGoogle Scholar
  6. 6.
    Hernández Hoyos, M., Orkisz, M., Douek, P.C., Magnin, I.E.: Assessment of carotid artery stenoses in 3D contrast-enhanced magnetic resonance angiography, based on improved generation of the centerline. Mach. Graphics and Vision 14(4), 349–378 (2005)Google Scholar
  7. 7.
    Hernández Hoyos, M., Serfaty, J.M., Maghiar, A., Mansard, C., Orkisz, M., Magnin, I.E., Douek, P.C.: Evaluation of semi-automatic arterial stenosis quantification. Int. J. of Computer Assisted Radiol. and Surg. 1(3), 167–175 (2006)CrossRefGoogle Scholar
  8. 8.
    Išgum, I., Rutten, A., Prokop, M., van Ginneken, B.: Detection of coronary calcifications from computed tomography scans for automated risk assessment of coronary artery disease. Med. Phys. 34(4), 1450–1461 (2007)CrossRefGoogle Scholar
  9. 9.
    Nain, D., Yezzi, A., Turk, G.: Vessel Segmentation Using a Shape Driven Flow. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 51–59. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  10. 10.
    World Health Organization: The top ten causes of death - Fact sheet N310 (October 2008)Google Scholar
  11. 11.
    Peng, H., Long, F., Ding, C.: Feature Selection Based on Mutual information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy. IEEE Trans. Pattern Anal. and Mach. Intell. 27(8), 1226–1238 (2005)CrossRefGoogle Scholar
  12. 12.
    Schaap, M., Metz, C., van Walsum, T., van der Giessen, A.G., Weustink, A.C., Mollet, N.R., Bauer, C., Bogunovic, H., Castro, C., Deng, X., Dikici, E., O’Donnell, T., Frenay, M., Friman, O., Hernández Hoyos, M., Kitslaar, P.H., Krissian, K., Kühnel, C., Luengo-Oroz, M.A., Orkisz, M., Smedby, Ö., Styner, M., Szymczak, A., Tek, H., Wang, C., Warfield, S.K., Zambal, S., Zhang, Y., Krestin, G.P., Niessen, W.J.: Standardized Evaluation Methodology and Reference Database for Evaluating Coronary Artery Centerline Extraction Algorithms. Med. Image Analysis 13(5), 701–714 (2009)CrossRefGoogle Scholar
  13. 13.
    Steinwart, I., Hush, D., Scovel, C.: A Classification Framework for Anomaly Detection. J. Mach. Learning Research 6, 211–232 (2005)MathSciNetMATHGoogle Scholar
  14. 14.
    Wróblewska, A., Boniński, P., Przelaskowski, A., Kazubek, M.: Segmentation and feature extraction for reliable classification of microclacifications in digital mammograms. Opto-electronics Review 11(3), 227–235 (2003)Google Scholar
  15. 15.
    Yang, X., Jia, L., Qingmao, H., Zhijun, C., Xiaohua, D, Pheng Ann, H.: F-score Feature Selection Method May Improve Texture-based Liver Segmentation Strategies. In: Proceedings of 2008 IEEE Int. Symp. on IT in Med. and Education, pp. 697–702 (2008)Google Scholar
  16. 16.
    Zheng, Y., Barbu, A., Georgescu, B., Scheuering, M., Comaniciu, D.: Fast automatic heart chamber segmentation from 3D CT data using marginal space learning and steerable features. In: Int. Conf on Computer Vision, pp. 1–8 (2007)Google Scholar
  17. 17.
    Zuluaga, M.A., Magnin, I.E., Hernández Hoyos, M., Delgado Leyton, E.J.F., Lozano, F., Orkisz, M.: Automatic detection of abnormal vascular cross-sections based on Density Level Detection and Support Vector Machines. Int. J. Comput. Assisted Radiol. Surg. (in-press, 2010), doi:10.1007/s11548-010-0494-8Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Maria A. Zuluaga
    • 1
    • 2
  • Edgar J. F. Delgado Leyton
    • 1
    • 2
  • Marcela Hernández Hoyos
    • 1
  • Maciej Orkisz
    • 2
  1. 1.Grupo Imagine, Grupo de Ingeniería BiomédicaUniversidad de los AndesBogotáColombia
  2. 2.CNRS UMR5220; INSERM U630CREATIS; Université de Lyon; Université Lyon 1; INSA-LyonVilleurbanneFrance

Personalised recommendations