Classification of breast masses via nonlinear transformation of features based on a kernel matrix | Medical & Biological Engineering & Computing Skip to main content
Springer Nature Link
Log in

Classification of breast masses via nonlinear transformation of features based on a kernel matrix

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

We propose methods to perform a certain nonlinear transformation of features based on a kernel matrix, before the classification step, aiming to improve the discriminating power of the comparatively weak edge-sharpness and texture features of breast masses in mammograms, and seek better incorporation of features representing different radiological characteristics than shape features only. Kernel principal component analysis (KPCA) is applied to improve the discriminating power of each single feature in an expanded feature space and the discriminating capability of different feature combinations in other transformed, more informative, lower-dimensional feature spaces. A kernel partial least squares (KPLS) method is developed to derive score vectors for a shape feature set, and an edge-sharpness and texture feature set, respectively, with minimal covariance between each other, to help in achieving improved diagnosis using multiple radiological characteristics of breast masses. Fisher’s linear discriminant analysis (FLDA) is employed to evaluate the classification capability of the transformed features. The methods were tested with a set of 57 regions in mammograms, of which 20 are related to malignant tumors and 37 to benign masses, represented using five shape features, three edge-sharpness features, and 14 texture features. The classification performance of the edge-sharpness and texture features, via KPCA transformation, was significantly improved from 0.75 to 0.85 in terms of the area under the receiver operating characteristics curve (A z ). The classification performance of all of the shape, edge-sharpness, and texture features, via KPLS transformation, was improved from 0.95 to 1.0 in A z value.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Alberta Cancer Board (2004) Screen Test: Alberta program for the early detection of breast cancer. 2001/2003 Biennial Report, Edmonton, Alberta, Canada, 2004 http://www.cancerboard.ab.ca/screentest/downloads/screentest_biennial_2 001-03.pdf

  2. Alto H, Rangayyan RM, Desautels JEL (2005) Content-based retrieval and analysis of mammographic masses. J Electronic Imaging 14(2):1–17 (article no. 023026)

    Google Scholar 

  3. André TCSS, Rangayyan RM (2006) Classification of breast masses in mammograms using neural networks with shape, edge sharpness, and texture features. J Electronic Imaging 15(1):1–10 (article no. 013019)

    Google Scholar 

  4. Bach F, Jordan M (2002) Kernel independent component analysis. J Mach Learn Res 3:1–48

    Article  Google Scholar 

  5. Bruce LM, Adhami RR (1999) Classifying mammographic mass shapes using the wavelet transform modulus-maxima method. IEEE Trans Med Imaging 18(12):1170–1177

    Article  Google Scholar 

  6. Burhenne LJW, Wood SA, D’Orsi CJ, Feig SA, Kopans DB, O’Shaughnessy KF, Sickles EA, Tabar L, Vyborny CJ, Castellino RA (2000) Potential contribution of computer-aided detection to the sensitivity of screening mammography. Radiology 215:554–562

    Google Scholar 

  7. Ciatto S, Del Turco MR, Risso G, Catarzi S, Bonaldi R, Viterbo V, Gnutti P, Guglielmoni B, Pinelli L, Pandiscia A, Navarra F, Lauria A, Palmiero R, Indovina PL (2003) Comparison of standard reading and computer aided detection (CAD) on a national proficiency test of screening mammography. Eur J Radiol 45:135–138

    Article  Google Scholar 

  8. Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, New York

    Google Scholar 

  9. Duijm L, Groenewoud JH, Jansen FH, Fracheboud J, Beek M, de Koning HJ (2004) Mammography screening in the Netherlands: delay in the diagnosis of breast cancer after breast cancer screening. Br J Cancer 91:1795–1799

    Article  Google Scholar 

  10. Evans WP, Burhenne LJW, Laurie L, O’Shaughnessy KF, Castellino RA (2002) Invasive lobular carcinoma of the breast: mammographic characteristics and computer-aided detection. Radiology 225(1):182–189

    Article  Google Scholar 

  11. Freer TW, Ulissey MJ (2001) Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology 220:781–786

    Article  Google Scholar 

  12. Guo Y, Sivaramakrishna R, Lu CC, Suri JS, Laxminarayan S (2006) Breast image registration techniques: a survey. Med Biol Eng Comput 44(1-2):15–26

    Article  Google Scholar 

  13. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC 3(6):610–622

    Google Scholar 

  14. Hardoon DR, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16(12):2639–2664

    Article  MATH  Google Scholar 

  15. Homer MJ (1997) Mammographic interpretation: a practical approach, 2nd edn. McGraw-Hill, Boston

    Google Scholar 

  16. Höskuldsson A (2006) PLS regression and the covariance. Danmarks Tekniske Universitet, IPL; DTU, Bldg 358, 2800 Kgs Lyngby, Denmark, September 2006. http://www.acc.umu.se/∼tnkjtg/Chemometrics/Editorial

  17. Höskuldsson A (1988) PLS regression methods. J Chemom 2:211–228

    Article  Google Scholar 

  18. Jolliffe IT (1986) Principal component analysis. Springer, New York

    Google Scholar 

  19. Mu T, Nandi AK, Rangayyan RM (2007) Classification of breast masses via transformation of features using kernel principal component analysis. In: Proceedings of the 5th IASTED international conference on biomedical engineering, BioMED. Innsbruck, Austria, February 2007

  20. Mudigonda NR, Rangayyan RM, Desautels JEL (2000) Gradient and texture analysis for the classification of mammographic masses. IEEE Trans Med Imaging 19(10):1032–1043

    Article  Google Scholar 

  21. Mudigonda NR, Rangayyan RM, Desautels JEL (2001) Detection of breast masses in mammograms by density slicing and texture flow field analysis. IEEE Trans Med Imaging 20(12):1215–1227

    Article  Google Scholar 

  22. Nandi RJ, Nandi AK, Rangayyan RM, Scutt D (2006) Classification of breast masses in mammograms using genetic programming and feature selection. Med Biol Eng Comput 44(8):693–694

    Article  Google Scholar 

  23. Peitgen HO (ed) (2002) In: Proceedings of the 6th international workshop on digital mammography. Bremen, Germany, June 2002. Springer, Heidelberg

  24. Pelckmans K, Suykens JAK, Gestel TV, Brabanter JD, Lukas L, Hamers B, Moor BD, Vandewalle J (2003) LS-SVMlab1.5: least squares support vector machines. Katholieke University Leuven, Belgium, 2003. Available at http://www.esat.kuleuven.ac.be/sista/lssvmlab/toolbox.html

  25. Pisano E (ed) (2004) In: Proceedings of the 7th international workshop on digital mammography. Durham, NC, June 2004

  26. Rangayyan RM, Nguyen TM (2006) Fractal analysis of contours of breast masses in mammograms. J Digital Imaging, October 2006. PMID: 17021926 (Epub ahead of print)

  27. Rangayyan RM, El-Faramawy NM, Desautels JEL, Alim OA (1997) Measures of acutance and shape for classification of breast tumors. IEEE Trans Med Imaging 16(6):799–810

    Article  Google Scholar 

  28. Rangayyan RM, Mudigonda NR, Desautels JEL (2000) Boundary modelling and shape analysis methods for classification of mammographic masses. Med Biol Eng Comput 38(5):487–496

    Article  Google Scholar 

  29. Rosipal R, Krämer N (2005) Overview and recent advances in partial least squares. In: Proceedings of subspace, latent structure, and feature selection workshop, SLSFS 2005. Bohinj, Slovenia, February 2005, pp 34–51

  30. Rosipal R, Trejo LJ (2001) Kernel partial least squares regression in reproducing kernel Hilbert space. J Mach Learn Res 2:97–123

    Article  Google Scholar 

  31. Sahiner BS, Chan HP, Petrick N, Helvie MA, Goodsitt MM (1998) Computerized characterization of masses on mammograms: the rubber band straightening transform and texture analysis. Med Phys 25(4):516–526

    Article  Google Scholar 

  32. Sahiner BS, Chan HP, Petrick N, Helvie MA, Hadjiiski LM (2001) Improvement of mammographic mass characterization using spiculation measures and morphological features. Med Phys 28(7):1455–1465

    Article  Google Scholar 

  33. Scholköpf B, Smola A, Müller KR (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5):1299–1319

    Article  Google Scholar 

  34. Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, Cambridge

    Google Scholar 

  35. Sherrah JR, Bogner RE, Bouzerdoum A (1997) The evolutionary pre-processor: automatic feature extraction for supervised classification using genetic programming. In: Proceedings of the 2nd annual genetic programming conference. Stanford, CA, July 1997, pp 304–312

  36. Weng S, Zhang C, Lin Z, Zhang X (2005) Mining the structural knowledge of high-dimensional medical data using isomap. Med Biol Eng Comput 43(3):410–412

    Article  Google Scholar 

  37. Wold H (1985) Partial least squares. In: Kotz S, Johnson NL (eds) Encyclopedia of the statistical sciences, vol 6. Wiley, New York, pp 581–591

    Google Scholar 

Download references

Acknowledgment

T. Mu would like to acknowledge financial support from the Overseas Research Students Awards Scheme (ORSAS), UK; the Hsiang Su Coppin Memorial Scholarship Fund, and the University of Liverpool, UK. We thank the University Research Grants Committee of the University of Calgary, Canada, and the Medical Research Council (the Interdisciplinary Bridging Awards), UK, for financial support.

Author information

Authors and Affiliations

  1. Department of Electrical Engineering and Electronics, The University of Liverpool, Liverpool, Brownlow Hill, L69 3GJ, UK

    Tingting Mu & Asoke K. Nandi

  2. Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada, T2N 1N4

    Rangaraj M. Rangayyan

Authors
  1. Tingting Mu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Asoke K. Nandi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rangaraj M. Rangayyan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Asoke K. Nandi.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mu, T., Nandi, A.K. & Rangayyan, R.M. Classification of breast masses via nonlinear transformation of features based on a kernel matrix. Med Bio Eng Comput 45, 769–780 (2007). https://doi.org/10.1007/s11517-007-0211-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-007-0211-0

Keywords

Search

Navigation