Skip to main content

Advertisement

SpringerLink
Log in

Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Objective

This paper presents a detailed study of fractal-based methods for texture characterization of mammographic mass lesions and architectural distortion. The purpose of this study is to explore the use of fractal and lacunarity analysis for the characterization and classification of both tumor lesions and normal breast parenchyma in mammography.

Materials and methods

We conducted comparative evaluations of five popular fractal dimension estimation methods for the characterization of the texture of mass lesions and architectural distortion. We applied the concept of lacunarity to the description of the spatial distribution of the pixel intensities in mammographic images. These methods were tested with a set of 57 breast masses and 60 normal breast parenchyma (dataset1), and with another set of 19 architectural distortions and 41 normal breast parenchyma (dataset2). Support vector machines (SVM) were used as a pattern classification method for tumor classification.

Results

Experimental results showed that the fractal dimension of region of interest (ROIs) depicting mass lesions and architectural distortion was statistically significantly lower than that of normal breast parenchyma for all five methods. Receiver operating characteristic (ROC) analysis showed that fractional Brownian motion (FBM) method generated the highest area under ROC curve (A z  = 0.839 for dataset1, 0.828 for dataset2, respectively) among five methods for both datasets. Lacunarity analysis showed that the ROIs depicting mass lesions and architectural distortion had higher lacunarities than those of ROIs depicting normal breast parenchyma. The combination of FBM fractal dimension and lacunarity yielded the highest A z value (0.903 and 0.875, respectively) than those based on single feature alone for both given datasets. The application of the SVM improved the performance of the fractal-based features in differentiating tumor lesions from normal breast parenchyma by generating higher A z value.

Conclusion

FBM texture model is the most appropriate model for characterizing mammographic images due to self-affinity assumption of the method being a better approximation. Lacunarity is an effective counterpart measure of the fractal dimension in texture feature extraction in mammographic images. The classification results obtained in this work suggest that the SVM is an effective method with great potential for classification in mammographic image analysis.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Cancer research UK (2008) online: http://www.cancerresearchuk.org/breastcancer/breast_cancer/. Accessed on 12 June 2008

  2. Forrest A, Aitken R (1990) Mammography screening for breast cancer. Annu Rev Med 41: 117–132. doi:10.1146/annurev.me.41.020190.001001

    Article  PubMed  CAS  Google Scholar 

  3. Giger ML, Huo Z, Kupinski MA, Vyborny CJ (2000) Computer-aided Diagnosis in Mammography. In: Sonka M, Fitzzpatrick JM (ed) Handbook of medical imaging, vol 2. SPIE, Bellingham, pp 915–1004

  4. Doi K, MacMahon H, Katsuragawa S, Nishikawa RM, Jiang Y (1997) Computer-aided diagnosis in radiology: potential and pitfalls. Eur J Radiol 31: 97–109. doi:10.1016/S0720-048X(99)00016-9

    Article  Google Scholar 

  5. Astley SM, Gilbert FJ (2004) Computer-aided detection in mammography. Clin Radiol 59: 390–399. doi:10.1016/j.crad.2003.11.017

    Article  PubMed  CAS  Google Scholar 

  6. American College of Radiology (1998) Illustrated breast imaging reporting and data system (BI-RADS), 3rd edn. American College of Radiology, Reston

  7. Knutzen AM, Gisvold JJ (1993) Likelihood of malignant disease for various categories of mammographically detected, nonpalpable breast lesions. Mayo Clin Proc 68: 454–460

    PubMed  CAS  Google Scholar 

  8. Yankaskas BC, Schell MJ, Bird RE, Desrochers DA (2001) Reassessment of breast cancers missed during routine screening mammography: a community-based study. AJR Am J Roentgenol 177: 535–541

    PubMed  CAS  Google Scholar 

  9. Burrell HC, Sibbering DM, Wilson ARM, Pinder SE, Evans AJ, Yeoman LJ, Elston CW, Ellis IO, Blamey RW, Robertson JFR (1996) Screening interval breast cancers: mammography features and prognostic factors. Radiology 199(7): 811–817

    PubMed  CAS  Google Scholar 

  10. Burrell HC, Evans AJ, Wilson ARM, Pinder S (2001) False-negative breast screening assessment: what lessons can we learn? Clin Radiol 56: 385–388. doi:10.1053/crad.2001.0662

    Article  PubMed  CAS  Google Scholar 

  11. Sickles EA (1986) Mammographic features of 300 consecutive nonpalpable breast cancers. AJR Am J Roentgenol 146: 661–663

    PubMed  CAS  Google Scholar 

  12. Broeders MJM, Onland-Moret NC, Rijken HJTM, Hendriks JHCL, Verbeek ALM, Holland R (2003) Use of previous screening mammograms to identify features indicating cases that would have a possible gain in prognosis following earlier detection. Eur J Cancer 39: 1770–1775. doi:10.1016/S0959-8049(03)00311-3

    Article  PubMed  CAS  Google Scholar 

  13. Mandelbrot BB (1983) The fractal geometry of nature. Freeman, New York

    Google Scholar 

  14. Pentland A (1984) Fractal-based description of natural scenes. IEEE Trans Pattern Anal Mach Intell 6(6): 661–674

    Article  Google Scholar 

  15. Deering W, West BJ (1992) Fractal physiology. IEEE Eng Med Biol 11(2): 40–46. doi:10.1109/51.139035

    Article  Google Scholar 

  16. Zheng L, Chan A (2001) An artificial intelligent algorithm for tumor detection in screening mammogram. IEEE Trans Med Imaging 20(7): 559–567. doi:10.1109/42.932741

    Article  PubMed  CAS  Google Scholar 

  17. Priebe CE, Solka JL, Lorey RA, Rogers GW, Poston WL, Kallergi M, Qian W, Clarke LP, Clark RA (1994) The application of fractal analysis to mammographic tissue classification. Cancer Lett 77: 183–189. doi:10.1016/0304-3835(94)90101-5

    Article  PubMed  CAS  Google Scholar 

  18. Li H, Liu KJR, Lo S-CB (1997) Fractal modelling and segmentation for the enhancement of microcalcifications in digital mammograms. IEEE Trans Med Imaging 16(6): 785–798. doi:10.1109/42.650875

    Article  PubMed  CAS  Google Scholar 

  19. Bocchi L, Coppini G, Nori J, Valli G (2004) Detection of single and clustered microcalcifications in mammograms using fractal models and neural networks. Med Eng Phys 26: 303–312. doi:10.1016/j.medengphy.2003.11.009

    Article  PubMed  CAS  Google Scholar 

  20. Tourassi GD, Delong DM, Floyd CE Jr (2006) A study on the computerized fractal analysis of architectural distortion in screening mammograms. Phys Med Biol 51: 1299–1312. doi:10.1088/0031-9155/51/5/018

    Article  PubMed  Google Scholar 

  21. Rangayyan RM, Prajna S, Ayres FJ, Desautels JEL (2008) Detection of architectural distortion in prior screening mammograms using Gabor filters, phase portraits, fractal dimension, and texture analysis. Int J CARS 2: 347–361. doi:10.1007/s11548-007-0143-z

    Article  Google Scholar 

  22. Burgess AE (1999) Mammographic structure: data preparation and spatial statistics. Proc SPIE Int Soc Opt Eng 3661: 642–653

    Google Scholar 

  23. Heine JJ, Deans SR, Velthuizen RP, Clarke LP (1999) On the statistical nature of mammograms. Med Phys 26: 2254–2265. doi:10.1118/1.598739

    Article  PubMed  CAS  Google Scholar 

  24. Heine JJ, Velthuizen RP (2000) A statistical methodology for mammographic density detection. Med Phys 27: 2644–2651. doi:10.1118/1.1323981

    Article  PubMed  CAS  Google Scholar 

  25. Caldwell CB, Stapleton SJ, Holdsworth DW, Jong RA, Weiser WJ, Cooke G, Yaffe MJ (1990) Characterization of mammographic parenchymal pattern by fractal dimension. Phys Med Biol 35(2): 235–247. doi:10.1088/0031-9155/35/2/004

    Article  PubMed  CAS  Google Scholar 

  26. Byng JW, Boyd NF, Fishell E, Jong RA, Yaffe MJ (1996) Automated analysis of mammographic densities. Phys Med Biol 41: 909–923. doi:10.1088/0031-9155/41/5/007

    Article  PubMed  CAS  Google Scholar 

  27. Keller JM, Chen S, Crownover RM (1989) Texture description and segmentation through fractal geometry. Comput Vis Graph Image Process 45: 150–166. doi:10.1016/0734-189X(89)90130-8

    Article  Google Scholar 

  28. Torres-Mejia G, De Stavola B, Allen DS, Perez-Gavilan JJ, Ferreira JM, Fentiman IS, dos Santos Silva I (2005) Mammographic features and subsequent risk of breast cancer: a comparison of qualitative and quantitative evaluations in the Guernsey prospective studies. Cancer Epidemiol Biomarkers Prev 14(5): 1052–1059. doi:10.1158/1055-9965.EPI-04-0717

    Article  PubMed  Google Scholar 

  29. de Melo RHC, Vieira EA, Conci A (2006) Characterizing the lacunarity of objects and image sets and its use as a technique for the analysis of textural patterns. ACIVS 2006, Belgium, pp 208–219

  30. Gagnepain JJ, Roques-Carmes C (1986) Fractal approach to two-dimensional and three dimensional surface roughness. Wear 109: 119–126. doi:10.1016/0043-1648(86)90257-7

    Article  Google Scholar 

  31. Sarkar N, Chaudhuri BB (1994) An efficient differential box-counting approach to compute fractal dimension of image. IEEE Trans Syst Man Cybern 24(1): 115–120. doi:10.1109/21.259692

    Article  Google Scholar 

  32. Peleg S, Naor J, Hartley R, Avnir D (1984) Multiple resolution texture analysis and classification. IEEE Trans Pattern Anal Mach Intell 6(4): 518–523

    Google Scholar 

  33. Voss RF (1985) Random fractal forgeries. In: Earnshaw RA (eds) Fundamental algorithms for computer graphics. Springer, Heidelberg, pp 805–835

    Google Scholar 

  34. Peitgen H-O, Saupe D (1988) The science of fractal images. Springer, Heidelberg

    Google Scholar 

  35. Mandelbrot BB, Wallis JW (1968) Fractional Brownian motions, fractional noises, and applications. SIAM Rev 10: 422–437. doi:10.1137/1010093

    Article  Google Scholar 

  36. Kube P, Pentland A (1988) On the imaging of fractal surfaces. IEEE Trans Pattern Anal Mach Intell 10(5): 704–707. doi:10.1109/34.6779

    Article  Google Scholar 

  37. Chen C-C, Daponte JS, Fox MD (1989) Fractal feature analysis and classification in medical imaging. IEEE Trans Med Imaging 8(2): 133–142. doi:10.1109/42.24861

    Article  PubMed  CAS  Google Scholar 

  38. Plotnick RE, Gardner RH, Hargrove WW, Prestegaard K, Perlmutter M (1996) Lacunarity analysis: a general technique for the analysis of spatial patterns. Phys Rev E Stat Phys Plasmas Fluids Relat Interdiscip Topics 53(5): 5461–5468. doi:10.1103/PhysRevE.53.5461

    PubMed  CAS  Google Scholar 

  39. Vapnik V (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  40. Smola AJ, Scholkopf B (1998) A tutorial on support vector regression. NeuroCOLT Tech Rep TR, Royal Holloway College, London

  41. Chen SS, Keller JM, Crownover RM (1993) On the calculation of fractal features from images. IEEE Trans Pattern Anal Mach Intell 15: 1087–1090. doi:10.1109/34.254066

    Article  Google Scholar 

  42. Suckling J, Dance DR, Lewis DJ, Blacker SG (1994) Parenchymal delineation by human and computer observers. In: Gale A, Astley SM, Dance DR, Cairns AY (ed) 2nd International workshop on digital mammography, Excerpta Medica, 1069, England, pp 315–324

  43. Lilliefors H (1967) On the Kolmogorov-Smirnov test for normality with mean and variance unknown. J Am Stat Assoc 62: 399–402. doi:10.2307/2283970

    Article  Google Scholar 

  44. Huang Q, Lorch JR, Dubes RC (1994) Can the fractal dimension of images be measured?. Pattern Recognit 27: 339–349. doi:10.1016/0031-3203(94)90112-0

    Article  Google Scholar 

  45. Petrou M, Sevilla PG (2006) Image processing: dealing with texture. Wiley, New York

    Google Scholar 

  46. Metz CE (1986) ROC methodology in radiological imaging. Invest Radiol 21: 720–733. doi:10.1097/00004424-198609000-00009

    Article  PubMed  CAS  Google Scholar 

  47. Metz CE, Herman BA, Shen J-H (1998) Maximum-likelihood estimation of ROC curves from continuously-distributed data. Stat Med 17: 1033–1053 doi:10.1002/(SICI)1097-0258(19980515)17:9<1033::AID-SIM784>3.0.CO;2-Z

    Article  PubMed  CAS  Google Scholar 

  48. Du G, Yeo TS (2002) A novel lacunarity estimation method applied to SAR image segmentation. IEEE Trans Geosci Remote Sensing 40: 2687–2691

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biomolecular Medicine, Imperial College London, South Kensington, London, SW7 2AZ, UK

    Qi Guo

  2. School of Systems Engineering, University of Reading, Whiteknights, Reading, RG6 6AY, UK

    Qi Guo & Virginie F. Ruiz

  3. Department of Electronics, University of Kent, Canterbury, Kent, CT2 7NT, UK

    Jiaqing Shao

Authors
  1. Qi Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiaqing Shao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Virginie F. Ruiz
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Qi Guo.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Guo, Q., Shao, J. & Ruiz, V.F. Characterization and classification of tumor lesions using computerized fractal-based texture analysis and support vector machines in digital mammograms. Int J CARS 4, 11–25 (2009). https://doi.org/10.1007/s11548-008-0276-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-008-0276-8

Keywords

Search

Navigation