Journal of Digital Imaging

, Volume 27, Issue 1, pp 145–151 | Cite as

A Vector Machine Formulation with Application to the Computer-Aided Diagnosis of Breast Cancer from DCE-MRI Screening Examinations

  • Jacob E. D. Levman
  • Ellen Warner
  • Petrina Causer
  • Anne L. Martel


This study investigates the use of a proposed vector machine formulation with application to dynamic contrast-enhanced magnetic resonance imaging examinations in the context of the computer-aided diagnosis of breast cancer. This paper describes a method for generating feature measurements that characterize a lesion’s vascular heterogeneity as well as a supervised learning formulation that represents an improvement over the conventional support vector machine in this application. Spatially varying signal-intensity measures were extracted from the examinations using principal components analysis and the machine learning technique known as the support vector machine (SVM) was used to classify the results. An alternative vector machine formulation was found to improve on the results produced by the established SVM in randomized bootstrap validation trials, yielding a receiver-operating characteristic curve area of 0.82 which represents a statistically significant improvement over the SVM technique in this application.


Breast Cancer Detection Computer-Aided Diagnosis Machine Learning Support Vector Machine Receiver-Operating Characteristic Curve Analysis Magnetic Resonance Imaging 



We would like to thank Elizabeth Ramsay for her assistance in image acquisition. The MRI data was acquired using funding from the Canadian Breast Cancer Research Alliance. The authors would like to thank the Canadian Breast Cancer Foundation and the Canadian Institute for Health Research for contributing to the funding of this study.


  1. 1.
    Ford S, et al: Genetic heterogeneity and penetrance analysis of the BRCA1 and BRCA2 genes in breast cancer families. Am Journal Hum Genet 62:676–689, 1998CrossRefGoogle Scholar
  2. 2.
    Curry SJ: Fulfilling the potential of cancer prevention and early detection. National Academies Press, Washington DC, USA, 2003Google Scholar
  3. 3.
    Warner E, et al: Surveillance of BRCA1 and BRCA2 mutation carriers with magnetic resonance imaging, ultrasound, mammography, and clinical breast examination. J Am Med Assoc 292:1317–1325, 2004CrossRefGoogle Scholar
  4. 4.
    Warner E, et al: Systematic review: using magnetic resonance imaging to screen women at high risk for breast cancer. Ann Intern Med 148(9):671–679, 2008PubMedCrossRefGoogle Scholar
  5. 5.
    Saslow D, et al: American Cancer Society guidelines for breast screening with mri as an adjunct to mammography. Cancer J Clin 57:75–89, 2007CrossRefGoogle Scholar
  6. 6.
    Nattkemper TW, et al: Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methods. Artif Intell Med 34:129–139, 2005PubMedCrossRefGoogle Scholar
  7. 7.
    Levman J, Leung T, Causer P, Plewes D, Martel AL: Classification of dynamic contrast-enhanced magnetic resonance breast lesions by support vector machines. IEEE Tran Med Imag 27(5):688–696, 2008CrossRefGoogle Scholar
  8. 8.
    Levman J, Martel AL: Computer-aided diagnosis of breast cancer from magnetic resonance imaging examinations by custom radial basis function vector machine. IEEE Proceedings of the Engineering in Medicine and Biology Society, Buenos Aires, Argentina, 2010Google Scholar
  9. 9.
    Efron B, et al: An introduction to the bootstrap. Chapman & Hall, New York, 1994Google Scholar
  10. 10.
    Eng J: Receiver operating characteristic analysis: a primer. Acad Radiol 12(7):909–916, 2005PubMedCrossRefGoogle Scholar
  11. 11.
    Twellmann T, et al: Model-free visualization of suspicious lesions in breast MRI based on supervised and unsupervised learning. Eng Appl Artif Intel 21(2):129–140, 2008CrossRefGoogle Scholar
  12. 12.
    Lucht R, Knopp M, Brix G: Classification of signal-time curves from dynamic MR mammography by neural networks. Magn Reson Imaging 19(1):51–57, 2001PubMedCrossRefGoogle Scholar
  13. 13.
    Vomweg T, et al: Improved artificial neural networks in prediction of malignancy of lesions in contrast-enhanced MR-mammography. Med Phys 30(9):2350, 2003PubMedCrossRefGoogle Scholar
  14. 14.
    Karahaliou A, et al: Assessing heterogeneity of lesion enhancement kinetics in dynamic contrast-enhanced MRI for breast cancer diagnosis. BJR 83:296–309, 2010PubMedCrossRefGoogle Scholar
  15. 15.
    Karahaliou A, et al: Quantifying heterogeneity of lesion uptake in dynamic contrast enhanced MRI for breast cancer diagnosis. 4th International Conference on Imaging Technologies in Biomedical Sciences, Milos, Greece, 2007Google Scholar
  16. 16.
    Preim U, Glaßer S, Preim B, Fischbach F, Ricke J: Computer-aided diagnosis in breast DCE-MRI—quantification of the heterogeneity of breast lesions. EJR 81(7):1532–1538, 2012CrossRefGoogle Scholar
  17. 17.
    Song C, Smith M, Huang Y, Jeraj R, Fain S: Heterogeneity of vascular permeability in breast lesions with dynamic contrast enhanced MRI. Proceedings of the 17th International Symposium for Magnetic Resonance in Medicine, 2009.Google Scholar
  18. 18.
    Mussurakis S, Gibbs P, Horsman A: Peripheral enhancement and spatial contrast uptake heterogeneity of primary breast tumours: quantitative assessment with dynamic MRI. J. Comput Assist Tomogr 22(1):35–46, 1998PubMedCrossRefGoogle Scholar
  19. 19.
    Greenman RL, et al: Bilateral imaging using separate interleaved 3D volumes and dynamically switched multiple receive coil arrays. Magn Reson Med 39:108–115, 1998PubMedCrossRefGoogle Scholar
  20. 20.
    Causer P, et al: MR imaging—guided breast localization system with medial or lateral access. Radiology 240(2):369–379, 2006PubMedCrossRefGoogle Scholar
  21. 21.
    Martel AL, et al: Evaluating an optical-flow-based registration algorithm for contrast-enhanced magnetic resonance imaging of the breast. Phys Med Biol 52(13):3803–3816, 2007PubMedCrossRefGoogle Scholar
  22. 22.
    Vapnik VN: The nature of statistical learning theory. Springer, New York, NY, 2000CrossRefGoogle Scholar
  23. 23.
    LIBSVM. Available at∼cjlin/libsvm/. Accessed Jan. 25, 2009.
  24. 24.
    Raudys SJ, Jain AK: Small sample size effects in statistical pattern recognition: recommendations for practitioners. IEEE T Pattern Anal 13(3):252–264, 1991CrossRefGoogle Scholar
  25. 25.
    Levman J, Martel AL: A margin sharpness measurement for the diagnosis of breast cancer from magnetic resonance imaging examinations. Acad Radiol 18(12):1577–1581, 2011PubMedCrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2013

Authors and Affiliations

  • Jacob E. D. Levman
    • 1
  • Ellen Warner
    • 2
  • Petrina Causer
    • 3
  • Anne L. Martel
    • 4
  1. 1.Institute of Biomedical Engineering, Department of Engineering Science, Old Road Campus Research BuildingUniversity of OxfordOxfordUK
  2. 2.Division of Medical Oncology, Department of MedicineSunnybrook Health Sciences CentreTorontoCanada
  3. 3.Medical Imaging DepartmentNorth York General HospitalTorontoCanada
  4. 4.Department of Medical Biophysics, Sunnybrook Health Sciences CentreUniversity of TorontoTorontoCanada

Personalised recommendations