Multimodal Classification of Breast Masses in Mammography and MRI Using Unimodal Feature Selection and Decision Fusion

  • Jan M. Lesniak
  • Guido van Schie
  • Christine Tanner
  • Bram Platel
  • Henkjan Huisman
  • Nico Karssemeijer
  • Gabor Székely
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7361)

Abstract

In this work, a classifier combination approach for computer aided diagnosis (CADx) of breast mass lesions in mammography (MG) and magnetic resonance imaging (MRI) is investigated, using a database with 278 and 243 findings in MG resp. MRI including 98 multimodal (MM) lesion annotations. For each modality, feature selection was performed separately with linear Support Vector Machines (SVM). Using nonlinear SVMs, calibrated unimodal malignancy estimates were obtained and fused to a multimodal (MM) estimate by averaging. Evaluating the area under the receiver operating characteristic curve (AUC), feature selection raised AUC from 0.68, 0.69 and 0.72 for MG, MRI and MM to 0.76, 0.73 and 0.81 with a significant improvement for MM (P=0.018). Multimodal classification offered increased performance compared to MG and MRI (P=0.181 and P=0.087). In conclusion, unimodal feature selection significantly increased multimodal classification performance and can provide a useful tool for generating joint CADx scores in the multimodal setting.

Keywords

Support Vector Machine Feature Selection Breast Masse Decision Fusion Decision Score 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Kuhl, C.K., Kuhn, W., Schild, H.: Management of women at high risk for breast cancer: new imaging beyond mammography. The Breast 14(6), 480–486 (2005)CrossRefGoogle Scholar
  2. 2.
    Horsch, K., Giger, M.L., Vyborny, C.J., Lan, L., Mendelson, E.B., Hendrick, R.E.: Classification of breast lesions with multimodality computer-aided diagnosis: observer study results on an independent clinical data set. Radiology 240(2), 357 (2006)CrossRefGoogle Scholar
  3. 3.
    Yuan, Y., Giger, M.L., Li, H., Bhooshan, N., Sennett, C.A.: Multimodality Computer-Aided Breast Cancer Diagnosis with FFDM and DCE-MRI. Academic Radiology 17(9), 1158–1167 (2010)CrossRefGoogle Scholar
  4. 4.
    Constantinos, S.P., Pattichis, M.S., Micheli-Tzanakou, E.: Medical imaging fusion applications: An overview. In: Conference Record of the Thirty-Fifth Asilomar Conference on Signals, Systems and Computers 2001, vol. 2, pp. 1263–1267. IEEE (2001)Google Scholar
  5. 5.
    Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)CrossRefGoogle Scholar
  6. 6.
    Bhooshan, N., Giger, M.L., Drukker, K., Yuan, Y., Li, H., McCann, S., Newstead, G., Sennett, C.: Performance of Triple-Modality CADx on Breast Cancer Diagnostic Classification. In: Martí, J., Oliver, A., Freixenet, J., Martí, R. (eds.) IWDM 2010. LNCS, vol. 6136, pp. 9–14. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  7. 7.
    Ng, A.Y.: Feature selection, l 1 vs. l 2 regularization, and rotational invariance. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 78. ACM (2004)Google Scholar
  8. 8.
    Weston, J., Mukherjee, S., Chapelle, O., Pontil, M., Poggio, T., Vapnik, V.: Feature selection for svms. Advances in Neural Information Processing Systems, 668–674 (2001)Google Scholar
  9. 9.
    Chen, Y.-W., Lin, C.-J.: Combining svms with various feature selection strategies. In: Guyon, I., Nikravesh, M., Gunn, S., Zadeh, L. (eds.) Feature Extraction. Studies in Fuzziness and Soft Computing, vol. 207, pp. 315–324. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Hupse, R., Karssemeijer, N.: Use of Normal Tissue Context in Computer-Aided Detection of Masses in Mammograms. IEEE Transactions on Medical Imaging 28(12), 2033–2041 (2009)CrossRefGoogle Scholar
  11. 11.
    Platel, B., Huisman, H., Laue, H., Mus, R., Mann, R., Hahn, H., Karssemeijer, N.: Computerized characterization of breast lesions using dual-temporal resolution dynamic contrast-enhanced mr images. In: Workshop on Breast Image Analysi in conjunction with the 14th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2011 (2011)Google Scholar
  12. 12.
    Veltman, J., Stoutjesdijk, M., Mann, R., Huisman, H.J., Barentsz, J.O., Blickman, J.G., Boetes, C.: Contrast-enhanced magnetic resonance imaging of the breast: the value of pharmacokinetic parameters derived from fast dynamic imaging during initial enhancement in classifying lesions. European Radiology 18(6), 1123–1133 (2008)CrossRefGoogle Scholar
  13. 13.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: A library for large linear classification. The Journal of Machine Learning Research 9, 1871–1874 (2008)MATHGoogle Scholar
  14. 14.
    Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST) 2(3), 27 (2011)Google Scholar
  15. 15.
    Robin, X., Turck, N., Hainard, A., Tiberti, N., Lisacek, F., Sanchez, J.C., Muller, M.: Proc: an open-source package for r and s+ to analyze and compare roc curves. BMC Bioinformatics 12(1), 77 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Jan M. Lesniak
    • 1
  • Guido van Schie
    • 2
  • Christine Tanner
    • 1
  • Bram Platel
    • 2
  • Henkjan Huisman
    • 2
  • Nico Karssemeijer
    • 2
  • Gabor Székely
    • 1
  1. 1.Computer Vision LaboratoryEidgenössische Technische Hochschule ZürichZürichSwitzerland
  2. 2.Department of RadiologyRadboud University Nijmegen Medical CentreNijmegenThe Netherlands

Personalised recommendations