Advertisement

Novel Morphological Features for Non-mass-like Breast Lesion Classification on DCE-MRI

  • Mohammad RazaviEmail author
  • Lei Wang
  • Tao Tan
  • Nico Karssemeijer
  • Lars Linsen
  • Udo Frese
  • Horst K. Hahn
  • Gabriel Zachmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10019)

Abstract

For both visual analysis and computer assisted diagnosis systems in breast MRI reading, the delineation and diagnosis of ductal carcinoma in situ (DCIS) is among the most challenging tasks. Recent studies show that kinetic features derived from dynamic contrast enhanced MRI (DCE-MRI) are less effective in discriminating malignant non-masses against benign ones due to their similar kinetic characteristics. Adding shape descriptors can improve the differentiation accuracy. In this work, we propose a set of novel morphological features using the sphere packing technique, aiming to discriminate non-masses based on their shapes. The feature extraction, selection and the classification modules are integrated into a computer-aided diagnosis (CAD) system. The evaluation was performed on a data set of 106 non-masses extracted from 86 patients, which achieved an accuracy of \(90.56\,\%\), precision of \(90.3\,\%\), and area under the receiver operating characteristic (ROC) curve (AUC) of 0.94 for the differentiation of benign and malignant types.

Keywords

Breast Lesion Invasive Lobular Carcinoma Sphere Packing Random Forest Classifier Internal Sphere 
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.

References

  1. 1.
    Jansen, S.A., Shimauchi, A., Zak, L., Fan, X., Karczmar, G.S., Newstead, G.M.: The diverse pathology and kinetics of mass, nonmass, and focus enhancement on MR imaging of the breast. J. MRI 33(6), 1382–1389 (2011)Google Scholar
  2. 2.
    Kuhl, C.K., Schrading, S., Bieling, H.B., Wardelmann, E., Leutner, C.C., Koenig, R., Kuhn, W., Schild, H.H.: MRI for diagnosis of pure ductal carcinoma in situ: a prospective observational study. Lancet 370(9586), 485–492 (2007)CrossRefGoogle Scholar
  3. 3.
    Jansen, S.A., Fan, X., Karczmar, G.S., Abe, H., Schmidt, R.A., Giger, M., Newstead, G.M.: DCEMRI of breast lesions: is kinetic analysis equally effective for both mass and nonmass-like enhancement? Med. Phys. 35(7), 3102–3109 (2008)CrossRefGoogle Scholar
  4. 4.
    Chen, W., Giger, M.L., Newstead, G.M., Bick, U., Jansen, S.A., Li, H., Lan, L.: Computerized assessment of breast lesion malignancy using DCE-MRI: robustness study on two independent clinical datasets from two manufacturers. Acad. Radiol. 17(7), 822–829 (2010)CrossRefGoogle Scholar
  5. 5.
    Hoffmann, S., Shutler, J.D., Lobbes, M., Burgeth, B., Meyer-Bäse, A.: Automated analysis of non-mass-enhancing lesions in breast MRI based on morphological, kinetic, and spatio-temporal moments and joint segmentation-motion compensation technique. EURASIP J. Adv. Sig. Process. 2013(1), 1–10 (2013)CrossRefGoogle Scholar
  6. 6.
    Goto, M., Ito, H., Akazawa, K., Kubota, T., Kizu, O., Yamada, K., Nishimura, T.: Diagnosis of breast tumors by contrast-enhanced MR imaging: comparison between the diagnostic performance of dynamic enhancement patterns and morphologic features. J. Magn. Reson. Imaging 25(1), 104–112 (2007)CrossRefGoogle Scholar
  7. 7.
    Weller, R., Zachmann, G.: Protosphere: a GPU-assisted prototype guided sphere packing algorithm for arbitrary objects. In: ACM SIGGRAPH ASIA, p. 8 (2010)Google Scholar
  8. 8.
    Chen, Z., Sun, S.-K.: A Zernike moment phase-based descriptor for local image representation and matching. IEEE Trans. Image Process. 19(1), 205–219 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Gärtner, B.: Fast and robust smallest enclosing balls. In: Nešetřil, J. (ed.) ESA 1999. LNCS, vol. 1643, pp. 325–338. Springer, Heidelberg (1999)Google Scholar
  10. 10.
    Ali, S., Veltri, R., Epstein, J.A., Christudass, C., Madabhushi, A.: Cell cluster graph for prediction of biochemical recurrence in prostate cancer patients from tissue microarrays. In: SPIE Medical Imaging, p. 86760H. International Society for Optics and Photonics (2013)Google Scholar
  11. 11.
    Botafogo, R.A., Rivlin, E., Shneiderman, B.: Structural analysis of hypertexts: identifying hierarchies and useful metrics. ACM Trans. Inf. Syst. (TOIS) 10(2), 142–180 (1992)CrossRefGoogle Scholar
  12. 12.
    Raidou, R.G., Van Der Heide, U., Dinh, C.V., Ghobadi, G., Kallehauge, J.F., Breeuwer, M., Vilanova, A.: Visual analytics for the exploration of tumor tissue characterization. Comput. Graph. Forum 34, 11–20 (2015). Wiley Online LibraryCrossRefGoogle Scholar
  13. 13.
    Boutin, F., Hascoet, M.: Cluster validity indices for graph partitioning. In: 2004 Proceedings of Eighth International Conference on Information Visualisation, IV 2004, pp. 376–381. IEEE (2004)Google Scholar
  14. 14.
    Ricard, J., Coeurjolly, D., Baskurt, A.: Generalizations of angular radial transform for 2D and 3D shape retrieval. Pattern Recogn. Lett. 26(14), 2174–2186 (2005)CrossRefGoogle Scholar
  15. 15.
    Novotni, M., Klein, R.: Shape retrieval using 3D Zernike descriptors. Comput. Aided Des. 36(11), 1047–1062 (2004)CrossRefGoogle Scholar
  16. 16.
    Calle, M.L., Urrea, V.: Letter to the editor: stability of random forest importance measures. Briefings Bioinform. 12, 86–89 (2010)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Mohammad Razavi
    • 1
    Email author
  • Lei Wang
    • 1
    • 5
  • Tao Tan
    • 2
  • Nico Karssemeijer
    • 2
  • Lars Linsen
    • 3
  • Udo Frese
    • 4
  • Horst K. Hahn
    • 1
  • Gabriel Zachmann
    • 4
  1. 1.Fraunhofer MEVIS - Institute for Medical Image ComputingBremenGermany
  2. 2.Radboud University Medical CenterNijmegenThe Netherlands
  3. 3.Jacobs University BremenBremenGermany
  4. 4.University of BremenBremenGermany
  5. 5.Surpath Medical GmbHWürzburgGermany

Personalised recommendations