Advertisement

LUT-QNE: Look-Up-Table Quantum Noise Equalization in Digital Mammograms

  • Alessandro Bria
  • Claudio Marrocco
  • Jan-Jurre Mordang
  • Nico Karssemeijer
  • Mario Molinara
  • Francesco Tortorella
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9699)

Abstract

Quantum noise is a signal-dependent, Poisson-distributed noise and the dominant noise source in digital mammography. Quantum noise removal or equalization has been shown to be an important step in the automatic detection of microcalcifications. However, it is often limited by the difficulty of robustly estimating the noise parameters on the images. In this study, a nonparametric image intensity transformation method that equalizes quantum noise in digital mammograms is described. A simple Look-Up-Table for Quantum Noise Equalization (LUT-QNE) is determined based on the assumption that noise properties do not vary significantly across the images. This method was evaluated on a dataset of 252 raw digital mammograms by comparing noise statistics before and after applying LUT-QNE. Performance was also tested as a preprocessing step in two microcalcification detection schemes. Results show that the proposed method statistically significantly improves microcalcification detection performance.

Keywords

Digital mammography Quantum noise Nonparametric Noise equalization Microcalcification detection 

References

  1. 1.
    Ekpo, E.U., Egbe, N.O., Egom, A.E., McEntee, M.F.: Mammographic breast density: comparison across women with conclusive and inconclusive mammography reports. J. Med. Imaging Radiat. Sci. 1, 55–59 (2015)Google Scholar
  2. 2.
    Eadie, L.H., Taylor, P., Gibson, A.P.: A systematic review of computer-assisted diagnosis in diagnostic cancer imaging. Eur. J. Radiol. 81(1), e70–e76 (2012)CrossRefGoogle Scholar
  3. 3.
    Romualdo, L., Vieira, M., Schiabel, H., Mascarenhas, N., Borges, L.: Mammographic image denoising and enhancement using the anscombe transformation, adaptive wiener filtering, and the modulation transfer function. J. Digit. Imaging 26(2), 183–197 (2013)CrossRefGoogle Scholar
  4. 4.
    McLoughlin, K.J., Bones, P.J., Karssemeijer, N.: Noise equalization for detection of microcalcification clusters in direct digital mammogram images. IEEE Trans. Med. Imaging 23(3), 313–320 (2004)CrossRefGoogle Scholar
  5. 5.
    Veldkamp, W.J.H., Karssemeijer, N.: Normalization of local contrast in mammograms. IEEE Trans. Med. Imaging 19(7), 731–738 (2000)CrossRefGoogle Scholar
  6. 6.
    van Schie, G., Karssemeijer, N.: Detection of microcalcifications using a nonuniform noise model. In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 378–384. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  7. 7.
    Tromans, C.E., Cocker, M.R., Brady, S.M.: Quantification and normalization of x-ray mammograms. Phys. Med. Biol. 57(20), 6519 (2012)CrossRefGoogle Scholar
  8. 8.
    Bria, A., Marrocco, C., Molinara, M., Tortorella, F.: Detecting clusters of microcalcifications with a cascade-based approach. In: Maidment, A.D.A., Bakic, P.R., Gavenonis, S. (eds.) IWDM 2012. LNCS, vol. 7361, pp. 111–118. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Dengler, J., Behrens, S., Desaga, J.: Segmentation of microcalcifications in mammograms. IEEE Trans. Med. Imaging 12, 634–642 (1993)CrossRefGoogle Scholar
  10. 10.
    El Naqa, I., Yang, W.M.N., Galatsanos, Y.N.P., Nishikawa, R.M.: A support vector machine approach for detection of microcalcifications. IEEE Trans. Med. Imaging 21(12), 1552–1563 (2002)CrossRefGoogle Scholar
  11. 11.
    Yousef, W.A.: Assessing classifiers in terms of the partial area under the ROC curve. Comput. Stat. Data Anal. 64, 51–70 (2013)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Bria, A., Karssemeijer, N., Tortorella, F.: Learning from unbalanced data: a cascade-based approach for detecting clustered microcalcifications. Med. Image Anal. 18(2), 241–252 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Alessandro Bria
    • 1
  • Claudio Marrocco
    • 1
  • Jan-Jurre Mordang
    • 2
  • Nico Karssemeijer
    • 2
  • Mario Molinara
    • 1
  • Francesco Tortorella
    • 1
  1. 1.DIEIUniversity of Cassino and Southern LatiumCassinoItaly
  2. 2.DIAGRadboud University Nijmegen Medical CentreNijmegenThe Netherlands

Personalised recommendations