The Automated Learning of Deep Features for Breast Mass Classification from Mammograms

  • Neeraj DhungelEmail author
  • Gustavo Carneiro
  • Andrew P. Bradley
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9901)


The classification of breast masses from mammograms into benign or malignant has been commonly addressed with machine learning classifiers that use as input a large set of hand-crafted features, usually based on general geometrical and texture information. In this paper, we propose a novel deep learning method that automatically learns features based directly on the optmisation of breast mass classification from mammograms, where we target an improved classification performance compared to the approach described above. The novelty of our approach lies in the two-step training process that involves a pre-training based on the learning of a regressor that estimates the values of a large set of hand-crafted features, followed by a fine-tuning stage that learns the breast mass classifier. Using the publicly available INbreast dataset, we show that the proposed method produces better classification results, compared with the machine learning model using hand-crafted features and with deep learning method trained directly for the classification stage without the pre-training stage. We also show that the proposed method produces the current state-of-the-art breast mass classification results for the INbreast dataset. Finally, we integrate the proposed classifier into a fully automated breast mass detection and segmentation, which shows promising results.


Deep learning Breast mass classification Mammograms 


  1. 1.
    Giger, M.L., Karssemeijer, N., Schnabel, J.A.: Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer. Ann. Rev. Biomed. Eng. 15, 327–357 (2013)CrossRefGoogle Scholar
  2. 2.
    Fenton, J.J., Taplin, S.H., Carney, P.A., et al.: Influence of computer-aided detection on performance of screening mammography. N. Engl. J. Med. 356(14), 1399–1409 (2007)CrossRefGoogle Scholar
  3. 3.
    Elmore, J.G., Jackson, S.L., Abraham, L., et al.: Variability in interpretive performance at screening mammography and radiologists characteristics associated with accuracy1. Radiology 253(3), 641–651 (2009)CrossRefGoogle Scholar
  4. 4.
    Varela, C., Timp, S., Karssemeijer, N.: Use of border information in the classification of mammographic masses. Phys. Med. Biol. 51(2), 425 (2006)CrossRefGoogle Scholar
  5. 5.
    Domingues, I., Sales, E., Cardoso, J., Pereira, W.: Inbreast-database masses characterization. In: XXIII CBEB (2012)Google Scholar
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, vol. 1 (2012)Google Scholar
  7. 7.
    LeCun, Y., Bengio, Y.: Convolutional networks for images, speech, and time series. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks. MIT Press, Massachusetts (1995). 3361Google Scholar
  8. 8.
    Dhungel, N., Carneiro, G., Bradley, A.: Automated mass detection in mammograms using cascaded deep learning and random forests. In: DICTA, November 2015Google Scholar
  9. 9.
    Dhungel, N., Carneiro, G., Bradley, A.P.: Deep learning and structured prediction for the segmentation of mass in mammograms. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 605–612. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24553-9_74 CrossRefGoogle Scholar
  10. 10.
    Moreira, I.C., Amaral, I., Domingues, I., et al.: Inbreast: toward a full-field digital mammographic database. Acad. Radiol. 19(2), 236–248 (2012)CrossRefGoogle Scholar
  11. 11.
    Ball, J.E., Bruce, L.M.: Digital mammographic computer aided diagnosis (cad) using adaptive level set segmentation. In: EMBS 2007. IEEE (2007)Google Scholar
  12. 12.
    Farabet, C., Couprie, C., Najman, L., et al.: Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1915 (2013)CrossRefGoogle Scholar
  13. 13.
    Carneiro, G., Nascimento, J., Bradley, A.P.: Unregistered multiview mammogram analysis with pre-trained deep learning models. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 652–660. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24574-4_78 CrossRefGoogle Scholar
  14. 14.
    Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: ICML (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Neeraj Dhungel
    • 1
    Email author
  • Gustavo Carneiro
    • 1
  • Andrew P. Bradley
    • 2
  1. 1.ACVT, School of Computer ScienceThe University of AdelaideAdelaideAustralia
  2. 2.School of ITEEThe University of QueenslandBrisbaneAustralia

Personalised recommendations