Deep Learning for Breast Region and Pectoral Muscle Segmentation in Digital Mammography

  • Kaier WangEmail author
  • Nabeel Khan
  • Ariane Chan
  • Jonathan Dunne
  • Ralph Highnam
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11854)


The accurate segmentation of a mammogram into different anatomical regions, such as breast or pectoral muscle, is a critical step in automated breast image analysis. This paper evaluates the performance of u-net deep learning architecture on segmenting breast area and pectoral muscle from digital mammograms and digital breast tomosynthesis. To minimise the image variations due to vendor and modality specifications, Volpara\(^\text {TM}\) algorithm was used to normalise the raw image to a unity representation that is independent of imaging conditions. Four factors and their interactions were investigated for their effects on the performance of u-net segmentation: image normalisation; zero and extrapolated padding techniques for image size standarisation; different contrast between breast and background; and image resolution. By training u-net on 2,000 normalised images, we obtained median dice-similarity coefficients of 0.8879 and 0.9919, respectively for pectoral and breast segmentations from 825 testing images. The model training speed was boosted by using down sampled images without compromising segmentation accuracy. Using normalised breast images by Volpara\(^\text {TM}\) algorithm, u-net was able to perform robust segmentation of breast area and pectoral muscle.


Mammography Pectoral segmentation Breast segmentation U-Net Volpara 


  1. 1.
    Ahn, C.K., Heo, C., Jin, H., Kim, J.H.: A novel deep learning-based approach to high accuracy breast density estimation in digital mammography. In: Armato, S.G., Petrick, N.A. (eds.) Medical Imaging 2017: Computer-Aided Diagnosis (2017)Google Scholar
  2. 2.
    Ariaratnam, N.S., Little, S.T., Whitley, M.A., Ferguson, K.: Digital breast tomosynthesis vacuum assisted biopsy for tomosynthesis-detected sonographically occult lesions. Clin. Imaging 47, 4–8 (2018)CrossRefGoogle Scholar
  3. 3.
    Camilus, K.S., Govindan, V.K., Sathidevi, P.S.: Computer-aided identification of the pectoral muscle in digitized mammograms. J. Digit. Imaging 23(5), 562–580 (2009)CrossRefGoogle Scholar
  4. 4.
    Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). Scholar
  5. 5.
    Chen, Z., Zwiggelaar, R.: Segmentation of the breast region with pectoral muscle removal in mammograms (2010)Google Scholar
  6. 6.
    Ekpo, E.U., McEntee, M.F.: Measurement of breast density with digital breast tomosynthesis—a systematic review. Br. J. Radiol. 87(1043), 20140460 (2014)CrossRefGoogle Scholar
  7. 7.
    Ferrari, R., Rangayyan, R., Desautels, J., Borges, R., Frere, A.: Automatic identification of the pectoral muscle in mammograms. IEEE Trans. Med. Imaging 23(2), 232–245 (2004)CrossRefGoogle Scholar
  8. 8.
    García, S., Luengo, J., Herrera, F.: Data Preprocessing in Data Mining, vol. 72. Springer, Cham (2015). Scholar
  9. 9.
    Highnam, R., Brady, M.: Mammographic Image Analysis. Computational Imaging and Vision. Springer, Netherlands (1999). Scholar
  10. 10.
    Kallenberg, M., et al.: Unsupervised deep learning applied to breast density segmentation and mammographic risk scoring. IEEE Trans. Med. Imaging 35(5), 1322–1331 (2016)CrossRefGoogle Scholar
  11. 11.
    Kwok, S., Chandrasekhar, R., Attikiouzel, Y.: Automatic pectoral muscle segmentation on mammograms by straight line estimation and cliff detection. In: The Seventh Australian and New Zealand Intelligent Information Systems Conference (2001)Google Scholar
  12. 12.
    Li, S., et al.: Computer-aided assessment of breast density: comparison of supervised deep learning and feature-based statistical learning. Phys. Med. Biol. 63(2), 025005 (2018)CrossRefGoogle Scholar
  13. 13.
    Liu, L., Liu, Q., Lu, W.: Pectoral muscle detection in mammograms using local statistical features. J. Digit. Imaging 27(5), 633–641 (2014)CrossRefGoogle Scholar
  14. 14.
    Mohamed, A.A., Berg, W.A., Peng, H., Luo, Y., Jankowitz, R.C., Wu, S.: A deep learning method for classifying mammographic breast density categories. Med. Phys. 45(1), 314–321 (2017)CrossRefGoogle Scholar
  15. 15.
    Mustra, M., Grgic, M.: Robust automatic breast and pectoral muscle segmentation from scanned mammograms. Sig. Process. 93(10), 2817–2827 (2013)CrossRefGoogle Scholar
  16. 16.
    Oliver, A., Llado, X., Torrent, A., Marti, J.: One-shot segmentation of breast, pectoral muscle, and background in digitised mammograms. In: IEEE International Conference on Image Processing (2014)Google Scholar
  17. 17.
    Petersen, K., Chernoff, K., Nielsen, M., Ng, A.: Breast density scoring with multiscale denoising autoencoders. In: MICCAI Workshop on Sparsity Techniques in Medical Imaging (2012)Google Scholar
  18. 18.
    Raba, D., Oliver, A., Martí, J., Peracaula, M., Espunya, J.: Breast segmentation with pectoral muscle suppression on digital mammograms. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds.) IbPRIA 2005. LNCS, vol. 3523, pp. 471–478. Springer, Heidelberg (2005). Scholar
  19. 19.
    Ribli, D., Horváth, A., Unger, Z., Pollner, P., Csabai, I.: Detecting and classifying lesions in mammograms with deep learning. Sci. Rep. 8(1), 4165 (2018)Google Scholar
  20. 20.
    Rodriguez-Ruiz, A., et al.: Pectoral muscle segmentation in breast tomosynthesis with deep learning. In: Mori, K., Petrick, N. (eds.) Medical Imaging 2018: Computer-Aided Diagnosis (2018)Google Scholar
  21. 21.
    Ronneberger, O.: U-net: Convolutional networks for biomedical image segmentation. Accessed 05 Jul 2019
  22. 22.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  23. 23.
    Smith, A.P., Niklason, L., Ren, B., Wu, T., Ruth, C., Jing, Z.: Lesion visibility in low dose tomosynthesis. In: Astley, S.M., Brady, M., Rose, C., Zwiggelaar, R. (eds.) IWDM 2006. LNCS, vol. 4046, pp. 160–166. Springer, Heidelberg (2006). Scholar
  24. 24.
    Spak, D., Plaxco, J., Santiago, L., Dryden, M., Dogan, B.: BI-RADs fifth edition: a summary of changes. Diagn. Intervent. Imaging 98(3), 179–190 (2017)CrossRefGoogle Scholar
  25. 25.
    Suckling, J.H., et al.: Mammographic image analysis society (MIAS) database v1.21 (2015)Google Scholar
  26. 26.
    Suzuki, K.: Overview of deep learning in medical imaging. Radiol. Phys. Technol. 10(3), 257–273 (2017)CrossRefGoogle Scholar
  27. 27.
    Tabik, S., Peralta, D., Herrera-Poyatos, A., Herrera, F.: A snapshot of image pre-processing for convolutional neural networks: case study of MNIST. Int. J. Comput. Intell. Syst. 10(1), 555 (2017)CrossRefGoogle Scholar
  28. 28.
    Tzikopoulos, S.D., Mavroforakis, M.E., Georgiou, H.V., Dimitropoulos, N., Theodoridis, S.: A fully automated scheme for mammographic segmentation and classification based on breast density and asymmetry. Comput. Methods Programs Biomed. 102(1), 47–63 (2011)CrossRefGoogle Scholar
  29. 29.
    Voulodimos, A., Doulamis, N., Doulamis, A., Protopapadakis, E.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 2018, 1–13 (2018)Google Scholar
  30. 30.
    Williams, D.J., Shah, M.: A fast algorithm for active contours and curvature estimation. CVGIP: Image Underst. 55(1), 14–26 (1992)CrossRefGoogle Scholar
  31. 31.
    Wirth, M., Stapinski, A.: Segmentation of the breast region in mammograms using snakes. In: IEEE First Canadian Conference on Computer and Robot Vision (2004)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Kaier Wang
    • 1
    Email author
  • Nabeel Khan
    • 1
  • Ariane Chan
    • 1
  • Jonathan Dunne
    • 1
  • Ralph Highnam
    • 1
  1. 1.Volpara Health Technologies LtdWellingtonNew Zealand

Personalised recommendations