Automatic Detection of Pectoral Muscle with the Maximum Intensity Change Algorithm

  • Zhiyong Zhang
  • Joan Lu
  • Yau Jim Yip
Conference paper


The accurate segmentation of pectoral muscle in mammograms is necessary to detect breast abnormalities in computer-aided diagnosis (CAD) of breast cancer. Based on morphological characteristics of pectoral muscle, a corner detector and the Maximum Intensity Change (MIC) algorithm were proposed in this research to detect the edge of pectoral muscle. The initial result shows that the proposed approach detected pectoral muscle with high quality.


Pectoral Muscle Candidate Point Corner Detector Breast Area Wavelet Filter Bank 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Suri, J.S. and R.M. Rangayyan, Recent Advances in Breast Imaging, Mammography, and Computer-Aided Diagnosis of Breast Cancer. 2006: SPIE Publications.Google Scholar
  2. 2.
    Yapa, R.D. and K. Harada, Breast Skin-Line Estimation and Breast Segmentation in Mammograms using Fast-Marching Method. International Journal of Biological, Biomedical and Medical Sciences, 2008. 3(1): p. 54-62.Google Scholar
  3. 3.
    Wirth, M., D. Nikitenko, and J. Lyon, Segmentation of the Breast Region in Mammograms using a Rule-Based Fuzzy Reasoning Algorithm. ICGST-GVIP, 2005. 5(2).Google Scholar
  4. 4.
    Karssemeijer, N., Automated Classification of Parenchymal Patterns in Mammograms. Physics in Medicine and Biology, 1998. 43(2): p. 365–378.CrossRefGoogle Scholar
  5. 5.
    Ferrari, R.J., et al., Automatic Identification of the Pectoral Muscle in Mammograms. IEEE Transactions on Medical Imaging, 2004. 23(2): p. 232-245.CrossRefGoogle Scholar
  6. 6.
    Kwok, S.M., et al., Automatic pectoral muscle segmentation on mediolateral oblique view mammograms. IEEE Transactions on Medical Imaging, 2004. 23(9): p. 1129-1140.CrossRefMathSciNetGoogle Scholar
  7. 7.
    Mustra, M., J. Bozek, and M. Grgic, Breast Border Extraction and Pectoral Muscle Detection Using WAVELET Decomposition. IEEE, 2009: p. 1428-1435.Google Scholar
  8. 8.
    Raba, D., et al. Breast Segmentation with Pectoral Muscle Suppression on Digital Mammograms. in Proceedings of the 2nd Iberian Conference (IbPRIA 2005). 2005. Estoril, Portugal: Springer Berlin / Heidelberg.Google Scholar
  9. 9.
    Ma, F., et al., Two graph theory based methods for identifying the pectoral muscle in mammograms. Pattern Recognition, 2007. 40: 2592–2602.CrossRefGoogle Scholar
  10. 10.
    Zhou, C., et al., Computerized image analysis: Texture-field orientation method for pectoral muscle identification on MLO-view mammograms. Medical Physics, 2010. 37(5): p. 2289-2299.CrossRefGoogle Scholar
  11. 11.
    Ferrari, R.J., et al., Segmentation of Mammograms: Identification of the Skin – air Boundary, Pectoral Muscle, and Fibroglandular Disc, in Proceedings of the 5th International Workshop on Digital Mammography. 2000: Toronto, Canada. p. 573–579.Google Scholar
  12. 12.
    Zhang, Z., J. Lu, and Y.J. Yip, Automatic Segmentation for Breast Skin-line, in Proceeding of the 10th IEEE International Conference on Computer and Information Technology. 2010, IEEE Computer Society: Bradford, West Yorkshire, UK. p. 1599-1604.Google Scholar
  13. 13.
    Zhang, Z., J. Lu, and Y.J. Yip. Pectoral Muscle Detection. in the 16th International Conference on Automation and Computing (ICAC’10). 2010. University of Birmingham, Birmingham, UK.Google Scholar
  14. 14.
    Ma, W.Y. and B.S. Manjunath, EdgeFlow: a technique for boundary detection and image segmentation. IEEE Trans. Image Processing, 2000. 9(8): p. 1375-1388.MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Suckling, J., et al., The Mammographic Image Analysis Society Digital Mammogram Database. Exerpta Medica. International Congress Series, 1994. 1069: p. 375-378.Google Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  1. 1.University of HuddersfieldHuddersfieldUK

Personalised recommendations