Automatic Evaluation of Mammographic Adequacy and Quality on the Mediolateral Oblique View

  • Ramachandran Chandrasekhar
  • Man Kwok Sze
  • Yianni Attikiouzel


A digitized mammogram is considered to be adequate and of sufficient quality when its extent and appearance, respectively, satisfy certain criteria that enable radiologists to make diagnoses of high specificity and sensitivity. Criteria related to breast positioning, suggested by radiologists, include: inferior extent of the pectoral muscle relative to the level of the nipple; curvature of the anterior pectoral margin; whether the nipple is in profile; and inclusion of all the breast tissue on the mammogram. We present here a systematic approach to automatically determine by computer the adequacy and quality of mammograms. First, landmarks such as the breast border, nipple, and pectoral margin were extracted by automatic algorithms. Compliance with the positioning criteria was then determined from these landmarks. Finally, adequacy of film exposure was assessed from the optical density histogram of the breast region. This approach has been applied to mammograms in the MIAS database. Automatic, computerized evaluation of mammographie adequacy and quality by computer is useful to highlight poor positioning and inadequate exposure, and to alert mammographic radiographers (technicians) to the need for additional exposures or views. It is also an important quality assurance step in any automated analysis of mammo¬grams for computer-assisted diagnosis.


Digital Mammography Pectoral Muscle Breast Region Border Segment Clinical Image Quality 
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.
    M. T. Rickard, E. A. Wilson, A. Ferris, and K. H. Blackett, Mammography Today: Positioning and Quality Control for Radiographers. Sydney, Australia: Central Sydney Breast X-Ray Programme, 1992.Google Scholar
  2. 2.
    G. W. Eklund, G. Cardenosa, and W. Parsons, “Assessing Adequacy of Mammo¬graphie Image Quality,” Radiology, vol. 190, pp. 297–307, Feb. 1994.PubMedGoogle Scholar
  3. 3.
    G. W. Eklund and G. Cardenosa, “The art of mammographie positioning,” The Radiologic Clinics of North America, vol. 30, Jan. 1992.Google Scholar
  4. 4.
    L. W. Bassett, I. A. Hirbawi, N. DeBruhl, and M. K. Hayes, “Mammographie positioning: Evaluation from the view box,” Radiology, vol. 188, pp. 803–806, 1993.PubMedGoogle Scholar
  5. 5.
    S. H. Heywang-Köbrunner, D. D. Dershaw, and I. Schreer, Diagnostic Breast Imag¬ing: Mammography, Sonography, Magnetic Resonance Imaging, and Interventional Procedures. Stuttgart, Germany: Georg Thieme Verlag, 2nd, enlarged and re¬vised ed., 2001.Google Scholar
  6. 6.
    S. H. Taplin, C. M. Rutter, C. Finder, M. T. Mandelson, F. Houn, and E. White, “Screening mammography: Clinical image quality and the risk of interval breast cancer,” American Journal of Roentgenology, vol. 178, pp. 797–803, Apr. 2002.PubMedGoogle Scholar
  7. 7.
    V. F. Andolina, S. Lille, and K. M. Willison, Mammographic Imaging: A Practical Guide. Philadelphia: J B Lippincott Company, 1992.Google Scholar
  8. 8.
    J. Suckling, J. Parker, D. R. Dance, and S. A. et al., “The Mammographic Im¬age Analysis Society Digital Mammogram Database,” in Digital Mammography (A. G. Gale, S. M. Astley, D. R. Dance, and A. Y. Cairns, eds.), ( Amsterdam, The Netherlands ), pp. 375–378, Elsevier Science, 1994.Google Scholar
  9. 9.
    R. Chandrasekhar and Y. Attikiouzel, “Automatic breast border segmentation by background modeling and subtraction,” in IWDM 2000: 5th International Work¬shop on Digital Mammography (M. J. Yaffe, ed.), pp. 560–565, Madison, WI, USA: Medical Physics Publishing, 2001. Proceedings of the Workshop, June 11–14, 2000, Toronto, Canada.Google Scholar
  10. 10.
    R. Chandrasekhar and Y. Attikiouzel, “A Simple Method for Automatically Locat¬ing the Nipple on Mammograms,” IEEE Transactions on Medical Imaging, vol. 16, pp. 483 – 494, Oct. 1997.PubMedCrossRefGoogle Scholar
  11. 11.
    S. M. Kwok, R. Chandrasekhar, and Y. Attikiouzel, “Automatic pectoral mus¬cle segmentation on mammograms by straight line estimation and cliff detection,” in ANZIIS 2001: Proceedings of the Seventh Australian and New Zealand Intel¬ligent Information Systems Conference, (Perth, Australia), pp. 67–72, ARCME, The University of Western Australia, Nov. 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Ramachandran Chandrasekhar
    • 1
  • Man Kwok Sze
    • 1
  • Yianni Attikiouzel
    • 2
  1. 1.Australian Research Centre for Medical Engineering (ARCME)The University of Western AustraliaCrawleyAustralia
  2. 2.Murdoch UniversityMurdochAustralia

Personalised recommendations