Computer-aided detection of clustered microcalcifications on digital mammograms

  • R. M. Nishikawa
  • M. L. Giger
  • K. Doi
  • C. J. Vyborny
  • R. A. Schmidt
Medical Physics and Imaging

Abstract

A computer-aided diagnosis scheme to assist radiologists in detecting clustered microcalcifications from mammograms is being developed. Starting with a digital mammogram, the scheme consists of three steps. First, the image is filtered so that the signal-to-noise ratio of microcalcifications is increased by suppression of the normal background structure of the breast. Secondly, potential microcalcifications are extracted from the filtered image with a series of three different techniques: a global thresholding based on the grey-level histogram of the full filtered image, an erosion operator for eliminating very small signals, and a local adaptive grey-level thresholding. Thirdly, some false-positive signals are eliminated by means of a texture analysis technique, and a non-linear clustering algorithm is then used for grouping the remaining signals. With this method, the scheme can detect approximately 85% of true clusters, with an average of two false clusters detected per image.

Keywords

Automated detection Computer-aided diagnosis Digital imaging Mammography Microcalcifications 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Andersson, I., Aspegren, K., Janzon, L., Landberg, T., Lindholm, K., Linell, F., Ljungberg, O., Jonas, R., andSigfusson, B. (1988): ‘Mammographic screening and mortality from breast cancer: the Malmo mammographic screening trial’,Br. Med. J.,297, pp. 943–948CrossRefGoogle Scholar
  2. Astley, S. M., Taylor, C. J., Boggis, C. R. M., Wison, M., andEllison, T. P. (1990): ‘Automated detection of abnormalities on screening mammograms’,Radiology,177(P), p. 288 (abstract)Google Scholar
  3. Baines, C. J., Miller, A. B., Wall, C., McFarlane, D. V., Simor, I. S., Jong, R., Shapiro, B. J., Audet, L., Petitclerc, M., Ouimet-Oliva, D., Ladouceur, J., Hebert, G., Minuk, T., Hardy, G., andStanding, H. K. (1986): ‘Sensitivity and specificity of first screen mammography in the Canadian national breast screening study: A preliminary report from five centers,’ibid.,160, pp. 295–298Google Scholar
  4. Bird, R. E. (1989): ‘Professional quality assurance for mammography screening programs’,ibid.,177, p. 587Google Scholar
  5. Chan, H.-P., Doi, K., Galhotra, S., Vyborny, C. J., MacMahon, H., andJokich, P. M. (1987): ‘Image feature analysis and computer-aided diagnosis in digital radiography. 1. Automated detection of microcalcifications in mammography’,Med. Phys.,14, pp. 538–548CrossRefGoogle Scholar
  6. Chan, H.-P., Doi, K., Vyborny, C. J., Lam, K. L., andSchmidt, R. A. (1988): ‘Computer-aided detection of microcalcifications in mammograms: Methodology and preliminary clinical study’,Invest. Radiol.,23, pp. 664–671Google Scholar
  7. Chan, H.-P., Doi, K., Vyborny, C. J., Schmidt, R. A., Metz, C., Lam, K., Ogura, T., Wu, Y., andMacMahon, H. (1990): ‘Improvement in radiologists' detection of clustered micro-calcifications on mammograms: the potential of computer-aided diagnosis’,ibid.,25, pp. 1102–1110CrossRefGoogle Scholar
  8. Davies, D. H., andDance, D. R. (1990): ‘Automatic computer detection of clustered calcifications in digital mammograms’,Phys. Med. Biol.,35, pp. 1111–1118CrossRefGoogle Scholar
  9. Fam, B. W., Olson, S. L., Winter, P. F., andScholz, F. J. (1988): ‘Algorithm for the detection of fine clustered calcifications on film mammograms’,Radiology,169, pp. 333–337Google Scholar
  10. Giger, M. L., Yin, F.-F., Doi, K., Metz, C. E., Schmidt, R. A. andVyborny, C. J. (1990): ‘Investigation of methods for the computerized detection and analysis of mammographic masses’,Proc. SPIE,1233, pp. 183–184Google Scholar
  11. Giger, M. L., Nishikawa, R. M., Doi, K., Yin, F.-F., Vyborny, C. J., Schmidt, R. A., Metz, C. E., Wu, Y., MacMahon, H., andYoshimura, H. (1991): ‘Development of a ‘smart’ workstation for use in mammography’,ibid.,1445, pp. 101–103Google Scholar
  12. Grimaud, M., Muller, S., andMeyer, F. (1990): ‘Automated detection of microcalcifications in mammograms’,Radiol.,177(P) p. 288 (abstract)Google Scholar
  13. Hermann, G., Janus, C., Schwartz, I. S., Papatestas, A., Hermann, D. G., andRabinowitz, J. G. (1988): ‘Occult malignant breast lesions in 114 patients: Relationship to age and the presence of microcalcifications,’ibid.,169, pp. 321–324Google Scholar
  14. Karssemeijer, N., andvan Earning (1991): ‘A stochastic method for automated detection of microcalcifications in digital mammograms’in Colchester, A. C. F., andHawkes, D. J. (Eds.): ‘Information processing in medical imaging’ (Springer-Verlag, New York) pp. 227–238CrossRefGoogle Scholar
  15. Katsuragawa, S., Doi, K., andMacMahon, H. (1988): ‘Image feature analysis and computer-aided diagnosis in digital radiography: Detection and characterization of interstitial lung disease in digital chest radiographs’,Med. Phys.,15, pp. 311–319CrossRefGoogle Scholar
  16. Magnin, I. E., El Alaoui, M., andBremond, A. (1989): ‘Automatic microcalcifications pattern recognition from X-ray mammographies,’Proc. SPIE,1137, pp. 170–175Google Scholar
  17. Metz, C. E. (1986): ‘ROC methodology in radiologic imaging’,Invest. Radiol.,21, pp. 720–733CrossRefGoogle Scholar
  18. Nishikawa, R. M., Doi, K., Giger, M. L., Vyborny, C. J., andSchmidt, R. A. (1990a): ‘Use of morphological filters in the computerized detection of microcalcifications in digitized mammograms’,M. Phys.,17, p. 524 (abstract)Google Scholar
  19. Nishikawa, R. M., Doi, K., Giger, M. L., Vyborny, C. J., andSchmidt, R. A. (1990b): ‘Automated detection of microcalcifications in mammograms: New feature-extraction technique using morphological filters’,Radiol.,177(P), p. 288 (abstract)Google Scholar
  20. Shapiro, S., Venet, W., Strax, P. H., Venet, L., andRoeset, R. (1982): ‘Ten to fourteen-year effect of screening on breast cancer mortality’,JNCI,69, pp. 349–355Google Scholar
  21. Sickles, E. A. (1986): ‘Mammographic features of 300 consecutive nonpalpable breast cancers’,Am. J. Roentgenol.,146, pp. 661–663Google Scholar
  22. Swets, J. A., Getty, D. J., Pickett, R. M., D'Orsi, C. J., Seltzer, S. E., andMcNeil, B. J. (1991): ‘Enhancing and evaluating diagnostic accuracy’,Med. Decision Making,11, pp. 9–18Google Scholar
  23. Tabar, L., Gad, A., Holmberg, L. H., Ljungquist, U., Fagerberg, C. J. G., Baldetorp, L., Grontoft, O., Lundstrom, B., Manson, J. C., Eklund, G., Day, N. E., andPettersson, F. (1985): ‘Reduction in mortality from breast cancer after mass screening with mammography. Randomized trial from the Breast Screening Working Groups of the Swedish National Board of Health & Welfare’,Lancet,1, pp. 829–832CrossRefGoogle Scholar
  24. Yin, F.-F., Giger, M. L., Doi, K., Metz, C. E., Vyborny, C. J., andSchmidt, R. A. (1991): ‘Computerized detection of masses in digital mammograms: Analysis of bilateral-subtraction images’,Med. Phys.,18, pp. 955–963CrossRefGoogle Scholar

Copyright information

© IFMBE 1995

Authors and Affiliations

  • R. M. Nishikawa
    • 1
  • M. L. Giger
    • 1
  • K. Doi
    • 1
  • C. J. Vyborny
    • 1
  • R. A. Schmidt
    • 1
  1. 1.Kurt Rossmann Laboratories for Radiologic Image Research, Department of RadiologyThe University of ChicagoChicagoUSA

Personalised recommendations