Journal of Computer Aided Diagnosis of Medical Images
Online ISSN : 1347-9245
ISSN-L : 1347-9245
Volume 3, Issue 3
Displaying 1-1 of 1 articles from this issue
  • Ryohei NAKAYAMA, Yoshikazu UCHIYAMA, Isamu HATSUKADE, Koji YAMAMOTO, R ...
    1999Volume 3Issue 3 Pages 17-23
    Published: 1999
    Released on J-STAGE: October 08, 2004
    JOURNAL FREE ACCESS
    In this paper a new classification method of clustered microcalcifications by using the weighted wavelet transform technique in digitized mammograms is introduced. The new method uses three types of indicators of malignancy, i.e., (1) the standard deviation of the densities of individual microcalcifications within a cluster, (2) the coefficient of variation of their sizes within a cluster, and (3) the circularity of a cluster. The method was applied to the evaluation of malignancy of 35 microcalcification clusters taken as somewhat difficult cases from Breastpia Namba Hospital's patient files by an experienced mammographer. The results of the discriminant analysis using these indicators showed 95.24% of sensitivity and 78.57% of specificity.
    Download PDF (1646K)
feedback
Top