Abstract
The authors have developed a method for the quantification of breast texture by using different algorithms to classify mammograms into the four patterns described by Wolfe (1976) (N1, P1, P2 and Dy). The computerized scheme employs craniocaudal views of conventional screen-film mammograms, which are digitized by a laser scanner. The authors used discriminant analysis to select among different feature-extraction techniques, including Fourier transform, local-contrast analysis, and grey-level distribution and quantification. The method has been evaluated on 117 clinical mammograms previously classified by five radiologists as to mammographic breast parenchymal patterns (MBPPS). The results show differences in agreement among radiologists and computer classification, depending on the Wolfe pattern: excellent for Dy ( kappa =0.77), good for P2 ( kappa =0.52) and N1 ( kappa =0.52) and poor for P1 ( kappa =0.22). The authors' quantitative texture measure as calculated from digital mammograms may be valuable to radiologists in their assessment of MBPP and therefore useful in establishing an index of risk for developing breast carcinoma.