AUTOMATED-ANALYSIS OF MAMMOGRAPHIC DENSITIES AND BREAST-CARCINOMA RISK

BACKGROUND, There is considerable evidence that one of the strongest r isk factors for breast carcinoma can be assessed from the mammographic appearance of the breast. However, the magnitude of the risk factor a nd the reliability of the prediction depend on the method of classific ation. Subjective classification requires specialized observer trainin g and suffers from inter- and intraobserver variability. Furthermore, the categoric scales make it difficult to distinguish small difference s in mammographic appearance. To address these limitations, automated analysis techniques that characterize mammographic density on a contin uous scale have been considered, but as yet, these have been evaluated only for their ability to reproduce subjective classifications of mam mographic parenchyma. METHODS, In this study, using a nested case-cont rol design, the authors evaluated the direct association between breas t carcinoma risk and quantitative image features derived from automate d analysis of digitized film mammograms. Two parameters one describing the distribution of breast tissue density as reflected by brightness of the mammogram (regional skewness) and the other characterizing text ure (fractal dimension), were calculated for images from 708 subjects identified from the Canadian National Breast Screening Study. RESULTS, These parameters were evaluated for their ability to distinguish case s (those women who developed breast carcinoma) from controls. It was f ound that both the skewness and fractal parameters were significantly related to risk of developing breast carcinoma. CONCLUSIONS, Although the relative risk estimates were moderate (typically greater than or e qual to 2.0) and less than those from subjective classification or for an interactive computer method the authors have previously described, they are comparable to other risk factors for the disease. The observ er independence and reproducibility of the automated methods may facil itate their more widespread use. (C) 1997 American Cancer Society.