Computerized analysis of mammographic parenchymal patterns for breast cancer risk assessment: Feature selection

Our purpose in this study was to identify computer-extracted, mammographic parenchymal patterns that are associated with breast cancer risk. We extrac ted 14 features from the central breast region on digitized mammograms to c haracterize the mammographic parenchymal patterns of women at different ris k levels. Two different approaches were employed to relate these mammograph ic features to breast cancer risk. In one approach, the features were used to distinguish mammographic patterns seen in low-risk women from those who inherited a mutated form of the BRCA1/BRCA2 gene, which confers a very high risk of developing breast cancer. In another approach, the features were r elated to risk as determined from existing clinical models (Gail and Claus models), which use well-known epidemiological factors such as a woman's age , her family history of breast cancer, reproductive history, etc. Stepwise linear discriminant analysis was employed to identify features that were us eful in differentiating between "low-risk" women and BRCA1/BRCA2-mutation c arriers. Stepwise linear regression analysis was employed to identify usefu l features in predicting the risk, as estimated from the call and Claus mod els. Similar computer-extracted mammographic features were identified in th e two approaches. Results show that women at high risk tend to have dense b reasts and their mammographic patterns tend to be coarse and low in contras t. (C) 2000 American Association of Physicists in Medicine. [S0094-2405(00) 01001-4].