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

• Published in: Medical physics (Lancaster) 2000-01, Vol.27 (1), p.4-12
• Main Authors: Huo, Zhimin, Giger, Maryellen L., Wolverton, Dulcy E., Zhong, Weiming, Cumming, Shelly, Olopade, Olufunmilayo I.
• Format: Article
• Language: English
• Subjects: Biomedical modeling; Biophysical Phenomena; Biophysics; BRCA2 Protein; breast cancer risk; Breast Neoplasms - diagnostic imaging; Breast Neoplasms - genetics; cancer; computerized classification; Computers; Discriminant Analysis; Diseases; feature extraction; Female; gene mutation; Genes, BRCA1; Genes, Tumor Suppressor; genetics; Humans; Image analysis; linear discriminant analysis; Linear regression; linear regression analysis; mammographic parenchyma; Mammography; Mammography - methods; medical image processing; Models, Biological; Mutation; Neoplasm Proteins - genetics; Physicists; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Regression Analysis; Risk Factors; statistical analysis; Subcellular structure and processes; Transcription Factors - genetics
• ISSN: 0094-2405; 2473-4209
• DOI: 10.1118/1.598851

Our purpose in this study was to identify computer-extracted, mammographic parenchymal patterns that are associated with breast cancer risk. We extracted 14 features from the central breast region on digitized mammograms to characterize the mammographic parenchymal patterns of women at different risk levels. Two different approaches were employed to relate these mammographic 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 related 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 useful in differentiating between “low-risk” women and BRCA1/BRCA2-mutation carriers. Stepwise linear regression analysis was employed to identify useful features in predicting the risk, as estimated from the Gail and Claus models. Similar computer-extracted mammographic features were identified in the two approaches. Results show that women at high risk tend to have dense breasts and their mammographic patterns tend to be coarse and low in contrast.