Analysis of density features surrounding mammographic abnormalities

In clinic, surrounding density of breast abnormalities is an important cue for radiologists to distinguish between benign and malignant abnormalities on mammogram. It may also be an important feature to be used in computer-aided diagnosis (CAD) system. The purpose of our work is to analyze the density distribution surrounding benign or malignant mass. The cases used in this study are selected from the Digital Database for Screening Mammography (DDSM) provided by the University of South Florida. For each case, the mass boundaries marked by experienced radiologists are used and 30 3-pixel-wide bands, one outside another, surrounding each mass are considered. A few density features including the average gray level and the distribution skewness of the gray levels on every surrounding band were calculated. For every feature in each corresponding band, average values were calculated for 10 benign cases and 10 malignant cases, respectively. The preliminary analysis results show that the intensities surrounding benign masses tend to be higher than those surrounding malignant masses. They also show that the standard deviation of intensities surrounding benign masses tend to be larger than those surrounding malignant masses. Similar analysis was also carried out with mass boundaries automatically identified by computer and the results corroborate the analysis with mass boundaries marked by radiologists.