Breast Cancer Classification Based on Improved Rough Set Theory Feature Selection

Breast cancer is one of the leading causes of death among the women. Mammogram analysis is the most effective method that helps in the early detection of breast cancer. In this paper we have made an attempt to classify the breast tissue based on Statistical features of a mammogram which extracted using simple image processing techniques with rough set theory. The proposed scheme uses texture models to capture the mammographic appearance within the breast. The statistical features extracted are the mean, standard deviation, smoothness, third moment, uniformity and entropy which signify the important texture features of breast tissue. Based on the values of these features of a digital mammogram, we have made an attempt to classify the breast tissue in to three basic categories normal, benign, and malignant given in the data base (mini-MIAS database). This categorization would help a radiologist to detect a normal breast from a cancer affected breast. Rough set theory can be regarded as a new mathematical tool for imperfect data analysis. Rough set based data analysis starts from a data table called a decision table. Each row of a decision table induces a decision rule, which specifies decision (action, results, outcome, etc.). We can know important data rules by using core and reduct which elimination of duplicate rows and elimination of superfluous values of attributes.