Analysis and Interpretation of Frequency Domain Texture Based Features for Mammographic Masses

Abstract

Breast cancer is one of the major causes of death among women. Small cluster of masses appearing as collection of white spots on mammograms show an early warning of breast cancer. At present, mammography associated with clinical breast examination and breast self-examination is the only effective and viable method for mass breast screening. An improvement of early diagnostic techniques is critical for women’s quality of life. Early detection performed on X-ray mammography is the key to improve breast cancer prognosis. In order to improve radiologist’s diagnostic performance, several computeraided diagnosis (CAD) systems have been developed to improve the detection of primary signatures of this disease masses. Most of the techniques used in the computerized analysis of mammographic masses use shape features on the segmented regions of masses extracted from the digitized mammograms. Since mammographic images usually suffer from poorly defined features, the extraction of shape features based on a segmentation process may not accurately represent microcalcifications. We are developing automated-detection and analysis schemes of mammographic masses. The purpose of this study is to improve the previous schemes on the mass detection and analysis. Computer-aided classification of benign and malignant masses on mammograms is attempted in this study by computing gradient-based and texture-based features. Features computed based on gray-level value of pixels are used to evaluate the effectiveness of textural information possessed by mass regions in comparison with the textural information present in mass margins.