Classification of Normal and Abnormal Patterns in Digital Mammograms for Diagnosis of Breast Cancer

Abstract

the last few years, computerized tool play important role in detection of breast cancer. This paper proposes a method for breast cancer diagnosis in digital mammograms using GLCM (Grey Level Co#occurrence Matrix) features. In this paper CAD (Computer Aided Diagnosis) system developed using GLCM feature and neural network. Mammography is an efficient tool for early detection of breast cancer. Computerized methods have recently show great tool in providing radiologists with second opinion about breast cancer diagnosis. Five GLCM features for mammogram images are extracted. Mammogram image is classified into normal image and cancer image. The effectiveness of this paper is examined on DDSM (Digital Database for Screening Mammography) database using classification accuracy, sensitivity and specificity. The overall accuracy can be improved by most relevant GLCM features, which is selected by feature selection algorithm.