Classification of Microcalcification based on wave atom transform

Abstract Mammography is commonly used for early cancer detection in women breast. The presence of microcalcification clusters in the digital mammograms is the significant indication of breast cancer and their nature is not necessarily malignant. It is very difficult task to distinguish between benign and malignant clusters. Computer-Aided Diagnosis (CADx) designed to help phatologists determine the type of microcalcification in a mammogram. Usually, it’s consisting of two steps, feature extraction and classification. In our methodology, we proposed the use of wave atom transform as feature extraction technique and Support Vector Machine (SVM) as classifier. Here the proposed method is compared with wavelet transform. While comparing, our proposed method achieved good classification accuracy. However, some of the previous researches have shown better results than ours.