Wavelet based features of circular scan lines for mammographic mass classification

Breast cancer is reported as the second most deadly cancer in the world on which public awareness has been increasing during the last few decades. Early detection can play an effective role in prevention and the most reliable detection technology is mammography. At the early stages of breast cancer, the clinical signs are very mild and vary in appearance, making diagnosis difficult even for specialists. Therefore, automatic reading of medical images becomes highly desirable. This paper aims to develop an automated system for mass classification in digital mammograms. Mini - MIAS database is used to obtain mammogram images. A novel approach for feature extraction is proposed which exploits the wavelet features of radial and circular scan lines drawn over the region of interest (ROI). The discriminating ability of these features are evaluated using three classifiers such as Neural Network (Scaled conjugate back propagation), Bayesian and Support Vector Machine (SVM). The experimental results show that SVM outperforms with an accuracy of 85.96%.