AdaBoost-based multiple SVM-RFE for classification of mammograms in DDSM

Digital mammography is one of the most promising options to diagnose breast cancer which is the most common cancer in women. However, it has weaknesses in excessive unnecessary biopsy referrals that enfeeble its effectiveness due to difficulty in distinguishing actual cancer lesions from benign abnormalities. To overcome this issue, computer aided diagnosis (CADx) using machine learning techniques have been studied worldwide. Since this is a classification problem and the number of features obtainable from a mammogram image is theoretically infinite, CADx can be improved by introducing feature selection techniques that is suitable for mammograms. In this paper, we propose a new ensemble feature selection method based on a recently developed multiple support vector machine recursive feature elimination (MSVM-RFE). We also conduct experiments on actual digital mammograms publicly available and find that our proposed method performs competitively with other leading feature selection schemes.