Automated breast cancer detection in mammography using ensemble classifier and feature weighting algorithms

Breast cancer exhibits one of the highest incidence and mortality rates among all cancers affecting women. The early detection of breast cancer reduces mortality and is crucial for prolonging life expectancy. Although mammography is the most often used screening technique in clinical practice, previous studies reviewing mammograms diagnosed by radiologists have commonly revealed false negatives and false positives. Ongoing advances in machine learning techniques have triggered new motivation for the development of computer-aided diagnosis (CAD) systems, which could be applied to assist radiologists in improving final diagnostic accuracy. In this study, an automated methodology for detecting breast cancer in mammography images is proposed based on an ensemble classifier and feature weighting algorithms. First, a novel region extraction approach is proposed to constrain the search area for suspicious breast lesions and an original pectoral removal method is proposed to avoid interference when identifying a region of interest (ROI). In addition, an effective segmentation strategy is developed to automatically identify ROIs whose textural and morphological features are then fused and weighted to generate new feature vectors using a feature weighting algorithm. Finally, an ensemble classifier model is designed using k-nearest neighbor (KNN), bagging, and eigenvalue classification (EigenClass) to determine whether a mammogram contains normal, benign, or malignant tumors based on a majority voting rule. A series of experiments was conducted using the Digital Database for Screening Mammography (DDSM) and Mammographic Image Analysis Society (MIAS) datasets, the results of which demonstrated the proposed scheme outperformed comparable algorithms.