Comparative study on the classification methods for breast cancer diagnosis

Digital mammography is one of the most widely used approaches for breast cancer diagnosis. Many researchers have demonstrated the superiority of machine learning methods in breast cancer diagnosis using different mammography databases. Since these methods often have different pros and cons, which may confuse doctors and researchers, an elaborate comparison and examination among them is urgently needed for practical breast cancer diagnosis. In this study, we conducted a comprehensive comparative study of the state-of-the-art machine learning methods that are promising in breast cancer diagnosis. For this purpose we analyze the largest mammography diagnosis database: Digital Database for Screening Mammography (DDSM). We considered various approaches for feature extraction including principal component analysis (PCA), nonnegative matrix factorization (NMF), spatial-temporal discriminant analysis (STDA) and those for classification including linear discriminant analysis (LDA), random forests (RaF), k-nearest neighbors (kNN), as well as deep learning methods including convolutional neural networks (CNN) and stacked sparse autoencoder (SSAE). This paper can serve as a guideline and useful clues for doctors who are going to select machine learning methods for their breast cancer computer-aided diagnosis (CAD) systems as well for researchers interested in developing more reliable and efficient methods for breast cancer diagnosis