X-ray mammography has been widely applied to breast cancer diagnosis due to its simplicity and reliability. However, X-ray will do harm to the health of patients or even cause cancer. Low dose mammography by reducing the tube current is an effective method to reduce radiation dose and has attracted more and more interests. In this paper, we implemented a method to improve the image quality of low dose mammography via deep learning. It is based on a convolutional neural network (CNN) and focuses on reducing the noise in low dose mammography. After training, it can obtain a high quality image from a low dose mammography image. This method is validated with experimental data sets obtained from The Cancer Imaging Archive (TCIA). It will promote the application of state-of-art deep learning technique in the field of low dose mammography.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.