Asymmetry Recognition of Mammogram Images Based on Convolutional Neural Network

Mammography is the first process to acquire breast imaging data. Approved radiologists screen the mammogram images for detecting suspicious lesions, e.g., mass, calcification, asymmetry. However, image screening is time-consuming and is a subjective decision-making process. In this paper, we propose an asymmetry recognition scheme with various convolutional neural network (CNN) architectures. The proposed scheme not only determines whether a pair of mammogram images is asymmetry, but it indicates that which image asymmetry occurs in.