A New Mammography Lesion Classification Method Based on Convolutional Neural Network

Breast cancer is a malignant tumor disease that is extremely high incidence among women around the world. And the cause of the disease is still unclear, the key to prevention and treatment of breast cancer is detection, diagnosis and treatment early. Mammography is the first choice for early diagnosis, however, limited experts have difficulty dealing with a large number of mammography images. Therefore, this paper is mainly devoted to the study of intelligent classification of mammography images, and applies the latest image processing method---Convolutional Neural Network (CNN) to study the classification of mammography images. In addition, we propose a new classification method of mammography images, which is to classify the lesions of normal (N), benign (B) and malignant (M) under different gland types.