Mammography Classification Based on Convolutional Neural Network

Abstract

Limited by various conditions, the features of mammography images are difficult to extract, so it is hard to classify them. The paper proposed a method based on deep learning method to classify benign and malignant mammography images. The convolutional neural network concludes four convolution layers, four pool layers, and two full-connection layers, and a Softmax layer. The paper designed a new network architecture to improve the traditional one. As a result, we have done an experiment on the DDSM database. Compared with other classification methods, it shows that the method proposed in this paper is more effective than other methods.