Combining Deep Learning with Traditional Features for Classification and Segmentation of Pathological Images of Breast Cancer

The automatic classification of pathological images of breast cancer has important clinical value. In order to improve the accuracy and efficiency of cancer detection, we implement two classifications in this paper. (1) Train deep convolutional neural network (CNN) models based on AlexNet and GoogLeNet network structures. (2) Take the idea of transfer learning to complete the training of classification models. We use CNN to extract image features, then select distinguished features to simplify feature set, and combine them with texture features of images. At last, a Support Vector Machine (SVM) is used for feature learning and classification.