Breast Cancer Histopathological Image Classification using Deep Learning

The paper employs deep learning to classify breast cancer histopathological image into benign and malignant categories. The Inception v1 convolutional neural network is mainly adopted. Spatial Pyramid Pooling and special global average pooling are added to the network to ensure that images can be imported in the original aspect ratio format. The experimental results show that the convolutional neural network performs well in breast cancer image classification, and the Global Average Pooling effect is slightly better than the Spatial Pyramid Pooling.