Detection algorithm of breast disease based on convolution neural network

In order to improve the accuracy of computer-aided breast disease detection, a breast disease detection algorithm based on convolution neural network is proposed. Firstly, the shallow and deep features of the images are extracted from the convolution neural network, and then fuse them in a weighted way. Secondly, the multi-scale input of the convolution neural network is realized by using the spatial Pyramid pool algorithm. Finally, the algorithm is tested on the Mammographic Image Analysis Society (MIAS) data set. The experimental results show that the average accuracy rate of the breast disease detection algorithm is up to 93.32%. Compared with other breast disease detection algorithms, the breast disease detection algorithm proposed in this paper has higher detection accuracy.