Malignant tumor classification method based on multi-view-angle information cooperation

The breast benign and malignant tumor classification method based on multi-view-angle information cooperation comprises the following steps: step 1) medical image preprocessing: performing data enhancement processing on images of four view angles of a breast molybdenum target X ray; step 2) constructing a multi-view convolution network sub-model for the image of each view; and step 3) constructinga multi-view information collaborative convolutional neural network model, unifying the output of the sub-models of the four views to the same neuron classification layer, and finally inputting a Sigmoid function to obtain a classification result; adding penalty function for false negative cases, and giving greater penalty to reduce the occurrence of false negative conditions; and step 4) breasttumor benign and malignant classification: inputting a to-be-detected breast molybdenum target X-ray image into the multi-view information collaborative convolutional neural network model constructedin the step 3), and perform