A breast cancer pathological image classification method based on depth feature aggregation

The invention discloses a breast cancer pathological image classification method based on depth feature aggregation, and belongs to the field of medical image classification. The method comprises thesteps of constructing a breast cancer pathology image data set, obtaining original pathology image data and label information, and performing data enhancement on an original pathology image; Traininga depth feature extraction module by means of a random gradient descent method, and optimizing parameters of the depth feature extraction module; A feature aggregation module is trained by adopting depth features obtained by a depth feature extraction module, and depth feature aggregation codes of a training set are calculated; and training a pre-classification module by using the depth feature aggregation coding of the training set. In the method test, a test set sample is input into a depth feature extraction module, a feature aggregation module and a pre-classification module which are connected in series to obtain