Medical image classification is a medical image that uses a classification algorithm to identify which type of disease the image belongs to, or whether it is a benign disease or a malignant disease. As a hot spot in the field of computer vision research, image classification provides a good and convenient way for medical image recognition and processing and reduces the burden of medical work. Medical image classification is also an important basis for disease detection, disease recognition and human posture estimation. This article introduces the current research status of deep learning in medical image classification and recognition, related deep learning models for classification, data sets and model evaluation standards, current problems and future development trends of medical image classification.