In recent years, deep learning technology has made remarkable progress in many computer vision tasks, and more and more researchers have tried to apply it to the field of medical image processing, such as segmentation of anatomical structures in high-throughput medical images (CT, MRI), which can improve the efficiency of image reading for doctors. For specific deep learning tasks in medical applications, the training of deep neural networks needs a large amount of labeled data. But in the medical field, it is awfully hard to obtain large amounts, even unlabeled data from a separate medical institution. Moreover, due to the difference in medical equipment and acquisition protocols, the data from different medical institutions are quite different. The large heterogeneity of data makes it difficult to obtain reliable results on the data of a certain medical institution, with the model trained with data from other medical institutions. In addition, the distribution of disease stage in a dataset is often very uneven, which may also reduce the reliability of the model. In order to reduce the impact of data heterogeneity and improve the generalization ability of the model, domain adaptation and multi-site learning gradually started to be used. Domain adaptation as a research hotspot in transfer learning, is intended to transfer knowledge learned from the source domain to unlabeled target domain data; and federated learning on non-independent and identically distributed (non-iid) data aim to improve the robustness of the model by learning a common representation on multiple data sets. This paper investigates, analyzes, and summarizes domain adaptation, multi-site learning, federated learning on non-iid data and datasets in recent years, and provides references to related research.