With the development of imaging-guided surgery and radiotherapy, the clinical demand for medical image matching research is stronger and the challenges are even greater. In recent years, deep learning, especially deep convolution neural networks, has made excellent achievements in medical image processing, and the research on medical image matching has developed rapidly. In this paper, the domestic and foreign research progress based on deep learning medical image alignment is summarized according to the classification of technical methods, including the similarity estimation based on optimization strategy, the transformation parameters of direct estimation of medical image alignment, etc. Then it analyses the challenge of the deep learning method in medical image matching and puts forward possible solutions and research directions. Key words: medical image recording, deep learning, CNN, full convolutional network