Deep learning-based medical image registration

Medical image registration aims to establish anatomical correspondences between images of different subjects or the same subject acquired at different time points or between images of different imaging modalities. It is a critical technique used in many clinical applications, such as population analysis, longitudinal studies, multi-modal image fusion and image-guided intervention. In recent years, deep learning, especially deep convolutional neural networks (CNNs), has shown great success in medical image registration. In this chapter, we introduce the recent development of deep learning-based medical image registration methods. Conventional and machine learning-based registration methods will also be introduced briefly.