While deep learning has become a methodology of choice in many areas, relatively few deep-learning-based image registration algorithms have been proposed. One reason for this is lack of ground-truth and the large variability of plausible deformations that can align corresponding anatomies. Therefore, the problem is much less constrained than for example image classification or segmentation.
mlVIRNET: Improved Deep Learning Registration Using a Coarse to Fine Approach to Capture all Levels of Motion
A. Hering and S. Heldmann
Bildverarbeitung für die Medizin 2020:175.