Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

© 2020 Elsevier Inc. All rights reserved. An in-depth introduction and thorough discussion of current approaches for medical image registration with sliding motion is presented in this chapter. Several strategies for locally-adaptive regularization in past, current and future work are described including related research from optical flow in computer vision. In particular recent advances to the Demons framework and discrete optimization strategies are presented that do no require any specific segmentation masks and led to substantial improvements over baseline approaches. A reduction target registration error with respect to expert landmarks and visually plausible sliding in the computed motion fields can be reached using these methods. The great clinical impact of a suitable handling of motion discontinuities is highlighted and future research directions towards advanced graph-based edge priors through supervised learning are presented to the reader.

Original publication





Book title

Handbook of Medical Image Computing and Computer Assisted Intervention

Publication Date



293 - 318