Fast and accurate optimisation for registration with little learning
Documentation: See corresponding publication
Source: https://github.com/multimodallearning/convexAdam
Jupyter: please create your own custom kernel for https://max-jhub.desy.de
Module: module load maxwell mdlma/convexAdam
Description:
Deformable image registration is an important step in medical image analysis. It enables an automatic labelling of anatomical structures using atlas-based segmentation, motion compensation and multi-modal fusion. The use of discrete optimisation approaches has recently attracted a lot attention for mainly two reasons. First, they are able to find an approximate global optimum of the registration cost function and can avoid false local optima. Second, they do not require a derivative of the similarity metric, which increases their flexibility. However, the necessary quantisation of the deformation space causes a very large number of degrees of freedom with a high computational complexity. To deal with this, previous work has focussed on parametric transformation models. In this work, we present an efficient non-parametric discrete registration method using a filter-based similarity cost aggregation and a decomposition of similarity and regularisation term into two convex optimisation steps. This approach enables non-parametric registration with billions of degrees of freedom with computation times of less than a minute. We apply our method to two different common medical image registration tasks, intra-patient 4D-CT lung motion estimation and inter-subject MRI brain registration for segmentation propagation. We show improvements on current state-of-the-art performance both in terms of accuracy and computation time.
Citation:
Siebert, H., Hansen, L., Heinrich, M.P. (2022),
Heinrich, M.P., Papież, B.W., Schnabel, J.A., Handels, H. (2014), Non-parametric Discrete Registration with Convex Optimisation