MIT
MGH
HMS
LCLN

LABORATORY FOR COMPUTATIONAL LONGITUDINAL NEUROIMAGING (LCLN)

Rotate to view desktop version ...

Image Registration

registration
Robust Registration
The registration of images is a task that is at the core of many applications in medical image computing and computer vision. In computational neuroimaging where the automated segmentation of brain structures is frequently used to quantify change, a highly accurate registration is necessary for motion correction of images taken in the same session, or across time in longitudinal studies where changes in the images can be expected.
In [1] we present a method based on robust statistics to accurately register images in the presence of differences, such as jaw movement, differential MR distortions and true anatomical change (e.g. see the image above for a time series for tumor treatment assessment). The approach guarantees inverse consistency (symmetry), can deal with different intensity scales and automatically estimates a sensitivity parameter to detect outlier regions in the images. The resulting registrations demonstrate superior accuracy relative to state-of-the-art registration tools such as FLIRT (in FSL) or the coregistration tool in SPM. The software is freely available as part of the FreeSurfer package.
Non-linear Registration
The choice of a reference image typically influences the results of deformable image registration, thereby making it asymmetric. This is a consequence of a spatially non-uniform weighting in the cost function integral that leads to general registration inaccuracy. In [2], we address the root of the problem: the non-uniformity of the cost function integral. We introduce a new quasi-volume-preserving constraint that allows for volume change only in areas with well-matching image intensities, and show that such a constraint puts a bound on the error arising from spatial non-uniformity.
Aligning a pair of images in a mid-space is a common approach to ensuring that deformable image registration is symmetric - that it does not depend on the arbitrary ordering of the input images. The results are, however, generally dependent on the choice of the mid-space. In [3] we make implicit-atlas-based pairwise registration independent of the mid-space, thereby eliminating the need for anti-drift constraints.
Selected Publications (full list):
Links:
clustrmaps.com
Martin Reuter - MIT - Cambridge, MA, USA - EMail: reu...@mit.edu
Last modified 14.01.2022 -- [xhtml] -- [css] -- [welcome]