A discretize-optimize approach for LDDMM registration. (English) Zbl 07274050

Polzin, Thomas; Niethammer, Marc; Vialard, François-Xavier; Modersitzki, Jan

Pennec, Xavier (ed.) et al., Riemannian geometric statistics in medical image analysis. Amsterdam: Elsevier/Academic Press (ISBN 978-0-12-814725-2/pbk; 978-0-12-814726-9/ebook). The Elsevier and Miccai Society Book Series, 479-532 (2020).

Summary: The goal of image registration is to establish spatial correspondences between images. Image registration is a challenging but important task in image analysis. In particular, in medical image analysis image registration is a key tool to compare patient data in a common space, to allow comparisons between pre-, inter-, or post-intervention images, or to fuse data acquired from different and complementary imaging devices such as positron emission tomography (PET), computed tomography (CT), or magnetic resonance imaging (MRI).
Image registration is of course not limited to medical imaging, but is important for a wide range of applications; for example, it is used in astronomy, biology/genetics, cartography, computer vision, and surveillance. Consequently, there exists a vast number of approaches and techniques.
For the entire collection see [Zbl 1428.92004].

MSC:

92C55	Biomedical imaging and signal processing
58D05	Groups of diffeomorphisms and homeomorphisms as manifolds

Keywords:

image registration; PET; CT; MRI; large deformation diffeomorphic metric mapping registration