Fast Curvature Based Registration of MR-mammography Images

Bernd Fischer, Jan Modersitzki


We introduce a new non-linear registration model based on a curvature type regularizer. We show that affine linear transformations belong to the kernel of this regularizer. Consequently, an additional global registration is superfluous. Furthermore, we present an implementation of the new scheme based on the numerical solution of the underlying Euler-Lagrange equations. The real DCT is the backbone of our implementation and leads to a stable and fast backslashmathcalObackslashleft( nbackslashtext log n backslashright)algorithm, where n denotes the number of voxels. We demonstrate the advantages of the new technique for synthetic data sets. Moreover, first convincing results for the registration of MR-mammography images are presented.
Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2002
EditorsMonika Meiler, Dietmar Saupe, Frithjof Kruggel, Heinz Handels, Thomas M. Lehmann
Number of pages4
Place of PublicationBerlin, Heidelberg
PublisherSpringer Berlin Heidelberg
Publication date01.03.2002
ISBN (Print)978-3-540-43225-8
ISBN (Electronic)978-3-642-55983-9
Publication statusPublished - 01.03.2002
EventWorkshop on Bildverarbeitung fur die Medizin 2002 - Leipzig, Germany
Duration: 10.03.200212.03.2002


Dive into the research topics of 'Fast Curvature Based Registration of MR-mammography Images'. Together they form a unique fingerprint.

Cite this