Fast Curvature Based Registration of MR-mammography Images

Bernd Fischer; Jan Modersitzki

doi:10.1007/978-3-642-55983-9_32

Fast Curvature Based Registration of MR-mammography Images

Institute of Mathematics

Abstract

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 language	English
Title of host publication	Bildverarbeitung für die Medizin 2002
Editors	Monika Meiler, Dietmar Saupe, Frithjof Kruggel, Heinz Handels, Thomas M. Lehmann
Number of pages	4
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.03.2002
Pages	139-142
ISBN (Print)	978-3-540-43225-8
ISBN (Electronic)	978-3-642-55983-9
DOIs	https://doi.org/10.1007/978-3-642-55983-9_32
Publication status	Published - 01.03.2002
Event	Workshop on Bildverarbeitung fur die Medizin 2002 - Leipzig, Germany Duration: 10.03.2002 → 12.03.2002

Access to Document

10.1007/978-3-642-55983-9_32

http://www.mic.uni-luebeck.de/uploads/tx_wapublications/2002-BVM-FM.pdf

Cite this

@inproceedings{ed716a32c69a42b781faca52b629cb3a,

title = "Fast Curvature Based Registration of MR-mammography Images",

abstract = "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.",

author = "Bernd Fischer and Jan Modersitzki",

year = "2002",

month = mar,

day = "1",

doi = "10.1007/978-3-642-55983-9_32",

language = "English",

isbn = "978-3-540-43225-8",

series = " Informatik aktuell",

publisher = "Springer Berlin Heidelberg",

pages = "139--142",

editor = "Monika Meiler and Dietmar Saupe and Frithjof Kruggel and Heinz Handels and Lehmann, {Thomas M.}",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2002",

note = "Workshop on Bildverarbeitung fur die Medizin 2002 ; Conference date: 10-03-2002 Through 12-03-2002",

}

Fischer, B & Modersitzki, J 2002, Fast Curvature Based Registration of MR-mammography Images. in M Meiler, D Saupe, F Kruggel, H Handels & TM Lehmann (eds), Bildverarbeitung für die Medizin 2002. Informatik aktuell, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 139-142, Workshop on Bildverarbeitung fur die Medizin 2002, Leipzig, Saxony, Germany, 10.03.02. https://doi.org/10.1007/978-3-642-55983-9_32

Fast Curvature Based Registration of MR-mammography Images. / Fischer, Bernd; Modersitzki, Jan.

Bildverarbeitung für die Medizin 2002. ed. / Monika Meiler; Dietmar Saupe; Frithjof Kruggel; Heinz Handels; Thomas M. Lehmann. Berlin, Heidelberg : Springer Berlin Heidelberg, 2002. p. 139-142 ( Informatik aktuell).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Fast Curvature Based Registration of MR-mammography Images

AU - Fischer, Bernd

AU - Modersitzki, Jan

PY - 2002/3/1

Y1 - 2002/3/1

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-55983-9_32

DO - 10.1007/978-3-642-55983-9_32

M3 - Conference contribution

SN - 978-3-540-43225-8

T3 - Informatik aktuell

SP - 139

EP - 142

BT - Bildverarbeitung für die Medizin 2002

A2 - Meiler, Monika

A2 - Saupe, Dietmar

A2 - Kruggel, Frithjof

A2 - Handels, Heinz

A2 - Lehmann, Thomas M.

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - Workshop on Bildverarbeitung fur die Medizin 2002

Y2 - 10 March 2002 through 12 March 2002

ER -

Fast Curvature Based Registration of MR-mammography Images

Abstract

Access to Document

Fingerprint

Cite this