Fast Computation of Mutual Information in a Variational Image Registration Approach

Stefan Heldmann; Oliver Mahnke; Daniel Potts; Jan Modersitzki; Bernd Fischer

doi:10.1007/978-3-642-18536-6_92

Fast Computation of Mutual Information in a Variational Image Registration Approach

Stefan Heldmann, Oliver Mahnke, Daniel Potts, Jan Modersitzki, Bernd Fischer

Institute of Mathematics

Abstract

In this paper we present a novel method for computing the Mutual Information of images using recently developed non-equidistant fast Fourier-transform (NFFT) techniques. Standard approaches suffer from the problem that some sort of quantization is needed in order to apply a fast equidistant FFT-technique. For the new method no quantization is necessary which on one hand leads to an improved registration accuracy and on the other hand to a straight forward implementation. The evaluation is done for MR brain registration as well as for synthetic examples.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2004
Editors	Thomas Tolxdorff, Jürgen Braun, Heinz Handels, Alexander Horsch, Hans-Peter Meinzer
Number of pages	5
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.03.2004
Pages	448-452
ISBN (Print)	978-3-540-21059-7
ISBN (Electronic)	978-3-642-18536-6
DOIs	https://doi.org/10.1007/978-3-642-18536-6_92
Publication status	Published - 01.03.2004
Event	Workshop on Bildverarbeitung fur die Medizin 2004 - Berlin, Germany Duration: 29.03.2004 → 30.03.2004

Access to Document

10.1007/978-3-642-18536-6_92

Cite this

Heldmann, S., Mahnke, O., Potts, D., Modersitzki, J., & Fischer, B. (2004). Fast Computation of Mutual Information in a Variational Image Registration Approach. In T. Tolxdorff, J. Braun, H. Handels, A. Horsch, & H.-P. Meinzer (Eds.), Bildverarbeitung für die Medizin 2004 (pp. 448-452). ( Informatik aktuell). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-18536-6_92

Heldmann, Stefan ; Mahnke, Oliver ; Potts, Daniel et al. / Fast Computation of Mutual Information in a Variational Image Registration Approach. Bildverarbeitung für die Medizin 2004. editor / Thomas Tolxdorff ; Jürgen Braun ; Heinz Handels ; Alexander Horsch ; Hans-Peter Meinzer. Berlin, Heidelberg : Springer Berlin Heidelberg, 2004. pp. 448-452 ( Informatik aktuell).

@inproceedings{da9926e4ce594432a2ac9539be169d3f,

title = "Fast Computation of Mutual Information in a Variational Image Registration Approach",

abstract = "In this paper we present a novel method for computing the Mutual Information of images using recently developed non-equidistant fast Fourier-transform (NFFT) techniques. Standard approaches suffer from the problem that some sort of quantization is needed in order to apply a fast equidistant FFT-technique. For the new method no quantization is necessary which on one hand leads to an improved registration accuracy and on the other hand to a straight forward implementation. The evaluation is done for MR brain registration as well as for synthetic examples.",

author = "Stefan Heldmann and Oliver Mahnke and Daniel Potts and Jan Modersitzki and Bernd Fischer",

year = "2004",

month = mar,

day = "1",

doi = "10.1007/978-3-642-18536-6_92",

language = "English",

isbn = "978-3-540-21059-7",

series = " Informatik aktuell",

publisher = "Springer Berlin Heidelberg",

pages = "448--452",

editor = "Thomas Tolxdorff and J{\"u}rgen Braun and Heinz Handels and Alexander Horsch and Hans-Peter Meinzer",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2004",

note = "Workshop on Bildverarbeitung fur die Medizin 2004, BVM 2004 ; Conference date: 29-03-2004 Through 30-03-2004",

}

Heldmann, S, Mahnke, O, Potts, D, Modersitzki, J & Fischer, B 2004, Fast Computation of Mutual Information in a Variational Image Registration Approach. in T Tolxdorff, J Braun, H Handels, A Horsch & H-P Meinzer (eds), Bildverarbeitung für die Medizin 2004. Informatik aktuell, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 448-452, Workshop on Bildverarbeitung fur die Medizin 2004, Berlin, Berlin, Germany, 29.03.04. https://doi.org/10.1007/978-3-642-18536-6_92

Fast Computation of Mutual Information in a Variational Image Registration Approach. / Heldmann, Stefan; Mahnke, Oliver; Potts, Daniel et al.
Bildverarbeitung für die Medizin 2004. ed. / Thomas Tolxdorff; Jürgen Braun; Heinz Handels; Alexander Horsch; Hans-Peter Meinzer. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. p. 448-452 ( Informatik aktuell).

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

TY - GEN

T1 - Fast Computation of Mutual Information in a Variational Image Registration Approach

AU - Heldmann, Stefan

AU - Mahnke, Oliver

AU - Potts, Daniel

AU - Modersitzki, Jan

AU - Fischer, Bernd

PY - 2004/3/1

Y1 - 2004/3/1

N2 - In this paper we present a novel method for computing the Mutual Information of images using recently developed non-equidistant fast Fourier-transform (NFFT) techniques. Standard approaches suffer from the problem that some sort of quantization is needed in order to apply a fast equidistant FFT-technique. For the new method no quantization is necessary which on one hand leads to an improved registration accuracy and on the other hand to a straight forward implementation. The evaluation is done for MR brain registration as well as for synthetic examples.

AB - In this paper we present a novel method for computing the Mutual Information of images using recently developed non-equidistant fast Fourier-transform (NFFT) techniques. Standard approaches suffer from the problem that some sort of quantization is needed in order to apply a fast equidistant FFT-technique. For the new method no quantization is necessary which on one hand leads to an improved registration accuracy and on the other hand to a straight forward implementation. The evaluation is done for MR brain registration as well as for synthetic examples.

U2 - 10.1007/978-3-642-18536-6_92

DO - 10.1007/978-3-642-18536-6_92

M3 - Conference contribution

SN - 978-3-540-21059-7

T3 - Informatik aktuell

SP - 448

EP - 452

BT - Bildverarbeitung für die Medizin 2004

A2 - Tolxdorff, Thomas

A2 - Braun, Jürgen

A2 - Handels, Heinz

A2 - Horsch, Alexander

A2 - Meinzer, Hans-Peter

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - Workshop on Bildverarbeitung fur die Medizin 2004

Y2 - 29 March 2004 through 30 March 2004

ER -

Heldmann S, Mahnke O, Potts D, Modersitzki J, Fischer B. Fast Computation of Mutual Information in a Variational Image Registration Approach. In Tolxdorff T, Braun J, Handels H, Horsch A, Meinzer HP, editors, Bildverarbeitung für die Medizin 2004. Berlin, Heidelberg: Springer Berlin Heidelberg. 2004. p. 448-452. ( Informatik aktuell). doi: 10.1007/978-3-642-18536-6_92

Fast Computation of Mutual Information in a Variational Image Registration Approach

Abstract

Access to Document

Fingerprint

Cite this