Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

Nils Papenberg; Janine Olesch; Thomas Lange; Peter M. Schlag; Bernd Fischer

doi:10.1007/978-3-540-93860-6_25

Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

Nils Papenberg, Janine Olesch, Thomas Lange, Peter M. Schlag, Bernd Fischer

Abstract

The incorporation of additional user knowledge into a nonrigid registration process is a promising topic in modern registration schemes. The combination of intensity based registration and some interactively chosen landmark pairs is a major approach in this direction. There exist different possibilities to incorporate landmark pairs into a variational non-parametric registration framework. As the interactive localization of point landmarks is always prone to errors, a demand for precise landmark matching is bound to fail. Here, the treatment of the distances of corresponding landmarks as penalties within a constrained optimization problem offers the possibility to control the quality of the matching of each landmark pair individually. More precisely, we introduce inequality constraints, which allow for a sphere-like tolerance around each landmark. We illustrate the performance of this new approach for artificial 2D images as well as for the challenging registration of preoperative CT data to intra-operative 3D ultrasound data of the liver.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2009
Editors	Hans-Peter Meinzer, Thomas Martin Deserno, Heinz Handels, Thomas Tolxdorff
Number of pages	5
Place of Publication	Berlin, Heidelberg
Publisher	Springer Berlin Heidelberg
Publication date	01.03.2009
Pages	122-126
ISBN (Print)	978-3-540-93859-0
ISBN (Electronic)	978-3-540-93860-6
DOIs	https://doi.org/10.1007/978-3-540-93860-6_25
Publication status	Published - 01.03.2009
Event	Workshops Bildverarbeitung fur die Medizin 2009 - Heidelberg, Germany Duration: 22.03.2009 → 25.03.2009 Conference number: 97568

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Access to Document

10.1007/978-3-540-93860-6_25

Cite this

Papenberg, N., Olesch, J., Lange, T., Schlag, P. M., & Fischer, B. (2009). Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances. In H.-P. Meinzer, T. M. Deserno, H. Handels, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2009 (pp. 122-126). (Informatik aktuell). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-540-93860-6_25

@inproceedings{bf7017b414084e8f8cc14b6f6ac6772b,

title = "Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances",

abstract = "The incorporation of additional user knowledge into a nonrigid registration process is a promising topic in modern registration schemes. The combination of intensity based registration and some interactively chosen landmark pairs is a major approach in this direction. There exist different possibilities to incorporate landmark pairs into a variational non-parametric registration framework. As the interactive localization of point landmarks is always prone to errors, a demand for precise landmark matching is bound to fail. Here, the treatment of the distances of corresponding landmarks as penalties within a constrained optimization problem offers the possibility to control the quality of the matching of each landmark pair individually. More precisely, we introduce inequality constraints, which allow for a sphere-like tolerance around each landmark. We illustrate the performance of this new approach for artificial 2D images as well as for the challenging registration of preoperative CT data to intra-operative 3D ultrasound data of the liver.",

author = "Nils Papenberg and Janine Olesch and Thomas Lange and Schlag, \{Peter M.\} and Bernd Fischer",

year = "2009",

month = mar,

day = "1",

doi = "10.1007/978-3-540-93860-6\_25",

language = "English",

isbn = "978-3-540-93859-0",

series = "Informatik aktuell",

publisher = "Springer Berlin Heidelberg",

pages = "122--126",

editor = "Hans-Peter Meinzer and Deserno, \{Thomas Martin\} and Heinz Handels and Thomas Tolxdorff",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2009",

note = "Workshops Bildverarbeitung fur die Medizin 2009 , BVM 2009 ; Conference date: 22-03-2009 Through 25-03-2009",

}

Papenberg, N, Olesch, J, Lange, T, Schlag, PM & Fischer, B 2009, Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances. in H-P Meinzer, TM Deserno, H Handels & T Tolxdorff (eds), Bildverarbeitung für die Medizin 2009. Informatik aktuell, Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 122-126, Workshops Bildverarbeitung fur die Medizin 2009 , Heidelberg, Baden-Württemberg, Germany, 22.03.09. https://doi.org/10.1007/978-3-540-93860-6_25

Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances. / Papenberg, Nils; Olesch, Janine; Lange, Thomas et al.
Bildverarbeitung für die Medizin 2009. ed. / Hans-Peter Meinzer; Thomas Martin Deserno; Heinz Handels; Thomas Tolxdorff. Berlin, Heidelberg: Springer Berlin Heidelberg, 2009. p. 122-126 (Informatik aktuell).

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

TY - GEN

T1 - Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

AU - Papenberg, Nils

AU - Olesch, Janine

AU - Lange, Thomas

AU - Schlag, Peter M.

AU - Fischer, Bernd

N1 - Conference code: 97568

PY - 2009/3/1

Y1 - 2009/3/1

N2 - The incorporation of additional user knowledge into a nonrigid registration process is a promising topic in modern registration schemes. The combination of intensity based registration and some interactively chosen landmark pairs is a major approach in this direction. There exist different possibilities to incorporate landmark pairs into a variational non-parametric registration framework. As the interactive localization of point landmarks is always prone to errors, a demand for precise landmark matching is bound to fail. Here, the treatment of the distances of corresponding landmarks as penalties within a constrained optimization problem offers the possibility to control the quality of the matching of each landmark pair individually. More precisely, we introduce inequality constraints, which allow for a sphere-like tolerance around each landmark. We illustrate the performance of this new approach for artificial 2D images as well as for the challenging registration of preoperative CT data to intra-operative 3D ultrasound data of the liver.

AB - The incorporation of additional user knowledge into a nonrigid registration process is a promising topic in modern registration schemes. The combination of intensity based registration and some interactively chosen landmark pairs is a major approach in this direction. There exist different possibilities to incorporate landmark pairs into a variational non-parametric registration framework. As the interactive localization of point landmarks is always prone to errors, a demand for precise landmark matching is bound to fail. Here, the treatment of the distances of corresponding landmarks as penalties within a constrained optimization problem offers the possibility to control the quality of the matching of each landmark pair individually. More precisely, we introduce inequality constraints, which allow for a sphere-like tolerance around each landmark. We illustrate the performance of this new approach for artificial 2D images as well as for the challenging registration of preoperative CT data to intra-operative 3D ultrasound data of the liver.

UR - https://www.scopus.com/pages/publications/80053035634

U2 - 10.1007/978-3-540-93860-6_25

DO - 10.1007/978-3-540-93860-6_25

M3 - Conference contribution

SN - 978-3-540-93859-0

T3 - Informatik aktuell

SP - 122

EP - 126

BT - Bildverarbeitung für die Medizin 2009

A2 - Meinzer, Hans-Peter

A2 - Deserno, Thomas Martin

A2 - Handels, Heinz

A2 - Tolxdorff, Thomas

PB - Springer Berlin Heidelberg

CY - Berlin, Heidelberg

T2 - Workshops Bildverarbeitung fur die Medizin 2009

Y2 - 22 March 2009 through 25 March 2009

ER -

Landmark Constrained Non-parametric Image Registration with Isotropic Tolerances

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this