Multilevel 2d-3d intensity-based image registration

Annkristin Lange; Stefan Heldmann

doi:10.1007/978-3-030-50120-4_6

Multilevel 2d-3d intensity-based image registration

Annkristin Lange^*, Stefan Heldmann

^*Corresponding author for this work

Institute of Mathematics and Image Computing

Abstract

2D-3D image registration is an important task for computer-aided minimally invasive vascular therapies. A crucial component for practical image registration is the use of multilevel strategies to avoid local optima and to speed-up runtime. However, due to the different dimensionalities of the 2D fixed and 3D moving image, the setup of multilevel strategies is not straightforward. In this work, we propose an intensity-driven 2D-3D multiresolution registration approach using the normalized gradient fields (NGF) distance measure. We discuss and empirically analyze the impact on the choice of 2D and 3D image resolutions. Furthermore, we show that our approach produces results that are comparable or superior to other state-of-the-art methods.

Original language	English
Title of host publication	WBIR 2020: Biomedical Image Registration
Editors	Žiga Špiclin, Jamie McClelland, Jan Kybic, Orcun Goksel
Number of pages	10
Volume	12120 LNCS
Publisher	Springer, Cham
Publication date	09.06.2020
Pages	57-66
ISBN (Print)	978-3-030-50119-8
ISBN (Electronic)	978-3-030-50120-4
DOIs	https://doi.org/10.1007/978-3-030-50120-4_6
Publication status	Published - 09.06.2020
Event	9th International Workshop on Biomedical Image Registration - Portoroz, Slovenia Duration: 01.12.2020 → 02.12.2020 Conference number: 240939

UN SDGs

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

Access to Document

10.1007/978-3-030-50120-4_6

Cite this

@inproceedings{20ca19963edf49c790349fa6ae2031cd,

title = "Multilevel 2d-3d intensity-based image registration",

abstract = "2D-3D image registration is an important task for computer-aided minimally invasive vascular therapies. A crucial component for practical image registration is the use of multilevel strategies to avoid local optima and to speed-up runtime. However, due to the different dimensionalities of the 2D fixed and 3D moving image, the setup of multilevel strategies is not straightforward. In this work, we propose an intensity-driven 2D-3D multiresolution registration approach using the normalized gradient fields (NGF) distance measure. We discuss and empirically analyze the impact on the choice of 2D and 3D image resolutions. Furthermore, we show that our approach produces results that are comparable or superior to other state-of-the-art methods.",

author = "Annkristin Lange and Stefan Heldmann",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2020. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 9th International Workshop on Biomedical Image Registration , WBIR 2020 ; Conference date: 01-12-2020 Through 02-12-2020",

year = "2020",

month = jun,

day = "9",

doi = "10.1007/978-3-030-50120-4_6",

language = "English",

isbn = "978-3-030-50119-8",

volume = "12120 LNCS",

series = "Lecture Notes in Computer Science",

publisher = "Springer, Cham",

pages = "57--66",

editor = "{\v S}piclin, {{\v Z}iga } and McClelland, {Jamie } and Kybic, {Jan } and Goksel, {Orcun }",

booktitle = "WBIR 2020: Biomedical Image Registration",

}

Lange, A & Heldmann, S 2020, Multilevel 2d-3d intensity-based image registration. in Ž Špiclin, J McClelland, J Kybic & O Goksel (eds), WBIR 2020: Biomedical Image Registration. vol. 12120 LNCS, Lecture Notes in Computer Science, vol. 12120 LNCS, Springer, Cham, pp. 57-66, 9th International Workshop on Biomedical Image Registration , Portoroz, Slovenia, 01.12.20. https://doi.org/10.1007/978-3-030-50120-4_6

Multilevel 2d-3d intensity-based image registration. / Lange, Annkristin; Heldmann, Stefan.
WBIR 2020: Biomedical Image Registration. ed. / Žiga Špiclin; Jamie McClelland; Jan Kybic; Orcun Goksel. Vol. 12120 LNCS Springer, Cham, 2020. p. 57-66 (Lecture Notes in Computer Science; Vol. 12120 LNCS).

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

TY - GEN

T1 - Multilevel 2d-3d intensity-based image registration

AU - Lange, Annkristin

AU - Heldmann, Stefan

N1 - Conference code: 240939

PY - 2020/6/9

Y1 - 2020/6/9

N2 - 2D-3D image registration is an important task for computer-aided minimally invasive vascular therapies. A crucial component for practical image registration is the use of multilevel strategies to avoid local optima and to speed-up runtime. However, due to the different dimensionalities of the 2D fixed and 3D moving image, the setup of multilevel strategies is not straightforward. In this work, we propose an intensity-driven 2D-3D multiresolution registration approach using the normalized gradient fields (NGF) distance measure. We discuss and empirically analyze the impact on the choice of 2D and 3D image resolutions. Furthermore, we show that our approach produces results that are comparable or superior to other state-of-the-art methods.

AB - 2D-3D image registration is an important task for computer-aided minimally invasive vascular therapies. A crucial component for practical image registration is the use of multilevel strategies to avoid local optima and to speed-up runtime. However, due to the different dimensionalities of the 2D fixed and 3D moving image, the setup of multilevel strategies is not straightforward. In this work, we propose an intensity-driven 2D-3D multiresolution registration approach using the normalized gradient fields (NGF) distance measure. We discuss and empirically analyze the impact on the choice of 2D and 3D image resolutions. Furthermore, we show that our approach produces results that are comparable or superior to other state-of-the-art methods.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85087033648&origin=inward&txGid=cd97a3525ce26ffd99a6dac95acdd0fc

U2 - 10.1007/978-3-030-50120-4_6

DO - 10.1007/978-3-030-50120-4_6

M3 - Conference contribution

SN - 978-3-030-50119-8

VL - 12120 LNCS

T3 - Lecture Notes in Computer Science

SP - 57

EP - 66

BT - WBIR 2020: Biomedical Image Registration

A2 - Špiclin, Žiga

A2 - McClelland, Jamie

A2 - Kybic, Jan

A2 - Goksel, Orcun

PB - Springer, Cham

T2 - 9th International Workshop on Biomedical Image Registration

Y2 - 1 December 2020 through 2 December 2020

ER -

Multilevel 2d-3d intensity-based image registration

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this