King's College London

Research portal

A level-set approach to joint image segmentation and registration with application to CT lung imaging

Research output: Contribution to journalArticle

Standard

A level-set approach to joint image segmentation and registration with application to CT lung imaging. / Swierczynski, Piotr; Papież, Bartłomiej W; Schnabel, Julia A; Macdonald, Colin.

In: Computerized Medical Imaging and Graphics, Vol. 65, 04.2018, p. 58-68.

Research output: Contribution to journalArticle

Harvard

Swierczynski, P, Papież, BW, Schnabel, JA & Macdonald, C 2018, 'A level-set approach to joint image segmentation and registration with application to CT lung imaging', Computerized Medical Imaging and Graphics, vol. 65, pp. 58-68. https://doi.org/10.1016/j.compmedimag.2017.06.003

APA

Swierczynski, P., Papież, B. W., Schnabel, J. A., & Macdonald, C. (2018). A level-set approach to joint image segmentation and registration with application to CT lung imaging. Computerized Medical Imaging and Graphics, 65, 58-68. https://doi.org/10.1016/j.compmedimag.2017.06.003

Vancouver

Swierczynski P, Papież BW, Schnabel JA, Macdonald C. A level-set approach to joint image segmentation and registration with application to CT lung imaging. Computerized Medical Imaging and Graphics. 2018 Apr;65:58-68. https://doi.org/10.1016/j.compmedimag.2017.06.003

Author

Swierczynski, Piotr ; Papież, Bartłomiej W ; Schnabel, Julia A ; Macdonald, Colin. / A level-set approach to joint image segmentation and registration with application to CT lung imaging. In: Computerized Medical Imaging and Graphics. 2018 ; Vol. 65. pp. 58-68.

Bibtex Download

@article{a428d381bc8445b7859bd98f7933c6df,
title = "A level-set approach to joint image segmentation and registration with application to CT lung imaging",
abstract = "Automated analysis of structural imaging such as lung Computed Tomography (CT) plays an increasingly important role in medical imaging applications. Despite significant progress in the development of image registration and segmentation methods, lung registration and segmentation remain a challenging task. In this paper, we present a novel image registration and segmentation approach, for which we develop a new mathematical formulation to jointly segment and register three-dimensional lung CT volumes. The new algorithm is based on a level-set formulation, which merges a classic Chan-Vese segmentation with the active dense displacement field estimation. Combining registration with segmentation has two key advantages: it allows to eliminate the problem of initializing surface based segmentation methods, and to incorporate prior knowledge into the registration in a mathematically justified manner, while remaining computationally attractive. We evaluate our framework on a publicly available lung CT data set to demonstrate the properties of the new formulation. The presented results show the improved accuracy for our joint segmentation and registration algorithm when compared to registration and segmentation performed separately.",
keywords = "Journal Article",
author = "Piotr Swierczynski and Papie{\.z}, {Bart{\l}omiej W} and Schnabel, {Julia A} and Colin Macdonald",
note = "Copyright {\textcopyright} 2017 Elsevier Ltd. All rights reserved.",
year = "2018",
month = apr,
doi = "10.1016/j.compmedimag.2017.06.003",
language = "English",
volume = "65",
pages = "58--68",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - A level-set approach to joint image segmentation and registration with application to CT lung imaging

AU - Swierczynski, Piotr

AU - Papież, Bartłomiej W

AU - Schnabel, Julia A

AU - Macdonald, Colin

N1 - Copyright © 2017 Elsevier Ltd. All rights reserved.

PY - 2018/4

Y1 - 2018/4

N2 - Automated analysis of structural imaging such as lung Computed Tomography (CT) plays an increasingly important role in medical imaging applications. Despite significant progress in the development of image registration and segmentation methods, lung registration and segmentation remain a challenging task. In this paper, we present a novel image registration and segmentation approach, for which we develop a new mathematical formulation to jointly segment and register three-dimensional lung CT volumes. The new algorithm is based on a level-set formulation, which merges a classic Chan-Vese segmentation with the active dense displacement field estimation. Combining registration with segmentation has two key advantages: it allows to eliminate the problem of initializing surface based segmentation methods, and to incorporate prior knowledge into the registration in a mathematically justified manner, while remaining computationally attractive. We evaluate our framework on a publicly available lung CT data set to demonstrate the properties of the new formulation. The presented results show the improved accuracy for our joint segmentation and registration algorithm when compared to registration and segmentation performed separately.

AB - Automated analysis of structural imaging such as lung Computed Tomography (CT) plays an increasingly important role in medical imaging applications. Despite significant progress in the development of image registration and segmentation methods, lung registration and segmentation remain a challenging task. In this paper, we present a novel image registration and segmentation approach, for which we develop a new mathematical formulation to jointly segment and register three-dimensional lung CT volumes. The new algorithm is based on a level-set formulation, which merges a classic Chan-Vese segmentation with the active dense displacement field estimation. Combining registration with segmentation has two key advantages: it allows to eliminate the problem of initializing surface based segmentation methods, and to incorporate prior knowledge into the registration in a mathematically justified manner, while remaining computationally attractive. We evaluate our framework on a publicly available lung CT data set to demonstrate the properties of the new formulation. The presented results show the improved accuracy for our joint segmentation and registration algorithm when compared to registration and segmentation performed separately.

KW - Journal Article

U2 - 10.1016/j.compmedimag.2017.06.003

DO - 10.1016/j.compmedimag.2017.06.003

M3 - Article

C2 - 28705410

VL - 65

SP - 58

EP - 68

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

ER -

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454