Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT

Christoph Bernhard Hoog Antink, Tarunraj Singh, Puneet Singla, Matthew Podgorsak

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Extensive use of high frequency imaging in medical applications permit the estimation of velocity fields which corresponds to motion of landmarks in the imaging field. The focus of this work is on the development of a robust local optical flow algorithm for velocity field estimation in medical applications. Local polynomial fits to the medical image intensity-maps are used to generate convolution operators to estimate the spatial gradients. A novel polynomial window function with a compact support is used to differentially weight the optical flow gradient constraints in the region of interest. Tikhonov regularization is exploited to synthesize a well posed optimization problem and to penalize large displacements. The proposed algorithm is tested and validated on benchmark datasets for deformable image registration. The ten datasets include large and small deformations, and illustrate that the proposed algorithm outperforms or is competitive with other algorithms tested on this dataset, when using mean and variance of the displacement error as performance metrics.

Original languageEnglish (US)
Pages (from-to)433-441
Number of pages9
JournalJournal of Clinical Monitoring and Computing
Volume27
Issue number4
DOIs
StatePublished - Aug 1 2013

Fingerprint

Four-Dimensional Computed Tomography
Thorax
Benchmarking
Diagnostic Imaging
Weights and Measures
Datasets

All Science Journal Classification (ASJC) codes

  • Health Informatics
  • Critical Care and Intensive Care Medicine
  • Anesthesiology and Pain Medicine

Cite this

Hoog Antink, Christoph Bernhard ; Singh, Tarunraj ; Singla, Puneet ; Podgorsak, Matthew. / Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT. In: Journal of Clinical Monitoring and Computing. 2013 ; Vol. 27, No. 4. pp. 433-441.
@article{030ae182949343bcbdfca0cac234ec69,
title = "Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT",
abstract = "Extensive use of high frequency imaging in medical applications permit the estimation of velocity fields which corresponds to motion of landmarks in the imaging field. The focus of this work is on the development of a robust local optical flow algorithm for velocity field estimation in medical applications. Local polynomial fits to the medical image intensity-maps are used to generate convolution operators to estimate the spatial gradients. A novel polynomial window function with a compact support is used to differentially weight the optical flow gradient constraints in the region of interest. Tikhonov regularization is exploited to synthesize a well posed optimization problem and to penalize large displacements. The proposed algorithm is tested and validated on benchmark datasets for deformable image registration. The ten datasets include large and small deformations, and illustrate that the proposed algorithm outperforms or is competitive with other algorithms tested on this dataset, when using mean and variance of the displacement error as performance metrics.",
author = "{Hoog Antink}, {Christoph Bernhard} and Tarunraj Singh and Puneet Singla and Matthew Podgorsak",
year = "2013",
month = "8",
day = "1",
doi = "10.1007/s10877-013-9454-5",
language = "English (US)",
volume = "27",
pages = "433--441",
journal = "Journal of Clinical Monitoring and Computing",
issn = "1387-1307",
publisher = "Springer Netherlands",
number = "4",

}

Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT. / Hoog Antink, Christoph Bernhard; Singh, Tarunraj; Singla, Puneet; Podgorsak, Matthew.

In: Journal of Clinical Monitoring and Computing, Vol. 27, No. 4, 01.08.2013, p. 433-441.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evaluation of advanced Lukas-Kanade optical flow on thoracic 4D-CT

AU - Hoog Antink, Christoph Bernhard

AU - Singh, Tarunraj

AU - Singla, Puneet

AU - Podgorsak, Matthew

PY - 2013/8/1

Y1 - 2013/8/1

N2 - Extensive use of high frequency imaging in medical applications permit the estimation of velocity fields which corresponds to motion of landmarks in the imaging field. The focus of this work is on the development of a robust local optical flow algorithm for velocity field estimation in medical applications. Local polynomial fits to the medical image intensity-maps are used to generate convolution operators to estimate the spatial gradients. A novel polynomial window function with a compact support is used to differentially weight the optical flow gradient constraints in the region of interest. Tikhonov regularization is exploited to synthesize a well posed optimization problem and to penalize large displacements. The proposed algorithm is tested and validated on benchmark datasets for deformable image registration. The ten datasets include large and small deformations, and illustrate that the proposed algorithm outperforms or is competitive with other algorithms tested on this dataset, when using mean and variance of the displacement error as performance metrics.

AB - Extensive use of high frequency imaging in medical applications permit the estimation of velocity fields which corresponds to motion of landmarks in the imaging field. The focus of this work is on the development of a robust local optical flow algorithm for velocity field estimation in medical applications. Local polynomial fits to the medical image intensity-maps are used to generate convolution operators to estimate the spatial gradients. A novel polynomial window function with a compact support is used to differentially weight the optical flow gradient constraints in the region of interest. Tikhonov regularization is exploited to synthesize a well posed optimization problem and to penalize large displacements. The proposed algorithm is tested and validated on benchmark datasets for deformable image registration. The ten datasets include large and small deformations, and illustrate that the proposed algorithm outperforms or is competitive with other algorithms tested on this dataset, when using mean and variance of the displacement error as performance metrics.

UR - http://www.scopus.com/inward/record.url?scp=84879552557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879552557&partnerID=8YFLogxK

U2 - 10.1007/s10877-013-9454-5

DO - 10.1007/s10877-013-9454-5

M3 - Article

C2 - 23549645

AN - SCOPUS:84879552557

VL - 27

SP - 433

EP - 441

JO - Journal of Clinical Monitoring and Computing

JF - Journal of Clinical Monitoring and Computing

SN - 1387-1307

IS - 4

ER -