Sparse registration for three-dimensional stress echocardiography

K.Y. Esther Leung, Marijn van Stralen, Atilla Nemes, Marco M. Voormolen, Gerard van Burken, Marcel L. Geleijnse, Folkert J. ten Cate, Johan H.C. Reiber, Nico de Jong, Antonius F.W. van der Steen, Johan G. Bosch

Research output: Contribution to journalArticleAcademicpeer-review

22 Citations (Scopus)

Abstract

Three-dimensional (3-D) stress echocardiography is a novel technique for diagnosing cardiac dysfunction. It involves evaluating wall motion of the left ventricle, by visually analyzing ultrasound images obtained in rest and in different stages of stress. Since the acquisitions are performed minutes apart, variabilities may exist in the visualized cross-sections. To improve anatomical correspondence between rest and stress, aligning the images is essential. We developed a new intensity-based, sparse registration method to retrieve standard anatomical views from 3-D stress images that were equivalent to the manually selected views in the rest images. Using sparse image planes, the influence of common image artifacts could be reduced. We investigated different similarity measures and different levels of sparsity. The registration was tested using data of 20 patients and quantitatively evaluated based on manually defined anatomical landmarks. Alignment was best using sparse registration with two long-axis and two short-axis views; registration errors were reduced significantly, to the range of interobserver variabilities. In 91% of the cases, the registration result was qualitatively assessed as better than or equal to the manual alignment. In conclusion, sparse registration improves the alignment of rest and stress images, with a performance similar to manual alignment. This is an important step towards objective quantification in 3-D stress echocardiography.
Original languageEnglish
Pages (from-to)1568-1579
Number of pages12
JournalIEEE transactions on medical imaging
Volume27
Issue number11
DOIs
Publication statusPublished - 2008

Fingerprint

Three-Dimensional Echocardiography
Echocardiography
Stress Echocardiography
Observer Variation
Three-Dimensional Imaging
Artifacts
Heart Ventricles
Ultrasonics

Keywords

  • METIS-253803

Cite this

Leung, K. Y. E., van Stralen, M., Nemes, A., Voormolen, M. M., van Burken, G., Geleijnse, M. L., ... Bosch, J. G. (2008). Sparse registration for three-dimensional stress echocardiography. IEEE transactions on medical imaging, 27(11), 1568-1579. https://doi.org/10.1109/TMI.2008.922685
Leung, K.Y. Esther ; van Stralen, Marijn ; Nemes, Atilla ; Voormolen, Marco M. ; van Burken, Gerard ; Geleijnse, Marcel L. ; ten Cate, Folkert J. ; Reiber, Johan H.C. ; de Jong, Nico ; van der Steen, Antonius F.W. ; Bosch, Johan G. / Sparse registration for three-dimensional stress echocardiography. In: IEEE transactions on medical imaging. 2008 ; Vol. 27, No. 11. pp. 1568-1579.
@article{94b9f1dc48a94a588dc6b07e9eec6a75,
title = "Sparse registration for three-dimensional stress echocardiography",
abstract = "Three-dimensional (3-D) stress echocardiography is a novel technique for diagnosing cardiac dysfunction. It involves evaluating wall motion of the left ventricle, by visually analyzing ultrasound images obtained in rest and in different stages of stress. Since the acquisitions are performed minutes apart, variabilities may exist in the visualized cross-sections. To improve anatomical correspondence between rest and stress, aligning the images is essential. We developed a new intensity-based, sparse registration method to retrieve standard anatomical views from 3-D stress images that were equivalent to the manually selected views in the rest images. Using sparse image planes, the influence of common image artifacts could be reduced. We investigated different similarity measures and different levels of sparsity. The registration was tested using data of 20 patients and quantitatively evaluated based on manually defined anatomical landmarks. Alignment was best using sparse registration with two long-axis and two short-axis views; registration errors were reduced significantly, to the range of interobserver variabilities. In 91{\%} of the cases, the registration result was qualitatively assessed as better than or equal to the manual alignment. In conclusion, sparse registration improves the alignment of rest and stress images, with a performance similar to manual alignment. This is an important step towards objective quantification in 3-D stress echocardiography.",
keywords = "METIS-253803",
author = "Leung, {K.Y. Esther} and {van Stralen}, Marijn and Atilla Nemes and Voormolen, {Marco M.} and {van Burken}, Gerard and Geleijnse, {Marcel L.} and {ten Cate}, {Folkert J.} and Reiber, {Johan H.C.} and {de Jong}, Nico and {van der Steen}, {Antonius F.W.} and Bosch, {Johan G.}",
year = "2008",
doi = "10.1109/TMI.2008.922685",
language = "English",
volume = "27",
pages = "1568--1579",
journal = "IEEE transactions on medical imaging",
issn = "0278-0062",
publisher = "IEEE",
number = "11",

}

Leung, KYE, van Stralen, M, Nemes, A, Voormolen, MM, van Burken, G, Geleijnse, ML, ten Cate, FJ, Reiber, JHC, de Jong, N, van der Steen, AFW & Bosch, JG 2008, 'Sparse registration for three-dimensional stress echocardiography' IEEE transactions on medical imaging, vol. 27, no. 11, pp. 1568-1579. https://doi.org/10.1109/TMI.2008.922685

Sparse registration for three-dimensional stress echocardiography. / Leung, K.Y. Esther; van Stralen, Marijn; Nemes, Atilla; Voormolen, Marco M.; van Burken, Gerard; Geleijnse, Marcel L.; ten Cate, Folkert J.; Reiber, Johan H.C.; de Jong, Nico; van der Steen, Antonius F.W.; Bosch, Johan G.

In: IEEE transactions on medical imaging, Vol. 27, No. 11, 2008, p. 1568-1579.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Sparse registration for three-dimensional stress echocardiography

AU - Leung, K.Y. Esther

AU - van Stralen, Marijn

AU - Nemes, Atilla

AU - Voormolen, Marco M.

AU - van Burken, Gerard

AU - Geleijnse, Marcel L.

AU - ten Cate, Folkert J.

AU - Reiber, Johan H.C.

AU - de Jong, Nico

AU - van der Steen, Antonius F.W.

AU - Bosch, Johan G.

PY - 2008

Y1 - 2008

N2 - Three-dimensional (3-D) stress echocardiography is a novel technique for diagnosing cardiac dysfunction. It involves evaluating wall motion of the left ventricle, by visually analyzing ultrasound images obtained in rest and in different stages of stress. Since the acquisitions are performed minutes apart, variabilities may exist in the visualized cross-sections. To improve anatomical correspondence between rest and stress, aligning the images is essential. We developed a new intensity-based, sparse registration method to retrieve standard anatomical views from 3-D stress images that were equivalent to the manually selected views in the rest images. Using sparse image planes, the influence of common image artifacts could be reduced. We investigated different similarity measures and different levels of sparsity. The registration was tested using data of 20 patients and quantitatively evaluated based on manually defined anatomical landmarks. Alignment was best using sparse registration with two long-axis and two short-axis views; registration errors were reduced significantly, to the range of interobserver variabilities. In 91% of the cases, the registration result was qualitatively assessed as better than or equal to the manual alignment. In conclusion, sparse registration improves the alignment of rest and stress images, with a performance similar to manual alignment. This is an important step towards objective quantification in 3-D stress echocardiography.

AB - Three-dimensional (3-D) stress echocardiography is a novel technique for diagnosing cardiac dysfunction. It involves evaluating wall motion of the left ventricle, by visually analyzing ultrasound images obtained in rest and in different stages of stress. Since the acquisitions are performed minutes apart, variabilities may exist in the visualized cross-sections. To improve anatomical correspondence between rest and stress, aligning the images is essential. We developed a new intensity-based, sparse registration method to retrieve standard anatomical views from 3-D stress images that were equivalent to the manually selected views in the rest images. Using sparse image planes, the influence of common image artifacts could be reduced. We investigated different similarity measures and different levels of sparsity. The registration was tested using data of 20 patients and quantitatively evaluated based on manually defined anatomical landmarks. Alignment was best using sparse registration with two long-axis and two short-axis views; registration errors were reduced significantly, to the range of interobserver variabilities. In 91% of the cases, the registration result was qualitatively assessed as better than or equal to the manual alignment. In conclusion, sparse registration improves the alignment of rest and stress images, with a performance similar to manual alignment. This is an important step towards objective quantification in 3-D stress echocardiography.

KW - METIS-253803

U2 - 10.1109/TMI.2008.922685

DO - 10.1109/TMI.2008.922685

M3 - Article

VL - 27

SP - 1568

EP - 1579

JO - IEEE transactions on medical imaging

JF - IEEE transactions on medical imaging

SN - 0278-0062

IS - 11

ER -

Leung KYE, van Stralen M, Nemes A, Voormolen MM, van Burken G, Geleijnse ML et al. Sparse registration for three-dimensional stress echocardiography. IEEE transactions on medical imaging. 2008;27(11):1568-1579. https://doi.org/10.1109/TMI.2008.922685