Dynamic texture based heart localization and segmentation in 4-D cardiac images

Junzhou Huang, Sharon Xiaolei Huang, Dimitris Metaxas, Leon Axel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D Spatio-temporal cardiac images. Our approach introduces time-dependent dynamic constraints into model-based segmentation, and it has the advantage of producing segmentation results that are both spatially and temporally consistent. Compared to previous methods that segment cardiac contours, our method offers the following advantages: 1) the heart can be quickly localized in 4D cardiac images with distinct dynamic signatures; 2) heart dynamics are learned online and adaptively by analyzing the dynamic texture from the video sequence of a cardiac cycle and then incorporated in the segmentation process; and 3) the proposed dynamic features can be easily integrated with model-based segmentation methods. We illustrate our framework through combining the new dynamic constraints with active contour models, and demonstrate its performance on sequences of 4D MRI and tagged MRI images of the heart. We also validate the accuracy of the segmentation results by comparing with ground truth marked by experts.

Original languageEnglish (US)
Title of host publication2007 4th IEEE International Symposium on Biomedical Imaging
Subtitle of host publicationFrom Nano to Macro - Proceedings
Pages852-855
Number of pages4
DOIs
StatePublished - Nov 27 2007
Event2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 - Arlington, VA, United States
Duration: Apr 12 2007Apr 15 2007

Publication series

Name2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

Other

Other2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07
CountryUnited States
CityArlington, VA
Period4/12/074/15/07

Fingerprint

Textures
Magnetic resonance imaging

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Medicine(all)

Cite this

Huang, J., Huang, S. X., Metaxas, D., & Axel, L. (2007). Dynamic texture based heart localization and segmentation in 4-D cardiac images. In 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings (pp. 852-855). [4193420] (2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings). https://doi.org/10.1109/ISBI.2007.356986
Huang, Junzhou ; Huang, Sharon Xiaolei ; Metaxas, Dimitris ; Axel, Leon. / Dynamic texture based heart localization and segmentation in 4-D cardiac images. 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. pp. 852-855 (2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings).
@inproceedings{b96df74c910f4d77b379bfe4352f8d24,
title = "Dynamic texture based heart localization and segmentation in 4-D cardiac images",
abstract = "In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D Spatio-temporal cardiac images. Our approach introduces time-dependent dynamic constraints into model-based segmentation, and it has the advantage of producing segmentation results that are both spatially and temporally consistent. Compared to previous methods that segment cardiac contours, our method offers the following advantages: 1) the heart can be quickly localized in 4D cardiac images with distinct dynamic signatures; 2) heart dynamics are learned online and adaptively by analyzing the dynamic texture from the video sequence of a cardiac cycle and then incorporated in the segmentation process; and 3) the proposed dynamic features can be easily integrated with model-based segmentation methods. We illustrate our framework through combining the new dynamic constraints with active contour models, and demonstrate its performance on sequences of 4D MRI and tagged MRI images of the heart. We also validate the accuracy of the segmentation results by comparing with ground truth marked by experts.",
author = "Junzhou Huang and Huang, {Sharon Xiaolei} and Dimitris Metaxas and Leon Axel",
year = "2007",
month = "11",
day = "27",
doi = "10.1109/ISBI.2007.356986",
language = "English (US)",
isbn = "1424406722",
series = "2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings",
pages = "852--855",
booktitle = "2007 4th IEEE International Symposium on Biomedical Imaging",

}

Huang, J, Huang, SX, Metaxas, D & Axel, L 2007, Dynamic texture based heart localization and segmentation in 4-D cardiac images. in 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings., 4193420, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings, pp. 852-855, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07, Arlington, VA, United States, 4/12/07. https://doi.org/10.1109/ISBI.2007.356986

Dynamic texture based heart localization and segmentation in 4-D cardiac images. / Huang, Junzhou; Huang, Sharon Xiaolei; Metaxas, Dimitris; Axel, Leon.

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. p. 852-855 4193420 (2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Dynamic texture based heart localization and segmentation in 4-D cardiac images

AU - Huang, Junzhou

AU - Huang, Sharon Xiaolei

AU - Metaxas, Dimitris

AU - Axel, Leon

PY - 2007/11/27

Y1 - 2007/11/27

N2 - In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D Spatio-temporal cardiac images. Our approach introduces time-dependent dynamic constraints into model-based segmentation, and it has the advantage of producing segmentation results that are both spatially and temporally consistent. Compared to previous methods that segment cardiac contours, our method offers the following advantages: 1) the heart can be quickly localized in 4D cardiac images with distinct dynamic signatures; 2) heart dynamics are learned online and adaptively by analyzing the dynamic texture from the video sequence of a cardiac cycle and then incorporated in the segmentation process; and 3) the proposed dynamic features can be easily integrated with model-based segmentation methods. We illustrate our framework through combining the new dynamic constraints with active contour models, and demonstrate its performance on sequences of 4D MRI and tagged MRI images of the heart. We also validate the accuracy of the segmentation results by comparing with ground truth marked by experts.

AB - In this paper we present a dynamic texture based motion segmentation approach to address the challenging problem of heart localization and segmentation in 4D Spatio-temporal cardiac images. Our approach introduces time-dependent dynamic constraints into model-based segmentation, and it has the advantage of producing segmentation results that are both spatially and temporally consistent. Compared to previous methods that segment cardiac contours, our method offers the following advantages: 1) the heart can be quickly localized in 4D cardiac images with distinct dynamic signatures; 2) heart dynamics are learned online and adaptively by analyzing the dynamic texture from the video sequence of a cardiac cycle and then incorporated in the segmentation process; and 3) the proposed dynamic features can be easily integrated with model-based segmentation methods. We illustrate our framework through combining the new dynamic constraints with active contour models, and demonstrate its performance on sequences of 4D MRI and tagged MRI images of the heart. We also validate the accuracy of the segmentation results by comparing with ground truth marked by experts.

UR - http://www.scopus.com/inward/record.url?scp=36349008107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36349008107&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2007.356986

DO - 10.1109/ISBI.2007.356986

M3 - Conference contribution

SN - 1424406722

SN - 9781424406722

T3 - 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

SP - 852

EP - 855

BT - 2007 4th IEEE International Symposium on Biomedical Imaging

ER -

Huang J, Huang SX, Metaxas D, Axel L. Dynamic texture based heart localization and segmentation in 4-D cardiac images. In 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. p. 852-855. 4193420. (2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings). https://doi.org/10.1109/ISBI.2007.356986