EPFL
 Biomedical Imaging GroupSTI
EPFL
  Publications
English only   BIG > Publications > Wavelet Footprints


 CONTENTS
 Home Page
 News & Events
 People
 Publications
 Tutorials and Reviews
 Research
 Demos
 Download Algorithms

 DOWNLOAD
 PDF
 Postscript
 All BibTeX References

Computer Vision in Echocardiography: Observer-Independent, Autonomous Echo Analysis Using Wavelet Footprints

C.H. Jansen, M. Arigovindan, M. Sühling, M. Unser, S. Marsch, P. Hunziker

Proceedings of the Fifty-Second Annual Scientific Session of the American College of Cardiology (ACC'03), Chicago IL, USA, March 30-April 2, 2003, Journal of the American College of Cardiology, vol. 41, no. 6, supp. 2, pp. 538A, March 19, 2003.



jansen0302fig01.jpg

Background: Image segmentation and feature extraction in dynamic ultrasound images is demanding because of the large noise content, the absence of continuous boundaries and the lack of constant intensities within objects. Therefore ultrasound imaging is largely subjective with high observer dependence.

Methods: Multidimensional, multiscale wavelet analysis produces highly specific “footprints” from echo images. We exploited this fact to create an analysis environment that is based on shape and motion specific wavelet subbands. To test the feasibility of multidimensional multiscale footprints we tried to identify the mitral valve autonomously in 182 cardiac ultrasound sequences. As gold standard for the correct location of the mitral valve in the cardiac ultrasound sequences valve localization was performed by an experienced echocardiographer.

Results: Correct location was found in 165 of 182 ultrasound sequences corresponding to 91% accuracy. The use of multidimensional multiscale footprints led to significant enhancement of the predefined structure (middle image) in the image and significantly suppressed noise and non related cardiac structures as shown in pixel statistics of the mitral valve region versus non related image parts (P < 0.05 by T Test).

Conclusion: Computer vision technology is applicable to clinical echo and allows autonomous localization of predefined cardiac structures transforming this subjective, qualitative art into a objective quantitative science.


@INPROCEEDINGS(http://bigwww.epfl.ch/publications/jansen0302.html,
AUTHOR="Jansen, C.H. and Arigovindan, M. and S{\"{u}}hling, M. and
        Unser, M. and Marsch, S. and Hunziker, P.",
TITLE="Computer Vision in Echocardiography: {O}bserver-Independent,
        Autonomous Echo Analysis Using Wavelet Footprints",
BOOKTITLE="Fifty-Second Annual Scientific Session of the American
        College of Cardiology ({ACC'03})",
YEAR="2003",
editor="",
volume="41, no. 6, supp. 2, March 19, 2003",
series="Journal of the American College of Cardiology",
pages="538A",
address="Chicago IL, USA",
month="March 30-April 2,",
organization="",
publisher="",
note="")

© 2003 ACC. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from ACC.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.