Improving border identification in two-dimensional echocardiograms using temporal information

Author

Choy, Marian M. ; Jin, Jesse S.

Author_Institution

Sch. of Comput. Sci. & Eng., New South Wales Univ., Kensington, NSW, Australia

Volume

2

fYear

1996

fDate

31 Oct-3 Nov 1996

Firstpage

879

Abstract

Border extraction in static two-dimensional echocardiograms (2D echo) using morphological image analysis with second derivative operator performs well. However, with large dropouts and high noise content, this segmentation method will generate false boundary points. By considering temporal information from neighbouring frame, this limitation can be solved. In this paper, we present the improvement of segmentation by adopting dynamic knowledge in our decision process. The results indicate that temporal information greatly reduces the noise sensitivity of the algorithm

Keywords

acoustic signal processing; echocardiography; edge detection; image segmentation; image sequences; mathematical morphology; medical image processing; motion estimation; recursive filters; 2D echocardiograms; Laplacian of Gaussian; algorithm noise sensitivity; border extraction; border identification; decision process; dynamic knowledge; end-systolic image; false boundary points; image segmentation method; large dropouts; morphological image analysis; moving echo image sequence; recursive filtering; second derivative operator; static echocardiograms; temporal information; watershed segmentation; zero-crossing points; Australia; Computer science; Data mining; Filtering; Image edge detection; Image segmentation; Noise generators; Noise reduction; Sequences; Ultrasonic imaging;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1996. Bridging Disciplines for Biomedicine. Proceedings of the 18th Annual International Conference of the IEEE

Conference_Location

Amsterdam

Print_ISBN

0-7803-3811-1

Type

conf

DOI

10.1109/IEMBS.1996.652021

Filename

652021