A robust active contour initialization and gradient vector flow for ultrasound image segmentation

C. Tauber; H. Batatia; A. Ayache

A robust active contour initialization and gradient vector flow for ultrasound image segmentation

C. Tauber^*, H. Batatia, A. Ayache

^*Corresponding author for this work

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Citations (Scopus)

Abstract

Speckle and low contrast make ultrasound image segmentation a difficult task. This paper presents an original robust active contour energy and the corresponding quasi-automatic initialization. Both are based on the coefficient of variation gradient vector flow. Our approach combines anisotropic diffusion with the gradient vector flow field. The gradient vector flow is calculated from a map of the amplitudes of the coefficient of variation. This makes it more robust to speckle. The centers of divergence are calculated and used to initialize the active contour model. The method has been tested on different echocardographic images. The results presented are very encouraging.

Original language	English
Title of host publication	Proceedings of the 9th IAPR Conference on Machine Vision Applications
Publisher	IAPR
Pages	164-167
Number of pages	4
ISBN (Print)	4901122045, 9784901122047
Publication status	Published - 2005
Event	9th IAPR Conference on Machine Vision Applications 2005 - Tsukuba Science City, Japan Duration: 16 May 2005 → 18 May 2005

Conference

Conference	9th IAPR Conference on Machine Vision Applications 2005
Abbreviated title	MVA 2005
Country/Territory	Japan
City	Tsukuba Science City
Period	16/05/05 → 18/05/05

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

Cite this

@inproceedings{bcc3c196169c4688aa9eb13a50997706,

title = "A robust active contour initialization and gradient vector flow for ultrasound image segmentation",

abstract = "Speckle and low contrast make ultrasound image segmentation a difficult task. This paper presents an original robust active contour energy and the corresponding quasi-automatic initialization. Both are based on the coefficient of variation gradient vector flow. Our approach combines anisotropic diffusion with the gradient vector flow field. The gradient vector flow is calculated from a map of the amplitudes of the coefficient of variation. This makes it more robust to speckle. The centers of divergence are calculated and used to initialize the active contour model. The method has been tested on different echocardographic images. The results presented are very encouraging.",

author = "C. Tauber and H. Batatia and A. Ayache",

year = "2005",

language = "English",

isbn = "4901122045",

pages = "164--167",

booktitle = "Proceedings of the 9th IAPR Conference on Machine Vision Applications",

publisher = "IAPR",

note = "9th IAPR Conference on Machine Vision Applications 2005, MVA 2005 ; Conference date: 16-05-2005 Through 18-05-2005",

}

TY - GEN

T1 - A robust active contour initialization and gradient vector flow for ultrasound image segmentation

AU - Tauber, C.

AU - Batatia, H.

AU - Ayache, A.

PY - 2005

Y1 - 2005

N2 - Speckle and low contrast make ultrasound image segmentation a difficult task. This paper presents an original robust active contour energy and the corresponding quasi-automatic initialization. Both are based on the coefficient of variation gradient vector flow. Our approach combines anisotropic diffusion with the gradient vector flow field. The gradient vector flow is calculated from a map of the amplitudes of the coefficient of variation. This makes it more robust to speckle. The centers of divergence are calculated and used to initialize the active contour model. The method has been tested on different echocardographic images. The results presented are very encouraging.

AB - Speckle and low contrast make ultrasound image segmentation a difficult task. This paper presents an original robust active contour energy and the corresponding quasi-automatic initialization. Both are based on the coefficient of variation gradient vector flow. Our approach combines anisotropic diffusion with the gradient vector flow field. The gradient vector flow is calculated from a map of the amplitudes of the coefficient of variation. This makes it more robust to speckle. The centers of divergence are calculated and used to initialize the active contour model. The method has been tested on different echocardographic images. The results presented are very encouraging.

UR - http://www.scopus.com/inward/record.url?scp=77951015990&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77951015990

SN - 4901122045

SN - 9784901122047

SP - 164

EP - 167

BT - Proceedings of the 9th IAPR Conference on Machine Vision Applications

PB - IAPR

T2 - 9th IAPR Conference on Machine Vision Applications 2005

Y2 - 16 May 2005 through 18 May 2005

ER -

A robust active contour initialization and gradient vector flow for ultrasound image segmentation

Abstract

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this