A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets

Sharif M.S. Al Sharif; Mohamed Deriche; Nabil Maalej; Sami El Ferik

doi:10.1007/s13369-013-0664-4

A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets

Sharif M.S. Al Sharif, Mohamed Deriche, Nabil Maalej, Sami El Ferik

Physics

King Fahd University for Petroleum and Minerals (KFUPM)

Research output: Contribution to journal › Article › peer-review

7 Scopus citations

Abstract

The deformable geodesic active contour (GAC) method is one of the most popular techniques used in object boundary detection in images. In this work, we improve the automatic GAC technique by incorporating prior information extracted from the image region of interest. In addition, we propose a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. The results show both an improvement of more than 40 % in convergence speed together with an excellent accuracy when compared with the previous work.

Original language	British English
Pages (from-to)	1017-1037
Number of pages	21
Journal	Arabian Journal for Science and Engineering
Volume	39
Issue number	2
DOIs	https://doi.org/10.1007/s13369-013-0664-4
State	Published - Feb 2014

Keywords

Boundary detection
Deformable models
Geometric active contour (GAC)
Medical image segmentation
Prior information
Snake method

Access to Document

10.1007/s13369-013-0664-4

Cite this

@article{6b33337150c844c6b169cb5f507b3a27,

title = "A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets",

abstract = "The deformable geodesic active contour (GAC) method is one of the most popular techniques used in object boundary detection in images. In this work, we improve the automatic GAC technique by incorporating prior information extracted from the image region of interest. In addition, we propose a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. The results show both an improvement of more than 40 % in convergence speed together with an excellent accuracy when compared with the previous work.",

keywords = "Boundary detection, Deformable models, Geometric active contour (GAC), Medical image segmentation, Prior information, Snake method",

author = "{Al Sharif}, {Sharif M.S.} and Mohamed Deriche and Nabil Maalej and {El Ferik}, Sami",

year = "2014",

month = feb,

doi = "10.1007/s13369-013-0664-4",

language = "British English",

volume = "39",

pages = "1017--1037",

journal = "Arabian Journal for Science and Engineering",

issn = "2193-567X",

publisher = "Springer Nature",

number = "2",

}

TY - JOUR

T1 - A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets

AU - Al Sharif, Sharif M.S.

AU - Deriche, Mohamed

AU - Maalej, Nabil

AU - El Ferik, Sami

PY - 2014/2

Y1 - 2014/2

N2 - The deformable geodesic active contour (GAC) method is one of the most popular techniques used in object boundary detection in images. In this work, we improve the automatic GAC technique by incorporating prior information extracted from the image region of interest. In addition, we propose a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. The results show both an improvement of more than 40 % in convergence speed together with an excellent accuracy when compared with the previous work.

AB - The deformable geodesic active contour (GAC) method is one of the most popular techniques used in object boundary detection in images. In this work, we improve the automatic GAC technique by incorporating prior information extracted from the image region of interest. In addition, we propose a new stopping function to speed up convergence and improve accuracy. The proposed technique was applied to both synthetic and real medical images. The results show both an improvement of more than 40 % in convergence speed together with an excellent accuracy when compared with the previous work.

KW - Boundary detection

KW - Deformable models

KW - Geometric active contour (GAC)

KW - Medical image segmentation

KW - Prior information

KW - Snake method

UR - http://www.scopus.com/inward/record.url?scp=84893154378&partnerID=8YFLogxK

U2 - 10.1007/s13369-013-0664-4

DO - 10.1007/s13369-013-0664-4

M3 - Article

AN - SCOPUS:84893154378

SN - 2193-567X

VL - 39

SP - 1017

EP - 1037

JO - Arabian Journal for Science and Engineering

JF - Arabian Journal for Science and Engineering

IS - 2

ER -

A Fast Geodesic Active Contour Model for Medical Image Segmentation Using Prior Analysis and Wavelets

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this