Fully automatic segmentation based on localizing active contour method

Toan Bui; Chunsoo Ahn; Jitae Shin; Yong Woo Lee

doi:10.1145/2557977.2558036

Fully automatic segmentation based on localizing active contour method

Toan Bui
, Chunsoo Ahn
, Jitae Shin
, Yong Woo Lee

Department of Electronic and Electrical Engineering

Sungkyunkwan University

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

Cartilage segmentation is one of challenging issues because knee magnetic resonance (MR) images are consisted of thin sheet structure, intensity inhomogeneity, and low contrast between cartilage and muscle. In this paper, a fully automatic segmentation method for knee cartilage is proposed using spatial fuzzy c-mean clustering (SFCM) and morphological operators. The proposed method modifies the way to generate an approximate boundary of cartilage region, and combines it with localizing region-based active contour method, and overcomes limitations of previous methods. The performance of the proposed method is improved more than 10.8% by Dice similarity coefficient (DSC) in comparison with previous methods.

Original language	English
DOIs	https://doi.org/10.1145/2557977.2558036
State	Published - 2014
Event	8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014 - Siem Reap, Cambodia Duration: 9 Jan 2014 → 11 Jan 2014

Conference

Conference	8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014
Country/Territory	Cambodia
City	Siem Reap
Period	9/01/14 → 11/01/14

Keywords

Cartilage segmentation
Localizing region-based active contour
SFCM

Access to Document

10.1145/2557977.2558036

Cite this

@conference{f59e4ec118054f658baf04c694ba4f48,

title = "Fully automatic segmentation based on localizing active contour method",

abstract = "Cartilage segmentation is one of challenging issues because knee magnetic resonance (MR) images are consisted of thin sheet structure, intensity inhomogeneity, and low contrast between cartilage and muscle. In this paper, a fully automatic segmentation method for knee cartilage is proposed using spatial fuzzy c-mean clustering (SFCM) and morphological operators. The proposed method modifies the way to generate an approximate boundary of cartilage region, and combines it with localizing region-based active contour method, and overcomes limitations of previous methods. The performance of the proposed method is improved more than 10.8\% by Dice similarity coefficient (DSC) in comparison with previous methods.",

keywords = "Cartilage segmentation, Localizing region-based active contour, SFCM",

author = "Toan Bui and Chunsoo Ahn and Jitae Shin and Lee, \{Yong Woo\}",

year = "2014",

doi = "10.1145/2557977.2558036",

language = "English",

note = "8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014 ; Conference date: 09-01-2014 Through 11-01-2014",

}

TY - CONF

T1 - Fully automatic segmentation based on localizing active contour method

AU - Bui, Toan

AU - Ahn, Chunsoo

AU - Shin, Jitae

AU - Lee, Yong Woo

PY - 2014

Y1 - 2014

N2 - Cartilage segmentation is one of challenging issues because knee magnetic resonance (MR) images are consisted of thin sheet structure, intensity inhomogeneity, and low contrast between cartilage and muscle. In this paper, a fully automatic segmentation method for knee cartilage is proposed using spatial fuzzy c-mean clustering (SFCM) and morphological operators. The proposed method modifies the way to generate an approximate boundary of cartilage region, and combines it with localizing region-based active contour method, and overcomes limitations of previous methods. The performance of the proposed method is improved more than 10.8% by Dice similarity coefficient (DSC) in comparison with previous methods.

AB - Cartilage segmentation is one of challenging issues because knee magnetic resonance (MR) images are consisted of thin sheet structure, intensity inhomogeneity, and low contrast between cartilage and muscle. In this paper, a fully automatic segmentation method for knee cartilage is proposed using spatial fuzzy c-mean clustering (SFCM) and morphological operators. The proposed method modifies the way to generate an approximate boundary of cartilage region, and combines it with localizing region-based active contour method, and overcomes limitations of previous methods. The performance of the proposed method is improved more than 10.8% by Dice similarity coefficient (DSC) in comparison with previous methods.

KW - Cartilage segmentation

KW - Localizing region-based active contour

KW - SFCM

UR - https://www.scopus.com/pages/publications/84899752406

U2 - 10.1145/2557977.2558036

DO - 10.1145/2557977.2558036

M3 - Paper

AN - SCOPUS:84899752406

T2 - 8th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2014

Y2 - 9 January 2014 through 11 January 2014

ER -

Fully automatic segmentation based on localizing active contour method

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this