Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities

Bei Yan; Chunming Li; Mei Xie; Christos Davatzikos

doi:10.1109/ISBI.2011.5872802

Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities

Bei Yan, Chunming Li, Mei Xie, Christos Davatzikos

School of Medicine

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

1 Scopus citations

Abstract

This paper presents a modified region-scalable fitting (RSF) model in [1] and a more efficient narrow band algorithm to perform level set evolution. A distance regularization term is used to maintain the regularity of the level set function, which is necessary for maintaining stable level set evolution and ensuring accurate numerical computation. The computational efficiency of our algorithm is further improved by using 1D directional convolutions to approximate the 2D convolutions in the computation of the two fitting functions in the RSF model. Our algorithm has been tested on synthetic and real medical images with promising results.

Original language	English (US)
Title of host publication	2011 8th IEEE International Symposium on Biomedical Imaging
Subtitle of host publication	From Nano to Macro, ISBI'11
Pages	1994-1997
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2011.5872802
State	Published - Nov 2 2011
Event	2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 - Chicago, IL, United States Duration: Mar 30 2011 → Apr 2 2011

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Other

Other	2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11
Country/Territory	United States
City	Chicago, IL
Period	3/30/11 → 4/2/11

Keywords

Image segmentation
Intensity inhomogeneity
Level set
Narrow band
Region-scalable fitting

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2011.5872802

Cite this

Yan, B., Li, C., Xie, M., & Davatzikos, C. (2011). Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities. In 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 (pp. 1994-1997). Article 5872802 (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2011.5872802

Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities. / Yan, Bei; Li, Chunming; Xie, Mei et al.
2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11. 2011. p. 1994-1997 5872802 (Proceedings - International Symposium on Biomedical Imaging).

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

Yan, B, Li, C, Xie, M & Davatzikos, C 2011, Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities. in 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11., 5872802, Proceedings - International Symposium on Biomedical Imaging, pp. 1994-1997, 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11, Chicago, IL, United States, 3/30/11. https://doi.org/10.1109/ISBI.2011.5872802

@inproceedings{8827784158a241808b7b289a3b995a5c,

title = "Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities",

abstract = "This paper presents a modified region-scalable fitting (RSF) model in [1] and a more efficient narrow band algorithm to perform level set evolution. A distance regularization term is used to maintain the regularity of the level set function, which is necessary for maintaining stable level set evolution and ensuring accurate numerical computation. The computational efficiency of our algorithm is further improved by using 1D directional convolutions to approximate the 2D convolutions in the computation of the two fitting functions in the RSF model. Our algorithm has been tested on synthetic and real medical images with promising results.",

keywords = "Image segmentation, Intensity inhomogeneity, Level set, Narrow band, Region-scalable fitting",

author = "Bei Yan and Chunming Li and Mei Xie and Christos Davatzikos",

year = "2011",

month = nov,

day = "2",

doi = "10.1109/ISBI.2011.5872802",

language = "English (US)",

isbn = "9781424441280",

series = "Proceedings - International Symposium on Biomedical Imaging",

pages = "1994--1997",

booktitle = "2011 8th IEEE International Symposium on Biomedical Imaging",

note = "2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11 ; Conference date: 30-03-2011 Through 02-04-2011",

}

TY - GEN

T1 - Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities

AU - Yan, Bei

AU - Li, Chunming

AU - Xie, Mei

AU - Davatzikos, Christos

PY - 2011/11/2

Y1 - 2011/11/2

N2 - This paper presents a modified region-scalable fitting (RSF) model in [1] and a more efficient narrow band algorithm to perform level set evolution. A distance regularization term is used to maintain the regularity of the level set function, which is necessary for maintaining stable level set evolution and ensuring accurate numerical computation. The computational efficiency of our algorithm is further improved by using 1D directional convolutions to approximate the 2D convolutions in the computation of the two fitting functions in the RSF model. Our algorithm has been tested on synthetic and real medical images with promising results.

AB - This paper presents a modified region-scalable fitting (RSF) model in [1] and a more efficient narrow band algorithm to perform level set evolution. A distance regularization term is used to maintain the regularity of the level set function, which is necessary for maintaining stable level set evolution and ensuring accurate numerical computation. The computational efficiency of our algorithm is further improved by using 1D directional convolutions to approximate the 2D convolutions in the computation of the two fitting functions in the RSF model. Our algorithm has been tested on synthetic and real medical images with promising results.

KW - Image segmentation

KW - Intensity inhomogeneity

KW - Level set

KW - Narrow band

KW - Region-scalable fitting

UR - http://www.scopus.com/inward/record.url?scp=80055050941&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055050941&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2011.5872802

DO - 10.1109/ISBI.2011.5872802

M3 - Conference contribution

AN - SCOPUS:80055050941

SN - 9781424441280

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1994

EP - 1997

BT - 2011 8th IEEE International Symposium on Biomedical Imaging

T2 - 2011 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI'11

Y2 - 30 March 2011 through 2 April 2011

ER -

Narrow band region-scalable fitting model for image segmentation in the presence of intensity inhomogeneities

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this