Three-dimensional adaptive split-and-merge method for medical image segmentation

Jin Shin Chou; Chin Tu Chen; Shiuh Yung Chen; Wei Chung Lin

Three-dimensional adaptive split-and-merge method for medical image segmentation

Jin Shin Chou^*, Chin Tu Chen, Shiuh Yung Chen, Wei Chung Lin

^*Corresponding author for this work

Electrical and Computer Engineering

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

3 Scopus citations

Abstract

We have developed a three-dimensional image segmentation algorithm using adaptive split-and-merge method. The framework of this method is based on a two-dimensional (2- D) split-and-merge scheme and the region homogeneity analysis. Hierarchical oct-tree is used as the basic data structure throughout the analysis, analogous to quad-tree in the 2-D case. A localized feature analysis and statistical tests are employed in the testing of region homogeneity. In feature analysis, standard deviation, gray-level contrast, likelihood ratio, and their corresponding co-occurrence matrix are computed. Histograms of the near- diagonal elements of the co-occurrence matrix are calculated. An optimal thresholding method is then applied to determine the desired threshold values. These values are then used as constraints in the tests, such that decision of splitting or merging can be made.

Original language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Publisher	Publ by Int Soc for Optical Engineering
Pages	439-445
Number of pages	7
Edition	pt 1
ISBN (Print)	081940814X
State	Published - 1992
Event	Biomedical Image Processing and Three-Dimensional Microscopy. Part 1 (of 2) - San Jose, CA, USA Duration: Feb 10 1991 → Feb 13 1991

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Number	pt 1
Volume	1660
ISSN (Print)	0277-786X

Other

Other	Biomedical Image Processing and Three-Dimensional Microscopy. Part 1 (of 2)
City	San Jose, CA, USA
Period	2/10/91 → 2/13/91

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Cite this

Chou, J. S., Chen, C. T., Chen, S. Y., & Lin, W. C. (1992). Three-dimensional adaptive split-and-merge method for medical image segmentation. In Proceedings of SPIE - The International Society for Optical Engineering (pt 1 ed., pp. 439-445). (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1660, No. pt 1). Publ by Int Soc for Optical Engineering.

@inproceedings{884296162d6d4a86b5ade0dc44502c18,

title = "Three-dimensional adaptive split-and-merge method for medical image segmentation",

abstract = "We have developed a three-dimensional image segmentation algorithm using adaptive split-and-merge method. The framework of this method is based on a two-dimensional (2- D) split-and-merge scheme and the region homogeneity analysis. Hierarchical oct-tree is used as the basic data structure throughout the analysis, analogous to quad-tree in the 2-D case. A localized feature analysis and statistical tests are employed in the testing of region homogeneity. In feature analysis, standard deviation, gray-level contrast, likelihood ratio, and their corresponding co-occurrence matrix are computed. Histograms of the near- diagonal elements of the co-occurrence matrix are calculated. An optimal thresholding method is then applied to determine the desired threshold values. These values are then used as constraints in the tests, such that decision of splitting or merging can be made.",

author = "Chou, {Jin Shin} and Chen, {Chin Tu} and Chen, {Shiuh Yung} and Lin, {Wei Chung}",

year = "1992",

language = "English (US)",

isbn = "081940814X",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "Publ by Int Soc for Optical Engineering",

number = "pt 1",

pages = "439--445",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

edition = "pt 1",

note = "Biomedical Image Processing and Three-Dimensional Microscopy. Part 1 (of 2) ; Conference date: 10-02-1991 Through 13-02-1991",

}

Chou, JS, Chen, CT, Chen, SY & Lin, WC 1992, Three-dimensional adaptive split-and-merge method for medical image segmentation. in Proceedings of SPIE - The International Society for Optical Engineering. pt 1 edn, Proceedings of SPIE - The International Society for Optical Engineering, no. pt 1, vol. 1660, Publ by Int Soc for Optical Engineering, pp. 439-445, Biomedical Image Processing and Three-Dimensional Microscopy. Part 1 (of 2), San Jose, CA, USA, 2/10/91.

Three-dimensional adaptive split-and-merge method for medical image segmentation. / Chou, Jin Shin; Chen, Chin Tu; Chen, Shiuh Yung et al.
Proceedings of SPIE - The International Society for Optical Engineering. pt 1. ed. Publ by Int Soc for Optical Engineering, 1992. p. 439-445 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1660, No. pt 1).

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

TY - GEN

T1 - Three-dimensional adaptive split-and-merge method for medical image segmentation

AU - Chou, Jin Shin

AU - Chen, Chin Tu

AU - Chen, Shiuh Yung

AU - Lin, Wei Chung

PY - 1992

Y1 - 1992

N2 - We have developed a three-dimensional image segmentation algorithm using adaptive split-and-merge method. The framework of this method is based on a two-dimensional (2- D) split-and-merge scheme and the region homogeneity analysis. Hierarchical oct-tree is used as the basic data structure throughout the analysis, analogous to quad-tree in the 2-D case. A localized feature analysis and statistical tests are employed in the testing of region homogeneity. In feature analysis, standard deviation, gray-level contrast, likelihood ratio, and their corresponding co-occurrence matrix are computed. Histograms of the near- diagonal elements of the co-occurrence matrix are calculated. An optimal thresholding method is then applied to determine the desired threshold values. These values are then used as constraints in the tests, such that decision of splitting or merging can be made.

AB - We have developed a three-dimensional image segmentation algorithm using adaptive split-and-merge method. The framework of this method is based on a two-dimensional (2- D) split-and-merge scheme and the region homogeneity analysis. Hierarchical oct-tree is used as the basic data structure throughout the analysis, analogous to quad-tree in the 2-D case. A localized feature analysis and statistical tests are employed in the testing of region homogeneity. In feature analysis, standard deviation, gray-level contrast, likelihood ratio, and their corresponding co-occurrence matrix are computed. Histograms of the near- diagonal elements of the co-occurrence matrix are calculated. An optimal thresholding method is then applied to determine the desired threshold values. These values are then used as constraints in the tests, such that decision of splitting or merging can be made.

UR - http://www.scopus.com/inward/record.url?scp=0026996286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026996286&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026996286

SN - 081940814X

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 439

EP - 445

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Publ by Int Soc for Optical Engineering

T2 - Biomedical Image Processing and Three-Dimensional Microscopy. Part 1 (of 2)

Y2 - 10 February 1991 through 13 February 1991

ER -

Three-dimensional adaptive split-and-merge method for medical image segmentation

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this