Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment

Yanqiao Zhu; Fuhai Li; Derek Cridebring; Jinwen Ma; Stephen T.C. Wong; Tegy J. Vadakkan; Mei Zhang; John Landua; Wei Wei; Mary E. Dickinson; Jeffrey M. Rosen; Michael T. Lewis

doi:10.1109/BIBM.2011.104

Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment

Yanqiao Zhu, Fuhai Li, Derek Cridebring, Jinwen Ma, Stephen T.C. Wong, Tegy J. Vadakkan, Mei Zhang, John Landua, Wei Wei, Mary E. Dickinson, Jeffrey M. Rosen, Michael T. Lewis

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

7 Scopus citations

Abstract

Interactions between cancer cells and factors within the tumor microenvironment (mE) are essential for understanding tumor development. The spatial relationships between blood vessel cells and cancer cells, e.g. tumor initiating cells (TICs), are an important parameter. Accurate segmentation of blood vessel is necessary for the quantization of their spatial relationships. However, this remains an open problem due to uneven intensity and low signal to noise ratio (SNR). To overcome these challenges, we propose a novel approach that integrates an oriented hidden Markov random field model (Ori-HMRF) with local clustering. The local clustering delineates boundaries of blood vessel segments with low SNR. Then blood vessel segments are viewed as random variables in the Ori-HMRF and their spatial dependence is defined based on directional information. The Ori-HMRF model suppresses noise and generates accurate blood vessel segmentation results. Experimental validations were conducted on both normal mammary and breast cancer tissues.

Original language	English
Title of host publication	Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Pages	352-357
Number of pages	6
DOIs	https://doi.org/10.1109/BIBM.2011.104
State	Published - 2011
Event	2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 - Atlanta, GA, United States Duration: Nov 12 2011 → Nov 15 2011

Publication series

Name	Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

Conference

Conference	2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Country/Territory	United States
City	Atlanta, GA
Period	11/12/11 → 11/15/11

Keywords

blood vessel segmentation
hidden Markov random field
superpixel
tumor microenvironment

Access to Document

10.1109/BIBM.2011.104

Cite this

Zhu, Y., Li, F., Cridebring, D., Ma, J., Wong, S. T. C., Vadakkan, T. J., Zhang, M., Landua, J., Wei, W., Dickinson, M. E., Rosen, J. M., & Lewis, M. T. (2011). Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 (pp. 352-357). Article 6120465 (Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011). https://doi.org/10.1109/BIBM.2011.104

Zhu, Yanqiao ; Li, Fuhai ; Cridebring, Derek et al. / Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment. Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. pp. 352-357 (Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011).

@inproceedings{c6314126ba8447578aa1f0774af60283,

title = "Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment",

abstract = "Interactions between cancer cells and factors within the tumor microenvironment (mE) are essential for understanding tumor development. The spatial relationships between blood vessel cells and cancer cells, e.g. tumor initiating cells (TICs), are an important parameter. Accurate segmentation of blood vessel is necessary for the quantization of their spatial relationships. However, this remains an open problem due to uneven intensity and low signal to noise ratio (SNR). To overcome these challenges, we propose a novel approach that integrates an oriented hidden Markov random field model (Ori-HMRF) with local clustering. The local clustering delineates boundaries of blood vessel segments with low SNR. Then blood vessel segments are viewed as random variables in the Ori-HMRF and their spatial dependence is defined based on directional information. The Ori-HMRF model suppresses noise and generates accurate blood vessel segmentation results. Experimental validations were conducted on both normal mammary and breast cancer tissues.",

keywords = "blood vessel segmentation, hidden Markov random field, superpixel, tumor microenvironment",

author = "Yanqiao Zhu and Fuhai Li and Derek Cridebring and Jinwen Ma and Wong, {Stephen T.C.} and Vadakkan, {Tegy J.} and Mei Zhang and John Landua and Wei Wei and Dickinson, {Mary E.} and Rosen, {Jeffrey M.} and Lewis, {Michael T.}",

year = "2011",

doi = "10.1109/BIBM.2011.104",

language = "English",

isbn = "9780769545745",

series = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

pages = "352--357",

booktitle = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

note = "2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 ; Conference date: 12-11-2011 Through 15-11-2011",

}

Zhu, Y, Li, F, Cridebring, D, Ma, J, Wong, STC, Vadakkan, TJ, Zhang, M, Landua, J, Wei, W, Dickinson, ME, Rosen, JM & Lewis, MT 2011, Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment. in Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011., 6120465, Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, pp. 352-357, 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, Atlanta, GA, United States, 11/12/11. https://doi.org/10.1109/BIBM.2011.104

Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment. / Zhu, Yanqiao; Li, Fuhai; Cridebring, Derek et al.
Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 352-357 6120465 (Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011).

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

TY - GEN

T1 - Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment

AU - Zhu, Yanqiao

AU - Li, Fuhai

AU - Cridebring, Derek

AU - Ma, Jinwen

AU - Wong, Stephen T.C.

AU - Vadakkan, Tegy J.

AU - Zhang, Mei

AU - Landua, John

AU - Wei, Wei

AU - Dickinson, Mary E.

AU - Rosen, Jeffrey M.

AU - Lewis, Michael T.

PY - 2011

Y1 - 2011

N2 - Interactions between cancer cells and factors within the tumor microenvironment (mE) are essential for understanding tumor development. The spatial relationships between blood vessel cells and cancer cells, e.g. tumor initiating cells (TICs), are an important parameter. Accurate segmentation of blood vessel is necessary for the quantization of their spatial relationships. However, this remains an open problem due to uneven intensity and low signal to noise ratio (SNR). To overcome these challenges, we propose a novel approach that integrates an oriented hidden Markov random field model (Ori-HMRF) with local clustering. The local clustering delineates boundaries of blood vessel segments with low SNR. Then blood vessel segments are viewed as random variables in the Ori-HMRF and their spatial dependence is defined based on directional information. The Ori-HMRF model suppresses noise and generates accurate blood vessel segmentation results. Experimental validations were conducted on both normal mammary and breast cancer tissues.

AB - Interactions between cancer cells and factors within the tumor microenvironment (mE) are essential for understanding tumor development. The spatial relationships between blood vessel cells and cancer cells, e.g. tumor initiating cells (TICs), are an important parameter. Accurate segmentation of blood vessel is necessary for the quantization of their spatial relationships. However, this remains an open problem due to uneven intensity and low signal to noise ratio (SNR). To overcome these challenges, we propose a novel approach that integrates an oriented hidden Markov random field model (Ori-HMRF) with local clustering. The local clustering delineates boundaries of blood vessel segments with low SNR. Then blood vessel segments are viewed as random variables in the Ori-HMRF and their spatial dependence is defined based on directional information. The Ori-HMRF model suppresses noise and generates accurate blood vessel segmentation results. Experimental validations were conducted on both normal mammary and breast cancer tissues.

KW - blood vessel segmentation

KW - hidden Markov random field

KW - superpixel

KW - tumor microenvironment

UR - http://www.scopus.com/inward/record.url?scp=84862918926&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2011.104

DO - 10.1109/BIBM.2011.104

M3 - Conference contribution

AN - SCOPUS:84862918926

SN - 9780769545745

T3 - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

SP - 352

EP - 357

BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

T2 - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

Y2 - 12 November 2011 through 15 November 2011

ER -

Zhu Y, Li F, Cridebring D, Ma J, Wong STC, Vadakkan TJ et al. Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 352-357. 6120465. (Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011). doi: 10.1109/BIBM.2011.104

Coupling oriented hidden Markov random field model with local clustering for segmenting blood vessels and measuring spatial structures in images of tumor microenvironment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this