On the use of spectral clustering for prostate tissue characterization

S. S. Mohamed; A. M. Youssef; E. F. El-Saadany; M. M.A. Salama

doi:10.1109/CCECE.2006.277317

On the use of spectral clustering for prostate tissue characterization

S. S. Mohamed
, A. M. Youssef
, E. F. El-Saadany
, M. M.A. Salama

Electrical Engineering

University of Waterloo
Concordia University

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

Abstract

Prostate cancer is the second most diagnosed malignancy in men over the age of fifty. Trans-Rectal Ultra-Sound (TRUS) is among the routine tests that are used for prostate cancer diagnosis as well as for directing prostate biopsy. To identify suspicious cancerous regions, TRUS images are usually segmented manually by an expert radiologist which can be a laborious process. In this paper, we investigate the use of spectral clustering for identifying suspicious cancerous regions in prostate TRUS images. Our preliminary results confirm that there is a high correlation between the desired segmentation and the second smallest eigenvector of the affinity matrix of the TRUS image.

Original language	British English
Title of host publication	2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	979-982
Number of pages	4
ISBN (Print)	1424400384, 9781424400386
DOIs	https://doi.org/10.1109/CCECE.2006.277317
State	Published - 2006
Event	2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06 - Ottawa, ON, Canada Duration: 7 May 2006 → 10 May 2006

Publication series

Name	Canadian Conference on Electrical and Computer Engineering
ISSN (Print)	0840-7789

Conference

Conference	2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06
Country/Territory	Canada
City	Ottawa, ON
Period	7/05/06 → 10/05/06

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Prostate cancer
Spectral clustering
Tissue characterization
TRUS

Access to Document

10.1109/CCECE.2006.277317

OpenUrl availability

Full text

Cite this

Mohamed, S. S., Youssef, A. M., El-Saadany, E. F., & Salama, M. M. A. (2006). On the use of spectral clustering for prostate tissue characterization. In 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06 (pp. 979-982). Article 4054787 (Canadian Conference on Electrical and Computer Engineering). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CCECE.2006.277317

@inproceedings{7cc8a017630d4077b2ae20dce2eebbb7,

title = "On the use of spectral clustering for prostate tissue characterization",

abstract = "Prostate cancer is the second most diagnosed malignancy in men over the age of fifty. Trans-Rectal Ultra-Sound (TRUS) is among the routine tests that are used for prostate cancer diagnosis as well as for directing prostate biopsy. To identify suspicious cancerous regions, TRUS images are usually segmented manually by an expert radiologist which can be a laborious process. In this paper, we investigate the use of spectral clustering for identifying suspicious cancerous regions in prostate TRUS images. Our preliminary results confirm that there is a high correlation between the desired segmentation and the second smallest eigenvector of the affinity matrix of the TRUS image.",

keywords = "Prostate cancer, Spectral clustering, Tissue characterization, TRUS",

author = "Mohamed, \{S. S.\} and Youssef, \{A. M.\} and El-Saadany, \{E. F.\} and Salama, \{M. M.A.\}",

year = "2006",

doi = "10.1109/CCECE.2006.277317",

language = "British English",

isbn = "1424400384",

series = "Canadian Conference on Electrical and Computer Engineering",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "979--982",

booktitle = "2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06",

address = "United States",

note = "2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06 ; Conference date: 07-05-2006 Through 10-05-2006",

}

Mohamed, SS, Youssef, AM, El-Saadany, EF & Salama, MMA 2006, On the use of spectral clustering for prostate tissue characterization. in 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06., 4054787, Canadian Conference on Electrical and Computer Engineering, Institute of Electrical and Electronics Engineers Inc., pp. 979-982, 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06, Ottawa, ON, Canada, 7/05/06. https://doi.org/10.1109/CCECE.2006.277317

On the use of spectral clustering for prostate tissue characterization. / Mohamed, S. S.; Youssef, A. M.; El-Saadany, E. F. et al.
2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06. Institute of Electrical and Electronics Engineers Inc., 2006. p. 979-982 4054787 (Canadian Conference on Electrical and Computer Engineering).

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

TY - GEN

T1 - On the use of spectral clustering for prostate tissue characterization

AU - Mohamed, S. S.

AU - Youssef, A. M.

AU - El-Saadany, E. F.

AU - Salama, M. M.A.

PY - 2006

Y1 - 2006

N2 - Prostate cancer is the second most diagnosed malignancy in men over the age of fifty. Trans-Rectal Ultra-Sound (TRUS) is among the routine tests that are used for prostate cancer diagnosis as well as for directing prostate biopsy. To identify suspicious cancerous regions, TRUS images are usually segmented manually by an expert radiologist which can be a laborious process. In this paper, we investigate the use of spectral clustering for identifying suspicious cancerous regions in prostate TRUS images. Our preliminary results confirm that there is a high correlation between the desired segmentation and the second smallest eigenvector of the affinity matrix of the TRUS image.

AB - Prostate cancer is the second most diagnosed malignancy in men over the age of fifty. Trans-Rectal Ultra-Sound (TRUS) is among the routine tests that are used for prostate cancer diagnosis as well as for directing prostate biopsy. To identify suspicious cancerous regions, TRUS images are usually segmented manually by an expert radiologist which can be a laborious process. In this paper, we investigate the use of spectral clustering for identifying suspicious cancerous regions in prostate TRUS images. Our preliminary results confirm that there is a high correlation between the desired segmentation and the second smallest eigenvector of the affinity matrix of the TRUS image.

KW - Prostate cancer

KW - Spectral clustering

KW - Tissue characterization

KW - TRUS

UR - https://www.scopus.com/pages/publications/39049128506

U2 - 10.1109/CCECE.2006.277317

DO - 10.1109/CCECE.2006.277317

M3 - Conference contribution

AN - SCOPUS:39049128506

SN - 1424400384

SN - 9781424400386

T3 - Canadian Conference on Electrical and Computer Engineering

SP - 979

EP - 982

BT - 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06

Y2 - 7 May 2006 through 10 May 2006

ER -

Mohamed SS, Youssef AM, El-Saadany EF, Salama MMA. On the use of spectral clustering for prostate tissue characterization. In 2006 Canadian Conference on Electrical and Computer Engineering, CCECE'06. Institute of Electrical and Electronics Engineers Inc. 2006. p. 979-982. 4054787. (Canadian Conference on Electrical and Computer Engineering). doi: 10.1109/CCECE.2006.277317

On the use of spectral clustering for prostate tissue characterization

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this