Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy

André Huisman, Lennert S. Ploeger, Hub F J Dullens, Trudy N. Jonges, Jeroen A M Belien, Gerrit A. Meijer, Neal Poulin, William E. Grizzle, Paul J. Van Diest

Research output: Contribution to journalArticle

Abstract

BACKGROUND. Analysis of chromatin texture may improve both the diagnosis and the assessment of the prognosis of prostate cancer. Confocal laser scanning microscopy (CLSM) allows performing measurements in nuclei reconstructed in 3-D. The aim of this study was to evaluate the clinical usefulness of 3-D texture analysis of prostate tissue. METHODS. Image stacks of eight prostate cancer sections were obtained by CLSM of both benign and malignant areas. Texture feature values were computed for individual nuclei. The discriminative power of the texture features was established by receiver operating characteristic (ROC) analysis and linear discriminant analysis (LDA). RESULTS. Texture features were identified that could discriminate between benign and malignant nuclei. LDA correctly classified 89% of the nuclei of the pooled set of benign and malignant nuclei. CONCLUSIONS. 3-D nuclear texture features allow discrimination of most benign and malignant prostate nuclei. We estimate that the classification rates can be increased by improving the image quality.

Original languageEnglish (US)
Pages (from-to)248-254
Number of pages7
JournalProstate
Volume67
Issue number3
DOIs
StatePublished - Feb 15 2007
Externally publishedYes

Fingerprint

Discriminant Analysis
Confocal Microscopy
Chromatin
Prostate
Prostatic Neoplasms
ROC Curve

Keywords

  • 3-D
  • Confocal laser scanning microscopy
  • DNA ploidy
  • Image analysis
  • Prostate cancer
  • Texture features

ASJC Scopus subject areas

  • Urology

Cite this

Huisman, A., Ploeger, L. S., Dullens, H. F. J., Jonges, T. N., Belien, J. A. M., Meijer, G. A., ... Van Diest, P. J. (2007). Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy. Prostate, 67(3), 248-254. https://doi.org/10.1002/pros.20507

Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy. / Huisman, André; Ploeger, Lennert S.; Dullens, Hub F J; Jonges, Trudy N.; Belien, Jeroen A M; Meijer, Gerrit A.; Poulin, Neal; Grizzle, William E.; Van Diest, Paul J.

In: Prostate, Vol. 67, No. 3, 15.02.2007, p. 248-254.

Research output: Contribution to journalArticle

Huisman, A, Ploeger, LS, Dullens, HFJ, Jonges, TN, Belien, JAM, Meijer, GA, Poulin, N, Grizzle, WE & Van Diest, PJ 2007, 'Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy', Prostate, vol. 67, no. 3, pp. 248-254. https://doi.org/10.1002/pros.20507
Huisman, André ; Ploeger, Lennert S. ; Dullens, Hub F J ; Jonges, Trudy N. ; Belien, Jeroen A M ; Meijer, Gerrit A. ; Poulin, Neal ; Grizzle, William E. ; Van Diest, Paul J. / Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy. In: Prostate. 2007 ; Vol. 67, No. 3. pp. 248-254.
@article{231ab2337d0b42a0ac3a53b3ead806b2,
title = "Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy",
abstract = "BACKGROUND. Analysis of chromatin texture may improve both the diagnosis and the assessment of the prognosis of prostate cancer. Confocal laser scanning microscopy (CLSM) allows performing measurements in nuclei reconstructed in 3-D. The aim of this study was to evaluate the clinical usefulness of 3-D texture analysis of prostate tissue. METHODS. Image stacks of eight prostate cancer sections were obtained by CLSM of both benign and malignant areas. Texture feature values were computed for individual nuclei. The discriminative power of the texture features was established by receiver operating characteristic (ROC) analysis and linear discriminant analysis (LDA). RESULTS. Texture features were identified that could discriminate between benign and malignant nuclei. LDA correctly classified 89{\%} of the nuclei of the pooled set of benign and malignant nuclei. CONCLUSIONS. 3-D nuclear texture features allow discrimination of most benign and malignant prostate nuclei. We estimate that the classification rates can be increased by improving the image quality.",
keywords = "3-D, Confocal laser scanning microscopy, DNA ploidy, Image analysis, Prostate cancer, Texture features",
author = "Andr{\'e} Huisman and Ploeger, {Lennert S.} and Dullens, {Hub F J} and Jonges, {Trudy N.} and Belien, {Jeroen A M} and Meijer, {Gerrit A.} and Neal Poulin and Grizzle, {William E.} and {Van Diest}, {Paul J.}",
year = "2007",
month = "2",
day = "15",
doi = "10.1002/pros.20507",
language = "English (US)",
volume = "67",
pages = "248--254",
journal = "Prostate",
issn = "0270-4137",
publisher = "Wiley-Liss Inc.",
number = "3",

}

TY - JOUR

T1 - Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser scanning microscopy

AU - Huisman, André

AU - Ploeger, Lennert S.

AU - Dullens, Hub F J

AU - Jonges, Trudy N.

AU - Belien, Jeroen A M

AU - Meijer, Gerrit A.

AU - Poulin, Neal

AU - Grizzle, William E.

AU - Van Diest, Paul J.

PY - 2007/2/15

Y1 - 2007/2/15

N2 - BACKGROUND. Analysis of chromatin texture may improve both the diagnosis and the assessment of the prognosis of prostate cancer. Confocal laser scanning microscopy (CLSM) allows performing measurements in nuclei reconstructed in 3-D. The aim of this study was to evaluate the clinical usefulness of 3-D texture analysis of prostate tissue. METHODS. Image stacks of eight prostate cancer sections were obtained by CLSM of both benign and malignant areas. Texture feature values were computed for individual nuclei. The discriminative power of the texture features was established by receiver operating characteristic (ROC) analysis and linear discriminant analysis (LDA). RESULTS. Texture features were identified that could discriminate between benign and malignant nuclei. LDA correctly classified 89% of the nuclei of the pooled set of benign and malignant nuclei. CONCLUSIONS. 3-D nuclear texture features allow discrimination of most benign and malignant prostate nuclei. We estimate that the classification rates can be increased by improving the image quality.

AB - BACKGROUND. Analysis of chromatin texture may improve both the diagnosis and the assessment of the prognosis of prostate cancer. Confocal laser scanning microscopy (CLSM) allows performing measurements in nuclei reconstructed in 3-D. The aim of this study was to evaluate the clinical usefulness of 3-D texture analysis of prostate tissue. METHODS. Image stacks of eight prostate cancer sections were obtained by CLSM of both benign and malignant areas. Texture feature values were computed for individual nuclei. The discriminative power of the texture features was established by receiver operating characteristic (ROC) analysis and linear discriminant analysis (LDA). RESULTS. Texture features were identified that could discriminate between benign and malignant nuclei. LDA correctly classified 89% of the nuclei of the pooled set of benign and malignant nuclei. CONCLUSIONS. 3-D nuclear texture features allow discrimination of most benign and malignant prostate nuclei. We estimate that the classification rates can be increased by improving the image quality.

KW - 3-D

KW - Confocal laser scanning microscopy

KW - DNA ploidy

KW - Image analysis

KW - Prostate cancer

KW - Texture features

UR - http://www.scopus.com/inward/record.url?scp=33846988928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846988928&partnerID=8YFLogxK

U2 - 10.1002/pros.20507

DO - 10.1002/pros.20507

M3 - Article

C2 - 17075809

AN - SCOPUS:33846988928

VL - 67

SP - 248

EP - 254

JO - Prostate

JF - Prostate

SN - 0270-4137

IS - 3

ER -