Related Experiment Video
Updated: Jul 19, 2026
08:40
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
Published on: April 8, 2016
Discrimination between benign and malignant prostate tissue using chromatin texture analysis in 3-D by confocal laser
André Huisman1, Lennert S Ploeger, Hub F J Dullens
1Department of Pathology, University Medical Center, Utrecht, The Netherlands.
The Prostate
|November 1, 2006
Summary
Three-dimensional (3-D) nuclear texture analysis using confocal laser scanning microscopy (CLSM) can effectively distinguish between benign and malignant prostate cancer cells. This technique shows promise for improving prostate cancer diagnosis and prognosis assessment.
Area of Science:
- Oncology
- Biomedical Imaging
- Computational Pathology
Background:
- Chromatin texture analysis offers potential for enhanced prostate cancer diagnosis and prognosis.
- Confocal laser scanning microscopy (CLSM) enables 3-D nuclear reconstruction and measurement.
- Evaluating the clinical utility of 3-D texture analysis in prostate tissue is crucial.
Purpose of the Study:
- To assess the clinical usefulness of 3-D texture analysis for prostate cancer tissue.
- To determine if 3-D texture features can differentiate between benign and malignant prostate nuclei.
Main Methods:
- Acquired CLSM image stacks from eight prostate cancer sections, covering both benign and malignant areas.
- Computed texture feature values for individual cell nuclei.
- Utilized receiver operating characteristic (ROC) analysis and linear discriminant analysis (LDA) to evaluate feature discriminative power.
Main Results:
- Identified specific texture features capable of discriminating between benign and malignant nuclei.
- Achieved 89% correct classification of pooled benign and malignant nuclei using LDA.
Conclusions:
- 3-D nuclear texture features demonstrate significant potential for discriminating between benign and malignant prostate nuclei.
- Improvements in image quality are expected to further enhance classification accuracy.
