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
Department of Pathology, University Medical Center, Utrecht, The Netherlands.
Prostate. 2007 Feb 15;67(3):248-54. doi: 10.1002/pros.20507.
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.
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).
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.
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.
染色质纹理分析可能会改善前列腺癌的诊断及预后评估。共聚焦激光扫描显微镜（CLSM）能够对三维重建的细胞核进行测量。本研究的目的是评估前列腺组织三维纹理分析的临床实用性。
通过CLSM获取八个前列腺癌切片的良性和恶性区域的图像堆栈。计算单个细胞核的纹理特征值。通过受试者工作特征（ROC）分析和线性判别分析（LDA）确定纹理特征的判别能力。
识别出能够区分良性和恶性细胞核的纹理特征。LDA对良性和恶性细胞核合并组中89%的细胞核进行了正确分类。
三维细胞核纹理特征能够区分大多数良性和恶性前列腺细胞核。我们估计通过改善图像质量可以提高分类率。
