Clinical and biomarker correlates of androgen-independent, locally aggressive prostate cancer with limited metastatic potential

Abstract

Purpose: We have identified a subset of patients exhibiting extended survival with metastases from androgenindependent prostate cancer of which the principal site of progression was the tumor primary. The purpose of this study was to evaluate the expression of selected biomarkers to characterize this subset of prostate cancer patients.

Experimental design: A 105 core tissue microarray was constructed from primary tumor samples from 16 patients, with matched lymph node metastases in 5 cases. Immunohistochemistry was used to evaluate selected biomarkers associated with prostate cancer progression. Standard statistical methodologies were used to compute the distribution of time to progression and overall survival associations between pairs of biomarkers. Hierarchical clustering was done between groups of biomarkers, and we devised new methods to assess homogeneity of biomarker expression.

Results: The median interval from diagnosis to salvage surgery was 65 months. The profile of biomarker expression was notable for virtual absence of neuroendocrine features, high CD10, low matrix metalloproteinase (MMP)-9, high E-cadherin expression, and high membranous beta-catenin. The mean proliferative index was 12.1 +/- 10.1%, and the mean apoptotic index was 3.48 +/- 2.22%, and there was a significant correlation between these indices. Expression of the epidermal growth factor receptor was associated with phospho-AKT and proliferative index but inversely associated with phospho-STAT3.

Conclusions: The cohort of prostate cancer patients, characterized by locally aggressive disease rather than lethal metastatic progression, was associated with a distinctive biomarker signature. The biomarker profile was, in general, more consistent with low-grade prostate cancer exhibiting local growth rather than metastatic progression. Ongoing studies will establish whether this unique subset of patients can be identified prospectively.