NUCLEAR TEXTURE ANALYSIS - A NEW PROGNOSTIC TOOL IN METASTATIC PROSTATE-CANCER

This report describes the prognostic value of computerized nuclear tex ture analysis in metastatic prostate cancer, Seventy-seven patients wi th histologically verified prostate carcinomas and skeletal metastases were selected from a Scandinavian multicenter study (SPCG-2), Thirty- six therapy-resistant patients experienced objective progression and c ancer-related death within 2 years after orchiectomy, Thirty patients responded well to orchiectomy, i.e., showed objective disease remissio n and no signs of progression during 3 years of follow-up, From this d ata set, 10 randomly chosen therapy-resistant and 10 randomly chosen t herapy-sensitive carcinomas were used in our previous study to find th e optimal combination of features that can discriminate between the tw o groups (Yogesan et al.: Cytometry 24:268-276, 1996), In addition to these two groups, 11 patients experienced stable disease or disease re mission during the first year and a secondary progression during the s econd or third year of follow-up, with subsequent cancer-related death , Traditional clinical prognostic factors such as histopathological gr ading and serum markers could not discriminate between these groups of patients, Therefore, image analysis techniques based on texture analy sis have been utilized in this study of prognosis of prostate cancer, Feulgen-stained monolayers of nuclei were prepared from paraffin-embed ded material taken from the primary tumor before endocrine ablation, F our different textural features were selected from the training data s et to calculate the discriminating function, This function separated t he therapy-sensitive and the therapy-resistant patients with 87% accur acy in the independent data set, This study demonstrates that it is po ssible to predict tumor progression and survival for endocrine-ablated metastatic prostate carcinomas using computerized nuclear texture ana lysis on light microscopy images from prostate biopsies taken at the t ime of diagnosis. (C) 1996 Wiley-Liss, Inc.