Classification of prostatic carcinoma with artificial neural networks using comparative genomic hybridization and quantitative stereological data.

Staging of prostate cancer is a mainstay of treatment decisions and prognostication. In the present study, 50 pT2N0 and 28 pT3N0 prostatic adenocarcinomas were characterized by Gleason grading, comparative genomic hybridization (CGH), and histological texture analysis based on principles of stereology and stochastic geometry. The cases were classified by learning vector quantization and support vector machines. The quality of classification was tested by cross-validation. Correct prediction of stage from primary tumor data was possible with an accuracy of 74-80% from different data sets. The accuracy of prediction was similar when the Gleason score was used as input variable, when stereological data were used, or when a combination of CGH data and stereological data was used. The results of classification by learning vector quantization were slightly better than those by support vector machines. A method is briefly sketched by which training of neural networks can be adapted to unequal sample sizes per class. Progression from pT2 to pT3 prostate cancer is correlated with complex changes of the epithelial cells in terms of volume fraction, of surface area, and of second-order stereological properties. Genetically, this progression is accompanied by a significant global increase in losses and gains of DNA, and specifically by increased numerical aberrations on chromosome arms 1q, 7p, and 8p.

Chromosomal changes in incidental prostatic carcinomas detected by comparative genomic hybridization.

OBJECTIVES: The genetic changes underlying the development and progression of prostate cancer are poorly understood. To identify chromosomal regions in incidental prostatic carcinoma (T1a and T1b) was the primary aim of this study. MATERIALS AND METHODS: We used comparative genomic hybridization (CGH) to search for DNA sequence copy number changes on a series of 48 T1 prostate cancer diagnosed by transurethral resection (TURP) and by adenomectomy. Incidental prostatic carcinomas have not been studied by CGH previously. RESULTS: CGH analysis indicated that 14 cases (29.2%) of incidental prostatic carcinoma showed chromosome alterations. The most frequent alterations were chromosomal losses of 8p (10.4%), 13q (6.3%), 5q (4.2%) and 18q (4.2%), and gains of 17p (10.4%), 17q (10.4%), 9q (6.3%) and 7q (4.2%). Minimal overlapping chromosomal regions of loss, indicative for the presence of tumor suppressor genes (TSGs), were mapped to 8p22 and 13q14.1-q21.3, and minimal overlapping regions of gain, indicative for the presence of oncogenes, were found at 9q34.2-qter, 17p12 and 17q24-qter. The statistical analysis displayed a significant association between chromosomal aberration detected by CGH and high Gleason score (P < 0.005) as well as between tumor categories T1a and T1b and chromosomal imbalance (P = 0.041). CONCLUSIONS: Studies directed at incidental prostatic carcinomas allow discovery of chromosomal changes in small and highly malignant tumors. Our results suggest that loss or gain of DNA in these regions are important in prostate cancer. This is the first study, which documents the spectrum of chromosomal changes in incidental prostatic carcinomas.

Chromosomal regions in prostatic carcinomas studied by comparative genomic hybridization, hierarchical cluster analysis and self-organizing feature maps.

Comparative genomic hybridization (CGH) is an established genetic method which enables a genome-wide survey of chromosomal imbalances. For each chromosome region, one obtains the information whether there is a loss or gain of genetic material, or whether there is no change at that place. Therefore, large amounts of data quickly accumulate which must be put into a logical order. Cluster analysis can be used to assign individual cases (samples) to different clusters of cases, which are similar and where each cluster may be related to a different tumour biology. Another approach consists in a clustering of chromosomal regions by rewriting the original data matrix, where the cases are written as rows and the chromosomal regions as columns, in a transposed form. In this paper we applied hierarchical cluster analysis as well as two implementations of self-organizing feature maps as classical and neuronal tools for cluster analysis of CGH data from prostatic carcinomas to such transposed data sets. Self-organizing maps are artificial neural networks with the capability to form clusters on the basis of an unsupervised learning rule. We studied a group of 48 cases of incidental carcinomas, a tumour category which has not been evaluated by CGH before. In addition we studied a group of 50 cases of pT2N0-tumours and a group of 20 pT3N0-carcinomas. The results show in all case groups three clusters of chromosomal regions, which are (i) normal or minimally affected by losses and gains, (ii) regions with many losses and few gains and (iii) regions with many gains and few losses. Moreover, for the pT2N0- and pT3N0-groups, it could be shown that the regions 6q, 8p and 13q lay all on the same cluster (associated with losses), and that the regions 9q and 20q belonged to the same cluster (associated with gains). For the incidental cancers such clear correlations could not be demonstrated.

alpha-Methylacyl-CoA racemase: expression levels of this novel cancer biomarker depend on tumor differentiation.

alpha-Methylacyl-CoA racemase (AMACR) has previously been shown to be a highly sensitive marker for colorectal and clinically localized prostate cancer (PCa). However, AMACR expression was down-regulated at the transcript and protein level in hormone-refractory metastatic PCa, suggesting a hormone-dependent expression of AMACR. To further explore the hypothesis that AMACR is hormone regulated and plays a role in PCa progression AMACR protein expression was characterized in a broad range of PCa samples treated with variable amounts and lengths of exogenous anti-androgens. Analysis included standard slides and high-density tissue microarrays. AMACR protein expression was significantly increased in localized hormone-naive PCa as compared to benign (P < 0.001). Mean AMACR expression was lower in tissue samples from patients who had received neoadjuvant hormone treatment but still higher compared to hormone-refractory metastases. The hormone-sensitive tumor cell line, LNCaP, demonstrated stronger AMACR expression by Western blot analysis than the poorly differentiated cell lines DU-145 and PC-3. AMACR protein expression in cells after exposure to anti-androgen treatment was unchanged, whereas prostate-specific antigen, known to be androgen-regulated, demonstrated decreased protein expression. Surprisingly, this data suggests that AMACR expression is not regulated by androgens. Examination of colorectal cancer, which is not hormone regulated, demonstrated high levels of AMACR expression in well to moderately differentiated tumors and weak expression in anaplastic colorectal cancers. Taken together, these data suggest that AMACR expression is not hormone-dependent but may in fact be a marker of tumor differentiation.