Inference network-based analyses of the histopathological effects of androgen deprivation on prostate cancer

The evaluation of prostate cancer histology Following hormonal therapy ofte n represents a diagnostic problem for the pathologist, Previous studies hav e shown that an inference or Bayesian belief network (BBN) offers a descrip tive classifier useful for the accurate analysis of morphological changes i n individual cases of prostate neoplasia, Three different BBNs were evaluat ed in 94 cancer foci present in 20 radical prostatectomy (RP) specimens and in the matching biopsies in which the initial diagnosis of prostatic adeno carcinoma was made. Ten RP specimens mere from patients treated with total androgen ablation or combination endocrine therapy (CET) before surgery. Th e first and second BBN allowed the identification with high certainty of th e cancer foci present in the biopsies and RP specimens, as well as their Gl eason grade, the belief value often being close to 1.0. The results of the second BBN showed a good correspondence between the Gleason grade given in the biopsies and that in the RP specimens, except in the surgical material of the treated patients, in which upgrading was always present. The third B BN showed the existence of three subgroups in treated RP specimens, one wit h morphological effect, another with poor effect, and the third with the hi stology of untreated (i.e. unaffected) cancer. In conclusion, an inference network-based analysis allows the characterization of treated prostate canc ers according to the degree of histopathological change. Copyright (C) 1999 John Wiley & Sons, Ltd.