SUBTLE CHANGES IN BENIGN TISSUE ADJACENT TO PROSTATE NEOPLASIA DETECTED WITH A BAYESIAN BELIEF NETWORK

The aim of this paper was to test the usefulness of a Bayesian belief network (BBN) as a decision support system in the uncertainty assessme nt of benign prostatic tissue, either associated or not with inflammat ion or adjacent to prostatic adenocarcinoma (PAC) or prostatic intraep ithelial neoplasia (PIN). A shallow network was used with eight first- level descendant nodes for the diagnostic clues, each independently li nked by a conditional probability matrix to a root node containing the diagnostic alternatives, One diagnostic evidence node was based on th e tissue architecture and the others were based on cell features, The efficacy of the network was tested on a series of 45 simple prostatect omy; specimens, subdivided as follows: benign prostatic tissue not ass ociated with ether diseases (15 cases), associated with acute and/or c hronic inflammation (15 cases), and adjacent to accidentally discovere d PAC or PIN (15 cases), The highest belief values for the diagnostic alternative normal prostate (NP) were obtained in the 15 cases not ass ociated with other diseases, the mean value being 0.996, The 15 cases evaluated in areas with inflammation showed the lowest belief values f or NP (mean 0.774), For the 15 cases evaluated in specimens with PAC o r PIN, the belief values for NP were intermediate between those from n ormal prostatic tissue associated with inflammation and those not asso ciated (mean 0.925), Moreover, it was found that subtle changes were a lso present at a certain distance from the tumour, In conclusion, the network can be used as a decision support system to differentiate with high certainty benign prostate adjacent to PAC or PIN from benign pro static tissue either associated or not with inflammation. The subtle m orphological alterations detected with the BBN may be considered malig nancy-associated changes, (C) 1997 by John Wiley & Sons, Ltd.