PROSTATIC INTRAEPITHELIAL NEOPLASIA (PIN) - PERFORMANCE OF BAYESIAN BELIEF NETWORK FOR DIAGNOSIS AND GRADING

Prostatic intraepithelial neoplasia (PIN) diagnosis and grading are af fected by uncertainties which arise from the fact that almost all know ledge of PIN histopathology is expressed in concepts, descriptive ling uistic terms, and words. A Bayesian belief network (BBN) was therefore used to reduce the problem of uncertainty in diagnostic clue assessme nt, while still considering the dependences between elements in the re asoning sequence. A shallow network was used with an open-tree topolog y, with eight first-level descendant nodes for the diagnostic clues (e vidence nodes), each independently linked by a conditional probability matrix to a root node containing the diagnostic alternatives (decisio n node). One of the evidence nodes was based on the tissue architectur e and the others were based on cell features. The system was designed to be interactive, in that the histopathologist entered evidence into the network in the form of likelihood ratios for outcomes at each evid ence node. The efficiency of the network was tested on a series of 110 prostate specimens, subdivided as follows: 22 cases of non-neoplastic prostate or benign prostatic tissue (NP), 22 PINs of low grade (PINlo w), 22 PINs of high grade (PINhigh), 22 prostatic adenocarcinomas with cribriform pattern (PACcri), and 22 prostatic adenocarcinomas with la rge acinar pattern (PAClgac). The results obtained in the benign and m alignant categories showed that the belief for the diagnostic alternat ives is very high, the values being in general more than 0.8 and often close to 1.0. When considering the PIN lesions, the network classifie d and graded most of the cases with high certainty. However, there wer e some cases which showed values less than 0.8 (13 cases out of 44), t hus indicating that there are situations in which the feature changes are intermediate between contiguous categories or grades. Discrepancy between morphological grading and the BBN results was observed in four out of 44 PIN cases: one PINlow was classified as PINhigh and three P INhigh were classified as PINlow. In conclusion, the network can grade PlN lesions and differentiate them from other prostate lesions with c ertainty. In particular, it offers a descriptive classifier which is r eadily implemented and which allows the use of linguistic, fuzzy varia bles.