BELIEF NETWORK FOR GRADING PROSTATE LESIONS

Authors
BIBBO M BARTELS PH PFEIFER T THOMPSON D MINIMO C DAVIDSON HG
Citation
M. Bibbo et al., BELIEF NETWORK FOR GRADING PROSTATE LESIONS, Analytical and quantitative cytology and histology, 15(2), 1993, pp. 124-135
Citations number
7
Categorie Soggetti
Cytology & Histology
Journal title
Analytical and quantitative cytology and histology → ACNP
ISSN journal
08846812
Volume
15
Issue
2
Year of publication
1993
Pages
124 - 135
Database
ISI
SICI code
0884-6812(1993)15:2<124:BNFGPL>2.0.ZU;2-P
Abstract
A Bayesian belief network for grading prostatic lesions into eight pri mary Gleason grades was developed and tested. The network employs 13 d iagnostic clues, 8 based on tissue architectural features and 5 based on nuclear features. For every diagnostic clue, three to five differen t outcomes are specified by membership functions. The network works in a robust fashion and attained agreement with consensus visual grading in 241 of 256 microscopic fields.