Digital knowledge and diagnostic information

The long term objective of this research was the development of objective, digitally defined procedures for histopathologic assessment. The developmen t of procedures based on digital knowledge had as its first aim the design of a machine vision system with image understanding capability (ie, capable of autonomous processing and analyses of istopathologic imagery). Next, hi stometric and karyometric diagnostic information extraction led to highly s pecific characterization of nuclei and lesions. Based on such detailed char acterizations, we were able to derive progression curves for prostatic, col onic, breast epithelial, and esophageal lesions. The specific signatures of nuclei and lesions revealed substantial diversity among lesions of the sam e visual-diagnostic grade; profiles of deviation of nuclei from a normal st andard were derived to provide a novel, additional level of diagnostically discriminating features. Knowledge guided machine vision opens the way to a n extremely specific characterization of nuclei and lesions, which may allo w better prediction of biological behavior and, thus, more accurate individ ual patient targeted prognosis.