MACHINE VISION-BASED HISTOMETRY OF PREMALIGNANT AND MALIGNANT PROSTATIC LESIONS

The implementation of knowledge-guided control of the processing and s egmentation of histopathologic images of prostatic lesions has made au tomated analysis and interpretation possible. To establish corresponde nce between histopathologic concepts, terms and diagnostic criteria, a nd computed histometric entities, ''interpretive transforms'' are intr oduced. Scene segmentation is controlled by an expert system following a model-based reasoning process. The expert system is structured as a n associative network with frames at each node, which controls a knowl edge file and a large library of image processing algorithms.