Knowledge-based visualization of myocardial perfusion tomographic images

A totally automated rule-based expert system developed for interpreting three-dimensional myocardial perfusion distributions obtained from thallium-201 tomographic images is described. Over 200 heuristic rules have been generated for interpreting stress perfusion defects and their characteristics. Perfusion defects are identified in terms of pixels below gender-matched normal patient distributions. Perfusion defects which reversed with time are identified in terms of pixels above gender-matched normal patient distributions. The expert system automatically calculates certainty factors from each perfusion defect to provide the relative certainty associated with the location and shape of each myocardial perfusion defect, as well as with the presence, location, and character of each coronary lesion. Results from a test using a pilot group of 20 patients are given