PERFEX - AN EXPERT-SYSTEM FOR INTERPRETING 3D MYOCARDIAL PERFUSION

Interpreting three-dimensional (3D) data is generally recognized as an ill-defined and information-intensive task. The task becomes increasi ngly difficult in the context of medical diagnostic imagery, wherein t he visual information must be interpreted in conjunction with other, n onvisual information. A novel approach is presented to perform the int erpretation of such multidimensional information, concentrating on a m edically important application: the interpretation of 3D tomograms of myocardial perfusion distribution. The overall goal is to assist in th e diagnosis of coronary artery disease. The approach employs knowledge -based methods to process and map the 3D visual information into symbo lic representations, which are subsequently used to infer structure (a natomy) from function (physiology), as well as to interpret the tempor al effects of perfusion redistribution, and assess the extent and seve rity of cardiovascular disease both quantitatively and qualitatively. The knowledge-based system presents the resulting diagnostic recommend ations in both visual and textual forms in an interactive framework, t hereby enhancing overall utility. This paper presents the methodology underlying this approach, including the implementation and testing of this system within an actual clinical environment.