IMAGE-ANALYSIS AND CATEGORIZATION OF VENTILATION-PERFUSION SCANS FOR THE DIAGNOSIS OF PULMONARY-EMBOLISM USING AN EXPERT-SYSTEM

An expert system was developed that interprets ventilation-perfusion l ung scans. The use of such scans for suspected pulmonary embolism is i deal for computer-assisted diagnosis by expert systems. The data are d igital, only a single disease entity is diagnosed or excluded, and wel l-established diagnostic criteria already exist for visual interpretat ion that can be easily integrated into an expert system. Methods: This expert system is divided into two modules. The first module is respon sible for image analysis, Analysis was performed on the eight standard perfusion images and on single-breath, equilibrium and 3-min washout ventilation images. Each image was analyzed for the presence of region al perfusion or ventilation defects, as determined by pixel values tha t fell 2.2 s.d. below the mean (or above the mean in the case of washo ut images) compared with a database of normal studies. The defect size , segment involved and number of defects were determined. Ventilation and perfusion images were then compared to determine whether defects w ere matched or mismatched. The second program module applied the modif ied Biello's criteria to the data and categorized the scan as normal t o low, intermediate or high probability. Results: A total of 80 patien ts were prospectively studied. An 81% (65 of 80) correlation was obtai ned when the results of the expert system were compared with visual in terpretations made by three experienced nuclear medicine physicians. C onclusion: This study shows that the interpretation of ventilation-per fusion lung scans by an expert system is possible. The technique holds the promise of reducing interobserver variability and assisting less experienced observers in the interpretation of such scans.