Problems in applying expert system technology to radiographic image interpretation

Abstract

A prototype expert system was developed to study the problems applying expert system technology to radiographic image interpretation. The Radiographic Image Interpretation System (RIIS) was developed on a microcomputer using Turbo Prolog, a low cost implementation of the prolog programming language. The present implementation of RIIS was developed to highlight potential problems in applying expert system technology in the evaluation of radiographic images. It was believed that the evaluation of this prototype expert system should include a large number of users unfamiliar with the program's use as this would probably be the case in clinical use of an image interpretation expert system. At present, the expert system deals with a limited domain of focal bony lesions. Twenty cases of pathologically proven bony lesions of varying difficulty were used to evaluate potential problems in the use of this expert system technology. RIIS, with the 20 sample cases, was presented as an exhibit at the 1987 Radiological Society of North America (RSNA) meeting to evaluate the potential problems with inexperienced users. These results were compared with those of experienced users. When a musculoskeletal radiologist, familiar with the programs use, provided the "proper description," the program averaged the correct diagnosis in the top five 80% of the time. During the program's use at the RSNA meeting, the program selected the correct diagnosis in the top five 22% of the time.