Performance Studies for Validation of CAD Systems

Evaluation of computational intelligence (CI) systems designed to improve the performance of a human operator is complicated by the necessity of including the effect of human variability. In this paper we examine the methodology available for addressing this variability within the context of medical imaging computer-assisted diagnosis (CAD) systems. We present a review of currently available techniques and give an example using computer simulation. It is shown how advanced statistical techniques lead to more efficient measures of CAD performance.