Validity of the Gaussian assumption in the analysis of ROC data obtained from scintigraphic-like images

Receiver operator characteristic (ROC) analysis without truth

Receiver operator characteristic (ROC) analysis, the preferred method of evaluating diagnostic imaging tests, requires an independent assessment of the true state of disease, which can be difficult to obtain and is often of questionable accuracy. A new method of analysis is described which does not require independent truth data and which can be used when several accurate tests are being compared. This method uses correlative information to estimate the underlying model of multivariate normal distributions of disease-positive and disease-negative patients. The method is shown to give results equivalent to conventional ROC analysis in a comparison of computed tomography, radionuclide scintigraphy, and magnetic resonance imaging for liver metastasis. When independent truth is available, the method can be extended to incorporate truth data or to evaluate the consistency of the truth data with the imaging data.

ROC steady: a receiver operating characteristic curve that is invariant relative to selection bias

This paper describes a simple method for constructing receiver operating characteristic (ROC) curves based on boundary conditions that restrict its theoretical shape. The resultant curve is identical to that for logistic distributions with equal variance. Although the underlying assumptions are highly restrictive, this method nevertheless possesses several attractive properties which are illustrated by its application to 2,567 patients undergoing a variety of noninvasive diagnostic tests for coronary artery disease: 1) the area under the curve is defined by a single parameter; 2) the associated standard deviation is analytically defined and readily computed; 3) the curve is completely invariant with respect to selection bias.