The use of ROC curves in histopathologic decision making

Abstract

The applicability of receiver operator characteristic (ROC) curves to histopathology is presented in three examples, along with a basic discussion of some properties of ROC curves. One major application is in the attempt to define stages in diseases that show a continuous spectrum of histologic patterns, in which the uncertainty of boundary points and the overlap of features makes such definition difficult. Construction and analysis of ROC curves may help to identify the features with the greatest utility, as, for example, in the grading of mucinous carcinomas of the ovary. ROC curves can also be used to assess diagnostic differences between histopathologists, whether they are using different criteria or the same criteria but with different weightings, as, for example, in cervical premalignancy or borderline ovarian tumors.