An ROC approach for evaluating functional brain MR imaging and postprocessing protocols

Abstract

A method that can be used to evaluate the performance of MRI methods for detecting discrete regional activations using functional MRI is presented. Computer derived receiver-operator-characteristic (ROC) curves have been used to evaluate quantitatively a range of conditions encountered in functional MRI studies. ROC analysis allows multiple acquisition strategies and multiple postprocessing strategies to be quantitatively and objectively compared. The authors first present this analysis technique and then illustrate its use for assessing the relative performances of different functional MRI data acquisition strategies using different gradient echo, echoplanar imaging protocols. In addition, the authors have used the ROC analysis to evaluate and compare several methods for analyzing functional MRI data to extract regions of activation. This approach to assessing the performance of different methods is of general use and can be applied to evaluate other data acquisition protocols and postprocessing methods.