A multiobjective approach to optimizing computerized detection schemes

Computerized detection and classification schemes have the potential of increasing diagnostic accuracy in medical imaging by alerting radiologists to lesions that they initially overlooked and/or assisting in the classification of detected lesions. These schemes, generally referred to as computer-aided diagnosis (CAD) schemes, typically employ multiple parameters such as threshold values or filter weights to arrive at a detection or classification decision. In order for the system to have a high performance, the values of these parameters need to be set optimally. Conventional optimization techniques are designed to optimize a scalar objective function. The task of optimizing the performance of a CAD scheme, however, is clearly a multiobjective problem: we wish to simultaneously improve the sensitivity and reduce the false-positive rate of the system. In this work we investigate a multiobjective approach optimizing CAD schemes. In a multiobjective optimization, multiple objectives are simultaneously optimized, with the objective now being a vector-valued function. The multiobjective optimization problem admits a set of solutions, known as the Pareto-optimal set, which are equivalent in the absence of any information regarding the preferences of the objectives. The performances of the Pareto-optimal solutions can be interpreted as operating points on an optimal ROC or FROC curve, greater than or equal to the points on any possible ROC or FROC curve for a given dataset and given CAD classifier.