Analysis of DCE-MRI Data using a Nonnegative Elastic Net

We present a nonnegative Elastic Net approach for the analysis of Dynamic Contrast-Enhanced Magnetic Resonance Imaging data. A multi-compartment approach is considered, which is translated into a (restricted) least square model selection problem. This is done by using a set of basis functions for a given set of candidate rate constants. The form of the basis functions is derived from a kinetic model and thus describes the contribution of some compartment. Us-ing the Elastic Net estimator, we chose clusters of basis functions, and hence, rate constants of compartments. As further challenge, the estimator has to be restricted to positive regression parameters, which correspond to transfer rates of the compartments. The proposed estimation method is applied to an in-vivo data set.