Rapid and direct quantification of longitudinal relaxation time (T1) in look-locker sequences using an adaptive neural network

Fast and accurate measurement of the longitudinal relaxation time, T₁, has become increasingly important in quantitative estimates of such tissue physiological parameters as perfusion, capillary permeability, and tissue interstitial space using dynamic contrast-enhanced MRI (DCE-MRI). The look-locker (LL) sequence provides accurate T₁ estimates, with the advantages of reduced acquisition time, and a wide range of sampling times post-inversion. In this study, an adaptive neural network (ANN) was trained and employed as an unbiased estimator of T₁. The ANN estimator was trained by simulating the LL signal at different levels of SNR. The results of its application to the simulated data were compared with T₁ maps estimated by conventional methods (simplex method with non-negative least-squares fitting). Experimental results of the ANN method for 19 animals were also compared to the the conventional method, and with values of T₁ reported in literature. The ANN and conventional methods produce estimates that are highly correlated in normal (r = 0.957, p < 0.0001) and tumorous (r = 0.965, p < 0.0001) tissues. It is concluded that the ANN method has very good potential to be used to produce a fast and accurate T₁ map in tissue, and thus to estimate from LL data in DCE studies the temporal change in tissue R₁ that occurs after administration of contrast agent, a measure that plays an important role in quantification of physiological parameters using MRI.