Semi-Supervised Learning for Spatially Regularized Quantitative MRI Reconstruction - Application to Simultaneous T1, B0, B1 Mapping

Typically, in quantitative MRI, an inverse problem of finding parameter maps from magnitude images has to be solved. Neural networks can be applied to replace non-linear regression models and implicitly learn a suitable spatial regularization. However, labeled training data is often limited. Thus, we propose a combination of training on synthetic data and on unlabeled in-vivo data utilizing pseudo-labels and a Noise2Self-inspired technique. We present a convolutional neural network trained to predict T1, B0, and B1 maps and their estimated aleatoric uncertainties from a single WASABITI scan.