Machine Learning for Quantitative MR Image Reconstruction

In the last years, the design of image reconstruction methods in the field ofquantitative Magnetic Resonance Imaging (qMRI) has experienced a paradigmshift. Often, when dealing with (quantitative) MR image reconstructionproblems, one is concerned with solving one or a couple of ill-posed inverseproblems which require the use of advanced regularization methods. Anincreasing amount of attention is nowadays put on the development ofdata-driven methods using Neural Networks (NNs) to learn meaningful priorinformation without the need to explicitly model hand-crafted priors. Inaddition, the available hardware and computational resources nowadays offer thepossibility to learn regularization models in a so-called model-aware fashion,which is a unique key feature that distinguishes these models fromregularization methods learned in a more classical, model-agnostic manner.Model-aware methods are not only tailored to the considered data, but also tothe class of considered imaging problems and nowadays constitute thestate-of-the-art in image reconstruction methods. In the following chapter, weprovide the reader with an extensive overview of methods that can be employedfor (quantitative) MR image reconstruction, also highlighting their advantagesand limitations both from a theoretical and computational point of view.