Magnetic resonance imaging is a powerful non-invasive technology that provides a unique window to the structure and the function of the body, with high resolution, speed, and biological contrast. The Rosen Lab focuses on new methods and tools to enable unconventional approaches to MRI scanner construction. We develop new acquisition strategies for robust ultra-low magnetic field implementations of MRI focused on brain imaging. We explore opportunities provided by hyperpolarization including in vivo Overhauser DNP, SABRE, and spin-exchange optical pumping. We create new quantitative strategies for the acquisition and the reconstruction of highly-undersampled imaging data including neural network deep learning based approaches such as AUTOMAP that leverage low-cost scalable-compute.