SUMMARY Arterial spin labeled (ASL) perfusion MRI provides noninvasive quantification of tissue blood flow in physiological units of ml/100g/min using magnetic labeling of blood water as an endogenous diffusible flow tracer, and is one of the few MRI parameters whose biological basis is known. ASL MRI has primarily been used in the brain to measure cerebral blood flow (CBF), a key physiological parameter that serves a biomarker of cerebrovascular integrity and regional brain function with a broad range of applications in basic and clinical neuroscience research and in clinical care. ASL MRI was originally conceived by our laboratory at the University of Pennsylvania, and we have been responsible for demonstrating many of its technical advances and applications in biomedical research. Although ASL MRI has been translated to clinical use, commercial ASL MRI technologies have failed to keep up with research progress. In response to the special funding mechanism: PAR-18-530, this Academic Industrial Partnership project will provide dedicated resources to further develop, maintain, and deliver state-of-the-art ASL MRI acquisition and processing technologies for clinical research on the Siemens MRI platform, which is the most widely used MRI platform in neuroscience. An Academic Industrial Partnership is needed because market forces for commercial MRI technologies have been insufficient to drive the development of state-of-the-art ASL MRI capabilities in product sequences, yet close collaboration between academia and industry are required to deliver a streamlined capability to users. The resulting technologies will be disseminated free of charge to research sites through a new code exchange platform developed by Siemens. While a major innovation will be the delivery of a free ASL MRI software package featuring state-of-the-art approaches to maximize sensitivity, spatial and temporal resolution, and robustness to artifacts to meet evolving research and clinical requirements for noninvasive quantification of regional cerebral blood flow, next-generation approaches leveraging deep machine learning and other improved computing hardware and algorithms are also proposed to achieve higher spatial and temporal resolution, faster online image reconstructions, and improved robustness to artifacts than are currently possible. The proposed alliance will leverage the interdisciplinary expertise of the investigative team to provide a reliable, reproducible, flexible and user friendly technology for quantifying a key parameter of brain health and function that also has numerous clinical applications, including the evaluation of brain tumors and other organ systems. The feasibility of the proposed work is supported by our preliminary data and track record of ASL MRI technology development and dissemination.