Magnetic resonance imaging has tremendous potential to illuminate ischemic stroke pathophysiology and guide rational treatment decisions. Clinical applications to date have been largely limited to trials. However, recent analyses of the major clinical studies have led to refinements in selection criteria and improved understanding of the potential implications for the risk vs. benefit of thrombolytic therapy. In parallel, preclinical studies have provided complementary information on the evolution of stroke that is difficult to obtain in humans due to the requirement for continuous or repeated imaging and pathological verification. We review the clinical and preclinical advances that have led to perfusion–diffusion mismatch being applied in phase 3 randomized trials and, potentially, future routine clinical practice.