Identification of the ischemic penumbra in the acute stroke clinical setting is an important goal for stroke researchers and clinicians. Various models for imaging the penumbra with MRI have been proposed, including the pioneering diffusion-perfusion mismatch model and later multivariate approaches. A number of multicenter clinical trials are now under way to test these models and confirm the utility of MRI-based treatment decisions. Present knowledge about MRI visualization of the salvageable penumbra suggests a promising future in which MRI studies are performed routinely in the acute stroke setting and the data provided by these MRI studies assist in individualizing therapeutic decisions and identifying effective therapies that can be delivered at late time points.