In many tertiary clinical care centers, decision-making and treatment selection for acute ischemic stroke is based on magnetic resonance imaging (MRI). The "mismatch" concept aims to segregate the infarct core from potentially salvageable hypo-perfused tissue, the so-called penumbra that is determined from a combination of different MRI modalities. Recent studies have challenged the current concept of tissue at risk stratification targeted to identify the best treatment options for every individual patient. Here, we propose a novel, more elaborate image analysis approach that is based on supervised classification methods to automatically segment and predict the extent of the tissue compartments of interest (healthy, infarct, penumbra regions). The output of the algorithm is a label image including quantitative volumetric information about each tissue compartment. The approach has been evaluated on an image dataset of 10 stroke patients and it compared favorably to currently available tools.