The role of imaging in healthcare is continuously increasing. Today, medical imaging plays a role in early patient diagnosis, individualized therapy planning, population screening, therapy outcome prediction and assessment, and translational pre-clinical and clinical research. Recent innovations in medical imaging technology have created a tsunami of imaging data, which is revolutionizing diagnosis, therapy planning and follow-up, as well as clinical, preclinical and biomedical research. Moreover, the rapid adoption of digital image archiving and communication makes that large image databases are readily available for multi-modal, multi-temporal, and multi-subject assessment. A consequence is that accurate quantitative image computing has become indispensable. A prerequisite for quantitative image computing is the availability of suitable models that incorporate prior knowledge about the image content and other patient data, including clinical and genetic information. A powerful strategy is to construct such models from the data itself by learning from a representative training set of image instances. In this seminar several clinical applications of this approach will illustrate the opportunities for population and disease modeling, therapy outcome prediction, evidence-based medicine, and predicting missing or unobserved data.