With the ageing society, there is an urgent need to develop new preventive and therapeutic strategies for common age-related diseases, such as Alzheimer’s disease, the most common form of dementia. MR brain imaging plays an increasingly important role in understanding and diagnosing different forms of dementia.  We will show developments towards a novel computer-aided diagnosis system, which automatically extracts information on brain anatomy, function, connectivity, and pathology from multi-modal MR imaging data, to assist in the early and differential diagnosis of neurodegenerative disease. The system also enables comparing a single subject to reference data obtained from a population imaging study. These reference data are not restricted to simple statistics of individual brain measures: it is even possible to construct a 4D references model of the ageing brain, to which an individual brain can be contrasted. Finally we discuss the potential of integrated analysis of MR brain imaging and genetic data for acquiring new knowledge on the course of dementia.