Multivariate Image Mining Julia Herold and Tim W. Nattkemper June 9, 2010 Abstract Due to recent advances in sensor technology and a rapid increase in storage capacities, a growing number of intensity values can be recorded and associated to pixel coordinates using new imaging technologies. This growth in dimension can be observed in different scientific areas and this new category of images is referred to as multivariate images (MVI). In these images, an almost arbitrary number of variables is associated to each pixel that represent for instance signal values at different time points, or for different spectral bands or for different imaging parameters or modal- ities. Thus, these images can not longer be interpreted as grey value im- ages or RGB color images and new information technologies are needed. In this review article we summarize the different imaging technologies and recently published approaches to multivariate image mining with a special focus on biomedical applications. Introduction In recent years, microscopy imaging in biomedicine has evolved to a high- throughput and high-content application allowing for an in-detail spatial analy- sis of a biomedical sample. Highly automated platforms are available facilitating a rapid and accurate image acquisition. 1