The continuous advent of novel image acquisition technologies has resulted in an increase in the complexity of medical images. Novel image acquisition techniques may contain temporal or spectral dimensions, resulting in 3D, 4D or even 5D images. These additional dimensions provide valuable diagnostic and prognostic information that is currently not fully utilized – manual quantitative expert analysis would be too laborious and time consuming, and automatic tools are not available. Hence, in current clinical practice 4D or 5D medical images are often evaluated as 2D or 3D, so potentially valuable information is ignored. Hence, in this project we aim to develop deep learning techniques for quantitative analysis of 4- and 5-dimensional CT and MR images of the heart for early detection and prevention of cardiovascular disease. The project is part of the TTW Perspectief DLMedia project and partially funded by Philips Healthcare and Pie Medical Imaging.