Rasmus R. Paulsen

I am an associate professor at the Section for Image Analysis and Computer Graphics (IACG) at the Department for Applied Mathematics and Computer Science (DTU Compute) at the Technical University of Denmark (DTU).

My research interests include surface based medical image analysis, computational geometry, deep learning, geometric deep learning and the application of advanced image analysis in clinical environments.

Traditionally medical image analysis has tackled problems in 2D images coming from for example X-ray machines or 3D images from computed tomography or magnetic resonance machines. Consequently, many algorithms working on volumetric data have been developed. An example is image registration where pre- and post-operative scannings are aligned and compared for evaluating surgery outcome. An alternative representation is surfaces that for example can represent boundaries between anatomies. Surfaces can also come directly from surface scanners (of for example the human face). My primary research focus is the analysis of surfaces from the medical domain.

Recently, deep learning has been applied to meshes and a new area of research named geometric deep learning has emerged. We have a strong focus on this research area and are applying geometric deep learning to for example face analysis and to plan cardiac interventions.

We have also had a long interest in shape and appearance models and are currently combining state-of-the-art of statistical shape modelling with the recent advantages within geometric deep learning.

I am responsible for courses in medical image analysis and I supervise several PhD, master, and bachelor students.