Ruud van Sloun is an Assistant Professor in the Signal Processing Systems group of the Electrical Engineering department at Eindhoven University of Technology (TU/e). He works on advanced sensing and signal processing algorithms, with a special focus on deep learning methods for image formation and reconstruction problems. He has a background in probabilistic signal processing for ultrasound-based cancer localization and exploiting signal structure and models to derive optimal estimators. After his PhD, this background has become intertwined with machine and deep learning, to develop powerful signal processing solutions that efficiently leverage both data and model-based signal structure. Applications span from ultrasound beamforming and image formation to clutter suppression and super-resolution imaging.
Van Sloun has contributed to over 40 journal publications and 4 patents. In 2019, he received a RUBICON grant on deep learning for next-gen ultrasound from The Netherlands Organization for Scientific Research (NWO), and in 2021 the Google Faculty Research award on model-based deep learning for imaging.
I aim at achieving better, faster, and more widely accessible (medical) imaging through the design of intelligent systems that efficiently learn how to optimally and autonomously sense, process, and interpret real-world signals.
Ruud van Sloun studied Electrical Engineering at Eindhoven University of Technology (TU/e) where he received the MSc and PhD degrees (both cum laude) in 2014 and 2018, respectively. In January 2018, he joined TU/e as an Assistant Professor. Since then, he has been working on deep learning and signal processing for diagnostic (imaging) applications, spending a significant amount of time at foreign research institutes. Van Sloun also acts as a kickstart-AI fellow for Philips Research, where he works one day per week.
Deep learning in ultrasound imagingProceedings of the IEEE (2020)
Super-resolution Ultrasound Localization Microscopy through Deep LearningIEEE Transactions on Medical Imaging (2021)
Adaptive ultrasound beamforming using deep learningIEEE Transactions on Medical Imaging (2020)
Deep probabilistic subsampling for task-adaptive compressed sensing(2020)
Learning sub-sampling and signal recovery with applications in ultrasound imagingIEEE Transactions on Medical Imaging (2020)