Background
Maarten Terpstra completed his Bachelors and Masters of Science at the University of Groningen (the Netherlands) in Computing Science in 2010-2016. During his Master he gained an interest in computer vision and visualization, which introduced him to deep learning. After briefly working at the Royal Netherlands Meteorological Institute as software developer, he found the opportunity to further develop his interest in deep learning at the radiotherapy department of the UMC Utrecht, which also introduced him to the magic of MRI.
Maarten is currently a PhD student in the Radiotherapy department of the UMC Utrecht and the Computational Imaging Group under the supervision Matteo Maspero, Nico van den Berg and Jan Lagendijk. During his PhD he works within the RESOLVE project, which is about enabling MR guided radiotherapy of moving abdominal tumors and organs by development of a dense eLement receiver array and highly undersampled, parallel MRI. Within this project Maarten primarily develops deep learning models for real-time imaging and motion estimation during treatment on the MR-linac.
Projects
Most recent publications
- ⊥-loss: A symmetric loss function for magnetic resonance imaging reconstruction and image registration with deep learning. Medical Image Analysis, 2022.
- Real‐time 3D motion estimation from undersampled MRI using multi‐resolution neural networks. Medical Physics, 2021.
- Deep learning-based image reconstruction and motion estimation from undersampled radial k-space for real-time MRI-guided radiotherapy. Physics in Medicine & Biology, 2020.
Keywords: Deep learning | Motion estimation/correction | (non)-Cartesian image reconstruction | MR-guided radiotherapy
Social media and other resources
Email: m.l.terpstra-5@umcutrecht.nl |
ORCiD |
Google Scholar |
ResearchGate |
LinkedIn