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 obtained his PhD in November, 2023 under the supervision Matteo Maspero, Nico van den Berg and Jan Lagendijk and is currently a Post-doctoral researcher in Computational Imaging Group. Currently, Maarten works on the development of deep learning models for real-time MRI imaging for radiotherapy, including, but not limited to, abdominal and cardiac motion-resolved image reconstruction.

PhD thesis

Real-time MRI-guided radiotherapy with deep learning, 14 November 2023, Utrecht, The Netherlands, ISBN: 978-90-393-7589-1, Utrecht University.

Projects

• Subject motion in MRI
• Deep learning in radiotherapy

Most recent publications

• al. and Maarten Lennart Terpstra. Real-time MRI-guided radiotherapy with deep learning. U, 2023.
• Maarten L. Terpstra, Matteo Maspero, Joost J. C. Verhoeff, and Cornelis A. T. Berg. Accelerated respiratory‐resolved 4D‐MRI with separable spatio‐temporal neural networks. Medical Physics, 2023.
• Maarten L. Terpstra, Matteo Maspero, Alessandro Sbrizzi, and Cornelis A.T. Berg. ⊥-loss: A symmetric loss function for magnetic resonance imaging reconstruction and image registration with deep learning. Medical Image Analysis, 2022.

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