I am a scientific researcher in machine learning for medical image analysis from the Netherlands.
Say hello at or
I work as a postdoc in the Pattern Recognition Laboratory of the TU Delft in Delft, the Netherlands, on medical image analysis for osteoarthritis imaging.
Until the end of 2019, I worked as a PhD student and researcher at the Biomedical Imaging Group Rotterdam, part of the Erasmus MC University Medical Center in Rotterdam, the Netherlands. After that, I was part of the Data Science group of the Radboud University in Nijmegen, the Netherlands, where I worked on transfer learning for breast cancer screening and taught deep learning to MSc students.
I work on domain adaptation and feature learning, and their applications in model-based medical image analysis. I am interested in the theoretical and practical aspects of machine learning and computer vision.
Shifting representations — Adventures in cross-modality domain adaptation for medical image analysis.
PhD thesis, Erasmus MC/Erasmus University, Rotterdam, June 2022.
elasticdeform is a Python library for differentiable elastic deformations for N-dimensional images. It works on 2D, 3D and higher-dimensional images as a data augmentation method. It computes gradients for use with TensorFlow or PyTorch.
I was a contributor to Theano when it was still cool.
See my profile on GitHub for a few other projects.
See my profile on Google Scholar or Semantic Scholar for co-authored papers.
Unpaired, unsupervised domain adaptation assumes your domains are already similar.
Medical Image Analysis, July 2023.
Multi-view Analysis of Unregistered Medical Images Using Cross-View Transformers.
Presented at MICCAI 2021, September 2021.
Learning Cross-Modality Representations from Multi-Modal Images.
IEEE Transactions on Medical Imaging, September 2018.
Representation Learning for Cross-Modality Classification.
Presented at the MICCAI 2016 Workshop on Medical Computer Vision, October 2016.
Combining Generative and Discriminative Representation Learning for Lung CT Analysis with Convolutional Restricted Boltzmann Machines.
IEEE Transactions on Medical Imaging, May 2016.
Why Does Synthesized Data Improve Multi-sequence Classification?
Oral presentation at MICCAI 2015, October 2015.
Learning Features for Tissue Classification with the Classification Restricted Boltzmann Machine.
Presented at the MICCAI 2014 Workshop on Medical Computer Vision, September 2014.
I have open access PDFs for some additional papers.
Sample reusability in importance-weighted active learning.
MSc thesis, Delft University of Technology, 2012.
You can also find me here:
After a reasonably successful but unfulfilling start as a student of economics and business, I had great fun as a computer science student at the Delft University of Technology. At the end of 2012 I completed my Master of Science in Media and Knowledge Engineering with a thesis on a theoretical aspect of active learning.
In early 2013 I started as a PhD student at the Biomedical Imaging Group Rotterdam, part of the Department of Radiology of the Erasmus MC University Medical Center in Rotterdam, the Netherlands.
I enjoy programming, tinkering with Linux, and web development. During my studies I worked as a freelance web developer, mostly for De Digitale School and Dalton Voorburg.
See my illustrated archive and old web development articles for some of this earlier work.