Science, science is great. I love science. With any luck, it'll save us all. Isaac Brock.
Erik Bekkers is a postdoctoral researcher in the Mathematical Image Analysis group at the Department of Mathematics and Computer Science at Eindhoven University of Technology (TU/e). His areas of expertise include differential geometry, machine learning and medical image analysis. With his current research on the mathematical foundations of deep learning he addresses core problems in medical image analysis based on generic mathematical solutions that enable a wide application scope. His research is highly interdisciplinary in nature (from advanced mathematics to applied engineering research and clinical science) which is reflected by his industrial and clinical involvement through collaborations and a previous Ph.D. project (cum laude) carried out in a joint position at medical device company i-Optics B.V. (the Hague, NL) and at Biomedical Engineering (TU/e). For his pioneering work in the field of geometric deep learning he was awarded the prestigious Young Scientist Award at MICCAI, the premier international conference in the field of medical image computing, and the Philips Impact Award at MIDL, the international conference on Medical Imaging with Deep Learning.
Erik Bekkers received his M.Sc. degree in Biomedical Engineering in 2012 at Eindhoven University of Technology (TU/e), the Netherlands. In January 2017 he received his Ph.D. degree (cum laude) for his thesis "Retinal Image Analysis using Sub-Riemannian Geometry in SE(2)," which was conducted in a combined position at Biomedical Engineering at TU/e and at the medical device company i-Optics B.V., the Hague, the Netherlands. He currently is a postdoctoral researcher at the Department of Mathematics and Computer Science at TU/e, working on the application of Lie group (and control) theory in medical image analysis and machine learning.
Roto-translation covariant convolutional networks for medical image analysis21st International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2018 (2018)
A PDE approach to data-driven sub-Riemannian geodesics in SE(2)SIAM Journal on Imaging Sciences (2015)
Template matching via densities on the roto-translation groupIEEE Transactions on Pattern Analysis and Machine Intelligence (2018)
Nilpotent approximations of sub-Riemannian distances for fast perceptual grouping of blood vessels in 2D and 3DJournal of Mathematical Imaging and Vision (2018)
Fourier transform on the homogeneous space of 3D positions and orientations for exact solutions to linear PDEsEntropy (2019)
Prizes & Grants
Centre for Analysis, Scientific Computing, and ApplicationsMICCAI Young Scientist Award (2018)
Centre for Analysis, Scientific Computing, and ApplicationsPhilips Impact Award (2018)
Centre for Analysis, Scientific Computing, and Applications W&IContext-aware Artificial Intelligence in medical image analysis (2019)