J.M. Suk MSc | People Pages: Find employees & contact details

I am a PhD student from Munich, Germany, working on deep learning for 3D medical data in the form of finite-element meshes and point clouds. I employ graph-convolutional neural networks (GCN) and use symmetry (geometric deep learning) and physics-informed deep learning to boost their performance.

Additionally, I am interested in the mathematical foundations of deep learning through the application of functional analysis and identification of the interplay with dynamical systems and partial differential equations.

I am excited about (super)computers, especially Linux-based systems and clusters. Consequently, I wrote my master's thesis on Hessian-based optimisation of deep neural networks in the context of high performance computing (HPC).

Open master thesis project: I am currently looking for a student to work on the interface of neural ODEs, optical flow and physics-informed neural networks (PINN) for blood flow in arteries. If you like programming (Python, JAX), deep learning and PDEs feel free to reach out to me!

Organisations

Publications

2024

Mesh neural networks for SE(3)-equivariant hemodynamics estimation on the artery wall, Article 108328. Suk, J., de Haan, P., Lippe, P., Brune, C. & Wolterink, J. M.https://doi.org/10.1016/j.compbiomed.2024.108328Generative modeling of living cells with SO(3)-equivariant implicit neural representations, Article 102991. Wiesner, D., Suk, J., Dummer, S., Nečasová, T., Ulman, V., Svoboda, D. & Wolterink, J. M.https://doi.org/10.1016/j.media.2023.102991

2023

SIRE: scale-invariant, rotation-equivariant estimation of artery orientations using graph neural networks. ArXiv.org. Alblas, D., Suk, J. M., Brune, C., Yeung, K. K. & Wolterink, J. M.SE(3) Symmetry Lets Graph Neural Networks Learn Arterial Velocity Estimation from Small DatasetsIn Functional Imaging and Modeling of the Heart: 12th International Conference, FIMH 2023, Lyon, France, June 19–22, 2023, Proceedings (pp. 445-454). Suk, J., Brune, C. & Wolterink, J. M.https://doi.org/10.1007/978-3-031-35302-4_46SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets, 1. ArXiv.org. Suk, J., Brune, C. & Wolterink, J. M.https://doi.org/10.48550/arXiv.2302.08780

2022

Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall, 1. ArXiv.org. Suk, J., de Haan, P., Lippe, P., Brune, C. & Wolterink, J. M.https://doi.org/10.48550/arXiv.2212.05023Mesh convolutional neural networks for wall shear stress estimation in 3D artery modelsIn Statistical Atlases and Computational Models of the Heart. Multi-Disease, Multi-View, and Multi-Center Right Ventricular Segmentation in Cardiac MRI Challenge: 12th International Workshop, STACOM 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27, 2021, Revised Selected Papers (pp. 93-102). Suk, J. M., de Haan, P., Lippe, P., Brune, C. & Wolterink, J. M.https://doi.org/10.1007/978-3-030-93722-5_11Implicit Neural Representations for Generative Modeling of Living Cell ShapesIn Medical Image Computing and Computer Assisted Intervention – MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part IV (pp. 58-67). Springer. Wiesner, D., Suk, J., Dummer, S., Svoboda, D. & Wolterink, J. M.https://doi.org/10.1007/978-3-031-16440-8_6

Research profiles

Courses academic year 2023/2024

Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.

Courses academic year 2022/2023

Address

University of Twente

Zilverling (building no. 11), room 2110
Hallenweg 19
7522 NH Enschede
Netherlands

Navigate to location

University of Twente

Zilverling (building no. 11)
Hallenweg 19
7522 NH Enschede
Netherlands

Navigate to location