no code implementations • 12 Mar 2024 • Julian Suk, Baris Imre, Jelmer M. Wolterink
We propose LaB-GATr, a transfomer neural network with geometric tokenisation that can effectively learn with large-scale (bio-)medical surface and volume meshes through sequence compression and interpolation.
no code implementations • 9 Nov 2023 • Dieuwertje Alblas, Julian Suk, Christoph Brune, Kak Khee Yeung, Jelmer M. Wolterink
Hence, SIRE can be trained with arbitrarily oriented vessels with varying radii to generalise to vessels with a wide range of calibres and tortuosity.
1 code implementation • 18 Apr 2023 • David Wiesner, Julian Suk, Sven Dummer, Tereza Nečasová, Vladimír Ulman, David Svoboda, Jelmer M. Wolterink
Finally, we show how microscopy images of living cells that correspond to our generated cell shapes can be synthesized using an image-to-image model.
1 code implementation • 17 Feb 2023 • Julian Suk, Christoph Brune, Jelmer M. Wolterink
We demonstrate how to construct an SE(3)-equivariant GNN that is independent of the spatial orientation of the input mesh and show how this reduces the necessary amount of training data compared to a baseline neural network.
1 code implementation • 9 Dec 2022 • Julian Suk, Pim de Haan, Phillip Lippe, Christoph Brune, Jelmer M. Wolterink
Computational fluid dynamics (CFD) is a valuable asset for patient-specific cardiovascular-disease diagnosis and prognosis, but its high computational demands hamper its adoption in practice.
1 code implementation • 13 Jul 2022 • David Wiesner, Julian Suk, Sven Dummer, David Svoboda, Jelmer M. Wolterink
Deep generative models for cell shape synthesis require a light-weight and flexible representation of the cell shape.
1 code implementation • 10 Sep 2021 • Julian Suk, Pim de Haan, Phillip Lippe, Christoph Brune, Jelmer M. Wolterink
In this work, we propose to instead use mesh convolutional neural networks that directly operate on the same finite-element surface mesh as used in CFD.