Self-Supervised Synthetic Cerebral Vessel Tree Generation using Semantic Signed Distance Fields

Thijs P. Kuipers, Praneeta R. Konduri, Erik J Bekkers, Henk Marquering
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:803-820, 2026.

Abstract

Advances in in-silico clinical trails for the development of novel treatment and devices for acute ischemic stroke have driven the creation of synthetic virtual patient populations to address the lack of large real-world datasets. Recent work proposed a method for generating semantic vascular centerline tree of the major cerebral arteries using pointcloud diffusion. However, this approach relies on separate post-processing algorithms to reconstruct the vessel tree topology, which does not generalize well to more topologically complex trees. To overcome this limitation, we introduce semantic signed distance fields for modeling cerebral vessel trees in a fully self-supervised manner. Our approach bypasses the need for separate reconstruction of the tree topology, and can be trained directly on shape-surfaces. Our method combines a variational autoencoder for encoding shapes to robust latent shape representations with a latent-diffusion model for generating synthetic vessel trees. By generating surface geometry directly, our approach eliminates the need for post-processing steps, enabling the generation of high-quality and topologically complex cerebral vessel trees.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-kuipers26a, title = {Self-Supervised Synthetic Cerebral Vessel Tree Generation using Semantic Signed Distance Fields}, author = {Kuipers, Thijs P. and Konduri, Praneeta R. and Bekkers, Erik J and Marquering, Henk}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {803--820}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/kuipers26a/kuipers26a.pdf}, url = {https://proceedings.mlr.press/v301/kuipers26a.html}, abstract = {Advances in in-silico clinical trails for the development of novel treatment and devices for acute ischemic stroke have driven the creation of synthetic virtual patient populations to address the lack of large real-world datasets. Recent work proposed a method for generating semantic vascular centerline tree of the major cerebral arteries using pointcloud diffusion. However, this approach relies on separate post-processing algorithms to reconstruct the vessel tree topology, which does not generalize well to more topologically complex trees. To overcome this limitation, we introduce semantic signed distance fields for modeling cerebral vessel trees in a fully self-supervised manner. Our approach bypasses the need for separate reconstruction of the tree topology, and can be trained directly on shape-surfaces. Our method combines a variational autoencoder for encoding shapes to robust latent shape representations with a latent-diffusion model for generating synthetic vessel trees. By generating surface geometry directly, our approach eliminates the need for post-processing steps, enabling the generation of high-quality and topologically complex cerebral vessel trees.} }
Endnote
%0 Conference Paper %T Self-Supervised Synthetic Cerebral Vessel Tree Generation using Semantic Signed Distance Fields %A Thijs P. Kuipers %A Praneeta R. Konduri %A Erik J Bekkers %A Henk Marquering %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-kuipers26a %I PMLR %P 803--820 %U https://proceedings.mlr.press/v301/kuipers26a.html %V 301 %X Advances in in-silico clinical trails for the development of novel treatment and devices for acute ischemic stroke have driven the creation of synthetic virtual patient populations to address the lack of large real-world datasets. Recent work proposed a method for generating semantic vascular centerline tree of the major cerebral arteries using pointcloud diffusion. However, this approach relies on separate post-processing algorithms to reconstruct the vessel tree topology, which does not generalize well to more topologically complex trees. To overcome this limitation, we introduce semantic signed distance fields for modeling cerebral vessel trees in a fully self-supervised manner. Our approach bypasses the need for separate reconstruction of the tree topology, and can be trained directly on shape-surfaces. Our method combines a variational autoencoder for encoding shapes to robust latent shape representations with a latent-diffusion model for generating synthetic vessel trees. By generating surface geometry directly, our approach eliminates the need for post-processing steps, enabling the generation of high-quality and topologically complex cerebral vessel trees.
APA
Kuipers, T.P., Konduri, P.R., Bekkers, E.J. & Marquering, H.. (2026). Self-Supervised Synthetic Cerebral Vessel Tree Generation using Semantic Signed Distance Fields. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:803-820 Available from https://proceedings.mlr.press/v301/kuipers26a.html.

Related Material