VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914409193930752 |
|---|---|
| author | Prabhakar, Chinmay Wittmann, Bastian Amiranashvili, Tamaz Büschl, Paul de la Rosa, Ezequiel McGinnis, Julian Wiestler, Benedikt Menze, Bjoern Shit, Suprosanna |
| author_facet | Prabhakar, Chinmay Wittmann, Bastian Amiranashvili, Tamaz Büschl, Paul de la Rosa, Ezequiel McGinnis, Julian Wiestler, Benedikt Menze, Bjoern Shit, Suprosanna |
| contents | Spatial graphs provide a lightweight and elegant representation of curvilinear anatomical structures such as blood vessels, lung airways, and neuronal networks. Accurately modeling these graphs is crucial in clinical and (bio-)medical research. However, the high spatial resolution of large networks drastically increases their complexity, resulting in significant computational challenges. In this work, we aim to tackle these challenges by proposing VesselTok, a framework that approaches spatially dense graphs from a parametric shape perspective to learn latent representations (tokens). VesselTok leverages centerline points with a pseudo radius to effectively encode tubular geometry. Specifically, we learn a novel latent representation conditioned on centerline points to encode neural implicit representations of vessel-like, tubular structures. We demonstrate VesselTok's performance across diverse anatomies, including lung airways, lung vessels, and brain vessels, highlighting its ability to robustly encode complex topologies. To prove the effectiveness of VesselTok's learnt latent representations, we show that they (i) generalize to unseen anatomies, (ii) support generative modeling of plausible anatomical graphs, and (iii) transfer effectively to downstream inverse problems, such as link prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18797 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation Prabhakar, Chinmay Wittmann, Bastian Amiranashvili, Tamaz Büschl, Paul de la Rosa, Ezequiel McGinnis, Julian Wiestler, Benedikt Menze, Bjoern Shit, Suprosanna Computer Vision and Pattern Recognition Spatial graphs provide a lightweight and elegant representation of curvilinear anatomical structures such as blood vessels, lung airways, and neuronal networks. Accurately modeling these graphs is crucial in clinical and (bio-)medical research. However, the high spatial resolution of large networks drastically increases their complexity, resulting in significant computational challenges. In this work, we aim to tackle these challenges by proposing VesselTok, a framework that approaches spatially dense graphs from a parametric shape perspective to learn latent representations (tokens). VesselTok leverages centerline points with a pseudo radius to effectively encode tubular geometry. Specifically, we learn a novel latent representation conditioned on centerline points to encode neural implicit representations of vessel-like, tubular structures. We demonstrate VesselTok's performance across diverse anatomies, including lung airways, lung vessels, and brain vessels, highlighting its ability to robustly encode complex topologies. To prove the effectiveness of VesselTok's learnt latent representations, we show that they (i) generalize to unseen anatomies, (ii) support generative modeling of plausible anatomical graphs, and (iii) transfer effectively to downstream inverse problems, such as link prediction. |
| title | VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.18797 |