# VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation

arXiv: https://arxiv.org/abs/2603.18797 · HTML: https://mlsanity.com/paper/2603.18797/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 63 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 30 of 40)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Link Prediction Based on Graph Neural Networks](https://mlsanity.com/paper/1802.09691/) (2018)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Shap-E: Generating Conditional 3D Implicit Functions](https://mlsanity.com/paper/2305.02463/) (2023)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation](https://mlsanity.com/paper/2306.17115/) (2023)
- [MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation](https://mlsanity.com/paper/2302.09048/) (2023)
- [Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders](https://mlsanity.com/paper/2412.17808/) (2024)
- [OpenGraph: Towards Open Graph Foundation Models](https://mlsanity.com/paper/2403.01121/) (2024)
- [The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography](https://mlsanity.com/paper/2312.17670/) (2023)
- [Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules](https://mlsanity.com/paper/2310.14753/) (2023)
- [VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs](https://mlsanity.com/paper/2308.02117/) (2023)
- [Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge](https://mlsanity.com/paper/2304.03708/) (2023)
- [Learning Graph Quantized Tokenizers](https://mlsanity.com/paper/2410.13798/) (2024)
- [vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation](https://mlsanity.com/paper/2411.17386/) (2024)
- [G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer](https://mlsanity.com/paper/2409.06322/) (2024)
- [Blood Vessel Geometry Synthesis using Generative Adversarial Networks](https://mlsanity.com/paper/1804.04381/) (2018)
- [VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesis](https://mlsanity.com/paper/2307.03592/) (2023)
- [Hunting imaging biomarkers in pulmonary fibrosis: Benchmarks of the AIIB23 challenge](https://mlsanity.com/paper/2312.13752/) (2023)
- [3D representation in 512-Byte:Variational tokenizer is the key for autoregressive 3D generation](https://mlsanity.com/paper/2412.02202/) (2024)
- [Neural Vector Fields for Implicit Surface Representation and Inference](https://mlsanity.com/paper/2204.06552/) (2022)

## Built on by (most cited first, 2 of 2)

- [SynVA: A Modular Toolkit for Vessel Generation and Aneurysm Editing](https://mlsanity.com/paper/2605.17620/) (2026)
- [End-to-End Autonomous Recursive Arborescence Deformable Flow and Non-Linear Hemodynamics for Patient-Specific Coronary Centerline Extraction](https://mlsanity.com/paper/2610.05900/) (2026)

## Abstract (arXiv)

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.