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

• URL: http://arxiv.org/abs/2603.18797v1
• Date: Thu, 19 Mar 2026 11:46:21 GMT
• Title: VesselTok: Tokenizing Vessel-like 3D Biomedical Graph Representations for Reconstruction and Generation
• Abstract summary: VesselTok is a framework that approaches spatially dense graphs from a parametric shape perspective.<n>We learn a novel latent representation conditioned on centerline points to encode neural implicit representations of vessel-like, tubular structures.<n>We demonstrate VesselTok's performance across diverse anatomies, including lung airways, lung vessels, and brain vessels.
• Score: 5.5556283437830665
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VesselSim: learning 3D blood vessel segmentation without expert annotations [7.634402582162916]
  We propose VesselSim, a two-stage framework for universal 3D blood vessel segmentation.<n>A 3D U-Net is trained solely on synthetic data to generate 16,500 anatomically plausible 3D angiographic volumes.<n>VesselSim achieves competitive performance with state-of-the-art segmentation foundation models.
  arXiv  Detail & Related papers  (2026-05-25T19:04:18Z)
• Vesselpose: Vessel Graph Reconstruction from Learned Voxel-wise Direction Vectors in 3D Vascular Images [2.8991059698468287]
  We propose an approach to extract topologically more accurate vascular graphs from 3D image data.<n>Our approach achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2026-05-01T09:34:39Z)
• Semantically Consistent Discrete Diffusion for 3D Biological Graph Modeling [2.737421165924947]
  We propose a novel 3D biological graph generation method that adheres to structural and semantic plausibility conditions.<n>Our method demonstrates superior performance on two real-world datasets, human circle of Willis and lung airways.
  arXiv  Detail & Related papers  (2025-07-07T10:29:54Z)
• Recursive Variational Autoencoders for 3D Blood Vessel Generative Modeling [0.7722830505405722]
  We developed a Recursive variational Neural Network (RvNN) that fully exploits the hierarchical organization of the vessel.<n>RvNN learns a low-dimensional manifold encoding branch connectivity along with geometry features describing the target surface.<n>We generate 3D models of blood vessels that are both accurate and diverse, which is crucial for medical and surgical training, hemodynamic simulations, and many other purposes.
  arXiv  Detail & Related papers  (2025-06-17T18:47:27Z)
• A Graph-Based Framework for Interpretable Whole Slide Image Analysis [86.37618055724441]
  We develop a framework that transforms whole-slide images into biologically-informed graph representations.<n>Our approach builds graph nodes from tissue regions that respect natural structures, not arbitrary grids.<n>We demonstrate strong performance on challenging cancer staging and survival prediction tasks.
  arXiv  Detail & Related papers  (2025-03-14T20:15:04Z)
• End-to-end Stroke imaging analysis, using reservoir computing-based effective connectivity, and interpretable Artificial intelligence [42.52549987351643]
  We propose a reservoir computing-based and directed graph analysis pipeline. The goal of this pipeline is to define an efficient brain representation for connectivity in stroke data. This representation is used within a directed graph convolutional architecture and investigated with explainable artificial intelligence (AI) tools.
  arXiv  Detail & Related papers  (2024-07-17T13:34:05Z)
• 3D Vessel Graph Generation Using Denoising Diffusion [4.100929120985704]
  Blood vessel networks, represented as 3D graphs, help predict disease biomarkers, simulate blood flow, and aid in synthetic image generation. Previous methods aimed at generating vessel trees mostly in an autoregressive style and could not be applied to vessel graphs with cycles such as capillaries. We introduce the first application of textitdenoising diffusion models in 3D vessel graph generation.
  arXiv  Detail & Related papers  (2024-07-08T11:39:21Z)
• Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields [56.69755544814834]
  We present evidence suggesting that depthwise convolutional kernels are effectively replicating the biological receptive fields observed in the mammalian retina. We propose a scheme that draws inspiration from the biological receptive fields.
  arXiv  Detail & Related papers  (2024-01-18T18:06:22Z)
• Learning Multimodal Volumetric Features for Large-Scale Neuron Tracing [72.45257414889478]
  We aim to reduce human workload by predicting connectivity between over-segmented neuron pieces. We first construct a dataset, named FlyTracing, that contains millions of pairwise connections of segments expanding the whole fly brain. We propose a novel connectivity-aware contrastive learning method to generate dense volumetric EM image embedding.
  arXiv  Detail & Related papers  (2024-01-05T19:45:12Z)
• Deep Feature Fusion via Graph Convolutional Network for Intracranial Artery Labeling [9.85779770378859]
  Intracranial arteries are critical blood vessels that supply the brain with oxygenated blood. Various machine learning algorithms have been carried out for automation in the anatomical labeling of cerebral arteries. This study investigates a novel graph convolutional neural network with deep feature fusion for cerebral artery labeling.
  arXiv  Detail & Related papers  (2022-05-22T06:11:21Z)
• An explainability framework for cortical surface-based deep learning [110.83289076967895]
  We develop a framework for cortical surface-based deep learning. First, we adapted a perturbation-based approach for use with surface data. We show that our explainability framework is not only able to identify important features and their spatial location but that it is also reliable and valid.
  arXiv  Detail & Related papers  (2022-03-15T23:16:49Z)
• Hyperbolic Graph Neural Networks: A Review of Methods and Applications [61.49208407567829]
  This survey paper provides a comprehensive review of the rapidly evolving field of Hyperbolic Graph Learning (HGL)<n>We systematically categorize and analyze existing methods dividing them into (1) hyperbolic graph embedding-based techniques, (2) graph neural network-based hyperbolic models, and (3) emerging paradigms.<n>We extensively discuss diverse applications of HGL across multiple domains, including recommender systems, knowledge graphs, bioinformatics, and other relevant scenarios.
  arXiv  Detail & Related papers  (2022-02-28T15:08:48Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation [57.20783326661043]
  We introduce a novel similarity measure termed centerlineDice (short clDice) We theoretically prove that clDice guarantees topology preservation up to homotopy equivalence for binary 2D and 3D segmentation. We benchmark the soft-clDice loss on five public datasets, including vessels, roads and neurons (2D and 3D)
  arXiv  Detail & Related papers  (2020-03-16T16:27:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.