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

TL;DR

VesselTok introduces a novel tokenization framework for dense 3D vessel-like graphs, enabling efficient encoding, generation, and transfer of complex anatomical structures in biomedical imaging.

Contribution

It proposes a parametric shape-based latent representation for vessel graphs, improving modeling, generation, and transfer capabilities over existing methods.

Findings

VesselTok effectively encodes diverse vessel anatomies.

The learned representations generalize to unseen structures.

Supports realistic graph generation and inverse problem solving.

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.