3D Vessel Graph Generation Using Denoising Diffusion

TL;DR

This paper introduces a novel 3D vessel graph generation method using denoising diffusion models, capable of producing realistic, diverse, and anatomically plausible vessel networks including complex structures like capillaries.

Contribution

It presents the first application of denoising diffusion models for 3D vessel graph generation, with a two-stage process for denoising node coordinates and edges, addressing limitations of previous autoregressive methods.

Findings

Successfully generated diverse vessel graphs from real datasets.

Demonstrated generalizability across different vessel types.

Produced anatomically plausible vessel structures.

Abstract

Blood vessel networks, represented as 3D graphs, help predict disease biomarkers, simulate blood flow, and aid in synthetic image generation, relevant in both clinical and pre-clinical settings. However, generating realistic vessel graphs that correspond to an anatomy of interest is challenging. 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 or specific anatomical structures such as the Circle of Willis. Addressing this gap, we introduce the first application of \textit{denoising diffusion models} in 3D vessel graph generation. Our contributions include a novel, two-stage generation method that sequentially denoises node coordinates and edges. We experiment with two real-world vessel datasets, consisting of microscopic capillaries and major cerebral vessels, and demonstrate the generalizability of our method for producing diverse, novel, and anatomically plausible vessel graphs.