VesselFusion: Diffusion Models for Vessel Centerline Extraction from 3D CT Images

TL;DR

VesselFusion introduces a diffusion model that employs a coarse-to-fine approach and voting-based aggregation to improve vessel centerline extraction accuracy and naturalness from 3D CT images.

Contribution

The paper presents VesselFusion, a novel diffusion-based method for vessel centerline extraction that outperforms traditional deterministic models.

Findings

Higher extraction accuracy than conventional methods

Produces more natural vessel structures

Effective on publicly available CT datasets

Abstract

Vessel centerline extraction from 3D CT images is an important task because it reduces annotation effort to build a model that estimates a vessel structure. It is challenging to estimate natural vessel structures since conventional approaches are deterministic models, which cannot capture a complex human structure. In this study, we propose VesselFusion, which is a diffusion model to extract the vessel centerline from 3D CT image. The proposed method uses a coarse-to-fine representation of the centerline and a voting-based aggregation for a natural and stable extraction. VesselFusion was evaluated on a publicly available CT image dataset and achieved higher extraction accuracy and a more natural result than conventional approaches.