VTrails: Inferring Vessels with Geodesic Connectivity Trees

TL;DR

VTrails is an end-to-end method that accurately extracts vascular trees from angiographic data by leveraging anisotropic fast marching on tensor fields, improving connectivity and structural analysis of vessels.

Contribution

The paper introduces VTrails, a novel approach for extracting vascular trees that enforces connectivity and acyclicity using anisotropic fast marching on tensor fields.

Findings

VTrails accurately extracts vascular trees with high precision and recall.

The method outperforms classical ridge detectors in connectivity assessment.

VTrails is robust to image degradation and preserves vessel connectivity.

Abstract

The analysis of vessel morphology and connectivity has an impact on a number of cardiovascular and neurovascular applications by providing patient-specific high-level quantitative features such as spatial location, direction and scale. In this paper we present an end-to-end approach to extract an acyclic vascular tree from angiographic data by solving a connectivity-enforcing anisotropic fast marching over a voxel-wise tensor field representing the orientation of the underlying vascular tree. The method is validated using synthetic and real vascular images. We compare VTrails against classical and state-of-the-art ridge detectors for tubular structures by assessing the connectedness of the vesselness map and inspecting the synthesized tensor field as proof of concept. VTrails performance is evaluated on images with different levels of degradation: we verify that the extracted vascular network is an acyclic graph (i.e. a tree), and we report the extraction accuracy, precision and recall.