# Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction

arXiv: https://arxiv.org/abs/2012.07262 · HTML: https://mlsanity.com/paper/2012.07262/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis](https://mlsanity.com/paper/2112.04863/) (2021)
- [PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds](https://mlsanity.com/paper/2210.08305/) (2022)
- [3D Vessel Segmentation with Limited Guidance of 2D Structure-agnostic Vessel Annotations](https://mlsanity.com/paper/2302.03299/) (2023)
- [Modeling and hexahedral meshing of cerebral arterial networks from centerlines](https://mlsanity.com/paper/2201.08279/) (2022)
- [A Hybrid Approach to Full-Scale Reconstruction of Renal Arterial Network](https://mlsanity.com/paper/2303.01837/) (2023)
- [Morphology Edge Attention Network and Optimal Geometric Matching Connection model for vascular segmentation](https://mlsanity.com/paper/2306.01808/) (2023)
- [An automated framework for brain vessel centerline extraction from CTA images](https://mlsanity.com/paper/2401.07041/) (2024)
- [Robust Curve Detection in Volumetric Medical Imaging via Attraction Field](https://mlsanity.com/paper/2408.01159/) (2024)
- [VesselFusion: Diffusion Models for Vessel Centerline Extraction from 3D CT Images](https://mlsanity.com/paper/2603.08135/) (2026)

## Abstract (arXiv)

Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods based on convolutional neural networks (CNNs) may suffer from discontinuities of extracted vessels when segmenting such thin tubular structures from 3D images. We argue that preserving the continuity of extracted vessels requires to take into account the global geometry. However, 3D convolutions are computationally inefficient, which prohibits the 3D CNNs from sufficiently large receptive fields to capture the global cues in the entire image. In this work, we propose a hybrid representation learning approach to address this challenge. The main idea is to use CNNs to learn local appearances of vessels in image crops while using another point-cloud network to learn the global geometry of vessels in the entire image. In inference, the proposed approach extracts local segments of vessels using CNNs, classifies each segment based on global geometry using the point-cloud network, and finally connects all the segments that belong to the same vessel using the shortest-path algorithm. This combination results in an efficient, fully-automatic and template-free approach to centerline extraction from 3D images. We validate the proposed approach on CTA datasets and demonstrate its superior performance compared to both traditional and CNN-based baselines.