Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction

TL;DR

This paper introduces a hybrid learning method combining CNNs and point-cloud networks to improve the continuity and accuracy of 3D vessel centerline extraction from medical images, addressing the limitations of traditional CNN approaches.

Contribution

It presents a novel hybrid framework that leverages local CNN features and global point-cloud geometry for efficient, continuous vessel centerline extraction in 3D images.

Findings

Outperforms traditional and CNN-based methods on CTA datasets

Achieves continuous vessel centerlines with higher accuracy

Demonstrates efficiency and fully-automatic operation

Abstract

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.