The Robust Vessel Segmentation and Centerline Extraction: One-Stage Deep Learning Approach

Abstract

The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65%±2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52%±8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit.

Keywords: computed tomography angiography images; multitask neural network; one-stage centerline reconstruction; vascular modeling toolkit; vessel centerline extraction; vessel segmentation.

Figure A1

Examples of ground truth segmentation masks (shown in white) and segmentation results (shown in red) for the proposed method and nnU-net.

Figure 1

Overview of the proposed hybrid network.

Figure 2

Example centerline reconstructions across different methods [34].

Figure 3

Examples of centerline reconstructions generated by the proposed method and the VMTK for input data subjected to small geometric deformations. White grid on CTA slices used as reference to visualize deformation. Green—proposed method, blue—VMTK, black—ground truth.

Figure 4

Comparison of centerline reconstructions generated by the proposed method: green—CTA with artifacts, blue—CTA without artifacts, black—ground truth.