Epifanov Rostislav, Fedotova Yana, Dyachuk Savely, Gostev Alexandr, Karpenko Andrei, Mullyadzhanov Rustam
Department of Mathematics and Mechanics, Novosibirsk State University, Novosibirsk 630090, Russia.
Meshalkin National Medical Research Center, Novosibirsk 630055, Russia.
J Imaging. 2025 Jun 26;11(7):209. doi: 10.3390/jimaging11070209.
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.
血管的精确分割和中心线提取在血管成像应用中至关重要，涵盖从术前规划到血流动力学建模等多个方面。本研究介绍了一种新颖的单阶段方法，该方法使用多任务神经网络同时进行血管分割和中心线提取。我们设计了一种混合架构，它集成了卷积层和图层，以及一个特定任务的损失函数，以有效捕捉分割和中心线提取之间的拓扑关系，利用它们的互补特征。所提出的端到端框架直接将中心线预测为具有实值坐标的折线，从而无需先前方法通常所需的后处理步骤，先前方法要么隐式推断中心线，要么无法确保点的连通性。我们在来自LIDC-IDRI和AMOS数据集的142张胸部和腹部计算机断层血管造影图像的组合数据集上评估了我们的方法。结果表明，与现有技术相比，我们的方法实现了卓越的中心线提取性能（阈值为3毫米时的表面骰子系数：97.65%±2.07%），并获得了最高的亚体素分辨率（阈值为1毫米时的表面骰子系数：72.52%±8.96%）。此外，我们进行了稳健性分析，以评估模型在输入数据的小刚性和可变形变换下的稳定性，并将其稳健性与广泛使用的VMTK工具包进行了基准测试。
