arXiv:2605.26277v2 Announce Type: replace 
Abstract: Blood vessel segmentation is a core task in medical image analysis for the care of vascular diseases and surgical planning, yet the challenges of providing expert vascular annotations pose a major obstacle for the progress of related deep learning techniques. To address this, we propose VesselSim, a two-stage framework for universal 3D blood vessel segmentation that eliminates the need for real annotated data during training. First, we introduce a stochastic, geometry-driven vascular simulation framework that models recursive branching, curvature-controlled growth, and collision-aware topology, followed by domain-randomized intensity synthesis to generate 16,500 anatomically plausible 3D angiographic volumes. Second, a 3D U-Net is trained solely on this synthetic data. To bridge the domain gap from synthetic to real images at inference time, we introduce a test-time adaptation strategy via a self-supervised mask reconstruction decoder, enabling adaptation to unseen clinical scans without prior domain knowledge. We evaluate VesselSim in a zero-shot setting on multiple real-world datasets spanning MR and CT across several anatomical regions, including the brain and kidneys. Despite being trained exclusively on synthetic data, VesselSim achieves performance competitive with state-of-the-art vascular segmentation foundation models. These findings suggest that learning vessel geometry from synthetic tubular structures is effective for robust cross-domain generalization, substantially reducing the reliance on acquired medical imaging data and more importantly, expert annotations.

تم تقديم VesselSim كإطار عمل من مرحلتين لتجزئة الأوعية الدموية ثلاثية الأبعاد، مما يلغي الحاجة إلى التعليقات التوضيحية من الخبراء أثناء التدريب، باستخدام إطار محاكاة وعائية عشوائية لتوليد بيانات اصطناعية لتدريب نموذج 3D U-Net.

VesselSim se ha presentado como un marco de dos etapas para la segmentación de vasos sanguíneos en 3D que elimina la necesidad de anotaciones de expertos durante el entrenamiento, utilizando un marco de simulación vascular estocástica para generar datos sintéticos para entrenar un modelo 3D U-Net.

VesselSim a été introduit comme un cadre en deux étapes pour la segmentation des vaisseaux sanguins en 3D, éliminant le besoin d'annotations d'experts pendant l'entraînement, en utilisant un cadre de simulation vasculaire stochastique pour générer des données synthétiques pour entraîner un modèle 3D U-Net.

VesselSim has been introduced as a two-stage framework for 3D blood vessel segmentation that eliminates the need for expert annotations during training, utilizing a stochastic vascular simulation framework to generate synthetic data for training a 3D U-Net model.