{"slug": "vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations", "title": "VesselSim: learning 3D blood vessel segmentation without expert annotations", "summary": "Researchers have developed VesselSim, a two-stage framework for 3D blood vessel segmentation that eliminates the need for expert annotations during training by generating 16,500 synthetic angiographic volumes. The system trains a 3D U-Net exclusively on synthetic data and uses a test-time adaptation strategy to bridge the gap to real clinical scans. In zero-shot evaluations across multiple MR and CT datasets, VesselSim achieved performance competitive with state-of-the-art foundation models, potentially reducing reliance on costly expert annotations for medical image analysis.", "body_md": "arXiv:2605.26277v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations", "canonical_source": "https://arxiv.org/abs/2605.26277", "published_at": "2026-05-27 04:00:00+00:00", "updated_at": "2026-05-27 04:27:10.137121+00:00", "lang": "en", "topics": ["computer-vision", "machine-learning", "artificial-intelligence", "neural-networks", "ai-research"], "entities": ["VesselSim", "3D U-Net"], "alternates": {"html": "https://wpnews.pro/news/vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations", "markdown": "https://wpnews.pro/news/vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations.md", "text": "https://wpnews.pro/news/vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations.txt", "jsonld": "https://wpnews.pro/news/vesselsim-learning-3d-blood-vessel-segmentation-without-expert-annotations.jsonld"}}