# VesselSim: learning 3D blood vessel segmentation without expert annotations

arXiv: https://arxiv.org/abs/2605.26277 · HTML: https://mlsanity.com/paper/2605.26277/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 12 of 12)

- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography](https://mlsanity.com/paper/2312.17670/) (2023)
- [Centerline Boundary Dice Loss for Vascular Segmentation](https://mlsanity.com/paper/2407.01517/) (2024)
- [vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation](https://mlsanity.com/paper/2411.17386/) (2024)
- [VesselVAE: Recursive Variational Autoencoders for 3D Blood Vessel Synthesis](https://mlsanity.com/paper/2307.03592/) (2023)
- [ReC-TTT: Contrastive Feature Reconstruction for Test-Time Training](https://mlsanity.com/paper/2411.17869/) (2024)
- [VesselGPT: Autoregressive Modeling of Vascular Geometry](https://mlsanity.com/paper/2505.13318/) (2025)
- [A Large Scale Benchmark for Test Time Adaptation Methods in Medical Image Segmentation](https://mlsanity.com/paper/2512.02497/) (2025)
- [TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation](https://mlsanity.com/paper/2508.00442/) (2025)
- [VesselShot: Few-shot learning for cerebral blood vessel segmentation](https://mlsanity.com/paper/2308.14626/) (2023)
- [Branching exponents of synthetic vascular trees under different optimality principles](https://mlsanity.com/paper/2304.11998/) (2023)

## Abstract (arXiv)

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.