# VessShape: Few-shot 2D blood vessel segmentation by leveraging shape priors from synthetic images

arXiv: https://arxiv.org/abs/2510.27646 · HTML: https://mlsanity.com/paper/2510.27646/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [clDice -- A Novel Topology-Preserving Loss Function for Tubular Structure Segmentation](https://mlsanity.com/paper/2003.07311/) (2020)
- [Topology-Preserving Deep Image Segmentation](https://mlsanity.com/paper/1906.05404/) (2019)
- [DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes](https://mlsanity.com/paper/1803.09340/) (2018)
- [Shape or Texture: Understanding Discriminative Features in CNNs](https://mlsanity.com/paper/2101.11604/) (2021)
- [A survey on shape-constraint deep learning for medical image segmentation](https://mlsanity.com/paper/2101.07721/) (2021)
- [A Two Stage GAN for High Resolution Retinal Image Generation and Segmentation](https://mlsanity.com/paper/1907.12296/) (2019)
- [Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning](https://mlsanity.com/paper/2201.04812/) (2022)
- [Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models](https://mlsanity.com/paper/2305.06813/) (2023)
- [LUNet: Deep Learning for the Segmentation of Arterioles and Venules in High Resolution Fundus Images](https://mlsanity.com/paper/2309.05780/) (2023)
- [VasTSD: Learning 3D Vascular Tree-state Space Diffusion Model for Angiography Synthesis](https://mlsanity.com/paper/2503.12758/) (2025)
- [Segmentation-guided Domain Adaptation and Data Harmonization of Multi-device Retinal Optical Coherence Tomography using Cycle-Consistent Generative Adversarial Networks](https://mlsanity.com/paper/2208.14635/) (2022)
- [Deep vessel segmentation based on a new combination of vesselness filters](https://mlsanity.com/paper/2402.14509/) (2024)
- [Simulation-Based Segmentation of Blood Vessels in Cerebral 3D OCTA Images](https://mlsanity.com/paper/2403.07116/) (2024)
- [Frangi-Net: A Neural Network Approach to Vessel Segmentation](https://mlsanity.com/paper/1711.03345/) (2017)
- [A new dataset for measuring the performance of blood vessel segmentation methods under distribution shifts](https://mlsanity.com/paper/2301.04517/) (2023)
- [Synthetic Data for Blood Vessel Network Extraction](https://mlsanity.com/paper/2504.11858/) (2025)

## Abstract (arXiv)

Semantic segmentation of blood vessels is an important task in medical image analysis, but its progress is often hindered by the scarcity of large annotated datasets and the poor generalization of models across different imaging modalities. A key aspect is the tendency of Convolutional Neural Networks (CNNs) to learn texture-based features, which limits their performance when applied to new domains with different visual characteristics. We hypothesize that leveraging geometric priors of vessel shapes, such as their tubular and branching nature, can lead to more robust and data-efficient models. To investigate this, we introduce VessShape, a methodology for generating large-scale 2D synthetic datasets designed to instill a shape bias in segmentation models. VessShape images contain procedurally generated tubular geometries combined with a wide variety of foreground and background textures, encouraging models to learn shape cues rather than textures. We demonstrate that a model pre-trained on VessShape images achieves strong few-shot segmentation performance on two real-world datasets from different domains, requiring only four to ten samples for fine-tuning. Furthermore, the model exhibits notable zero-shot capabilities, effectively segmenting vessels in unseen domains without any target-specific training. Our results indicate that pre-training with a strong shape bias can be an effective strategy to overcome data scarcity and improve model generalization in blood vessel segmentation.