# ReG-SAM: Reference Graph-Driven SAM for 2D Foundational Vessel Segmentation

arXiv: https://arxiv.org/abs/2609.31160 · HTML: https://mlsanity.com/paper/2609.31160/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [ROSE: A Retinal OCT-Angiography Vessel Segmentation Dataset and New Model](https://mlsanity.com/paper/2007.05201/) (2020)
- [Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation](https://mlsanity.com/paper/2209.14566/) (2022)
- [Towards a glaucoma risk index based on simulated hemodynamics from fundus images](https://mlsanity.com/paper/1805.10273/) (2018)
- [Synthetic optical coherence tomography angiographs for detailed retinal vessel segmentation without human annotations](https://mlsanity.com/paper/2306.10941/) (2023)
- [Deep Placental Vessel Segmentation for Fetoscopic Mosaicking](https://mlsanity.com/paper/2007.04349/) (2020)
- [DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation](https://mlsanity.com/paper/2406.01591/) (2024)
- [An Accurate and Efficient Neural Network for OCTA Vessel Segmentation and a New Dataset](https://mlsanity.com/paper/2309.09483/) (2023)
- [ASPS: Augmented Segment Anything Model for Polyp Segmentation](https://mlsanity.com/paper/2407.00718/) (2024)
- [DIAS: A Dataset and Benchmark for Intracranial Artery Segmentation in DSA sequences](https://mlsanity.com/paper/2306.12153/) (2023)
- [Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images](https://mlsanity.com/paper/2012.09250/) (2020)
- [DSCA: A Digital Subtraction Angiography Sequence Dataset and Spatio-Temporal Model for Cerebral Artery Segmentation](https://mlsanity.com/paper/2406.00341/) (2024)
- [Dr-SAM: An End-to-End Framework for Vascular Segmentation, Diameter Estimation, and Anomaly Detection on Angiography Images](https://mlsanity.com/paper/2404.17029/) (2024)
- [MCP-MedSAM: A Powerful Lightweight Medical Segment Anything Model Trained with a Single GPU in Just One Day](https://mlsanity.com/paper/2412.05888/) (2024)
- [Efficient MedSAMs: Segment Anything in Medical Images on Laptop](https://mlsanity.com/paper/2412.16085/) (2024)
- [SAM-DA: Decoder Adapter for Efficient Medical Domain Adaptation](https://mlsanity.com/paper/2501.06836/) (2025)

## Abstract (arXiv)

Vessel segmentation in medical images is essential for many clinical tasks, ranging from diagnosis to treatment planning. However, it remains challenging due to complex vascular morphology and diverse imaging conditions. Existing deep learning methods rarely aim at building a generalizable vessel segmentor across anatomies and modalities. While the Seg- ment Anything Model (SAM) has shown promise for med- ical image segmentation, its original design does not fully exploit vascular morphology and struggles with fine-grained vascular structures, leading to suboptimal performance. In this paper, we propose ReG-SAM, a SAM-based framework tailored to 2D vessel segmentation that leverages reference graph set for enhancing vascular representations. Specifically, we introduce two modality-aware representations derived from the reference masks: graph prompt embeddings (GPEs) that encode global spatial features from graphs, and vascu- lar prototype embeddings (VPEs) that capture fine-grained modality-specific vessel characteristics from multi-scale fea- ture maps and vascular masks. Since both require vascular masks that are unavailable during inference and require robust modality-aware vascular feature representations, we construct a modality-wise vascular database and develop two reference graph-guided representation learning schemes for estimating GPEs and VPEs using samples from the database rather than ground-truth masks. Extensive experiments across 19 datasets demonstrate that ReG-SAM consistently outperforms existing baselines, even those using manual prompts, particularly on challenging thin vessels.