VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fu, Suzhong, Sun, Rui, Ding, Xuan, Dong, Jingqi, Yang, Yiming, Zhu, Yao, Ren, Min Chang Jordan, Deng, Delin, Aviles-Rivero, Angelica, Cui, Shuguang, Li, Zhen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918249446244352
author Fu, Suzhong
Sun, Rui
Ding, Xuan
Dong, Jingqi
Yang, Yiming
Zhu, Yao
Ren, Min Chang Jordan
Deng, Delin
Aviles-Rivero, Angelica
Cui, Shuguang
Li, Zhen
author_facet Fu, Suzhong
Sun, Rui
Ding, Xuan
Dong, Jingqi
Yang, Yiming
Zhu, Yao
Ren, Min Chang Jordan
Deng, Delin
Aviles-Rivero, Angelica
Cui, Shuguang
Li, Zhen
contents Accurate vessel segmentation is critical for clinical applications such as disease diagnosis and surgical planning, yet remains challenging due to thin, branching structures and low texture contrast. While foundation models like the Segment Anything Model (SAM) have shown promise in generic segmentation, they perform sub-optimally on vascular structures. In this work, we present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation. VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, including skeletons, bifurcation points, and segment midpoints, via hierarchical cross-attention, and (3) a lightweight mask decoder to reduce jagged artifacts. We also introduce an automated pipeline to generate structured multi-prompt annotations, and curate a diverse benchmark dataset spanning 8 datasets across 5 imaging modalities. Experimental results demonstrate that VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU, and achieves competitive performance compared to fully fine-tuned methods, with significantly fewer parameters. VesSAM also generalizes well to out-of-distribution (OoD) settings, outperforming all baselines in average OoD Dice and IoU.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00981
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
Fu, Suzhong
Sun, Rui
Ding, Xuan
Dong, Jingqi
Yang, Yiming
Zhu, Yao
Ren, Min Chang Jordan
Deng, Delin
Aviles-Rivero, Angelica
Cui, Shuguang
Li, Zhen
Computer Vision and Pattern Recognition
Accurate vessel segmentation is critical for clinical applications such as disease diagnosis and surgical planning, yet remains challenging due to thin, branching structures and low texture contrast. While foundation models like the Segment Anything Model (SAM) have shown promise in generic segmentation, they perform sub-optimally on vascular structures. In this work, we present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation. VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, including skeletons, bifurcation points, and segment midpoints, via hierarchical cross-attention, and (3) a lightweight mask decoder to reduce jagged artifacts. We also introduce an automated pipeline to generate structured multi-prompt annotations, and curate a diverse benchmark dataset spanning 8 datasets across 5 imaging modalities. Experimental results demonstrate that VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU, and achieves competitive performance compared to fully fine-tuned methods, with significantly fewer parameters. VesSAM also generalizes well to out-of-distribution (OoD) settings, outperforming all baselines in average OoD Dice and IoU.
title VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.00981