A

Continuous and complete liver vessel segmentation with graph-attention guided diffusion

arXiv (Cornell University)

Abstract

Improving connectivity and completeness are the most challenging aspects of liver vessel segmentation, especially for small vessels. These challenges require both learning the continuous vessel geometry, and focusing on small vessel detection. However, current methods do not explicitly address these two aspects and cannot generalize well when constrained by inconsistent annotations. Here, we take advantage of the generalization of the diffusion model and explicitly integrate connectivity and completeness in our diffusion-based segmentation model. Specifically, we use a graph-attention module that adds knowledge about vessel geometry, and thus adds continuity. Additionally, we perform the graph-attention at multiple-scales, thus focusing on small liver vessels. Our method outperforms eight state-of-the-art medical segmentation methods on two public datasets: 3D-ircadb-01 and LiVS. Our code is available at https://github.com/ZhangXiaotong015/GATSegDiff.

Authors 5

  1. Leiden University · Leiden University Medical Center

    Affiliation as printed

    Radiology department , Leiden University Medical Center , Albinusdreef 2 , Leiden , 2333 ZA , South Holland , The Netherlands

  2. Leiden University · Leiden University Medical Center

    Affiliation as printed

    Radiology department , Leiden University Medical Center , Albinusdreef 2 , Leiden , 2333 ZA , South Holland , The Netherlands

  3. Leiden University · Leiden University Medical Center

    Affiliation as printed

    Radiology department , Leiden University Medical Center , Albinusdreef 2 , Leiden , 2333 ZA , South Holland , The Netherlands

  4. Leiden University · Leiden University Medical Center

    Affiliation as printed

    Radiology department , Leiden University Medical Center , Albinusdreef 2 , Leiden , 2333 ZA , South Holland , The Netherlands

  5. Leiden University · Leiden University Medical Center

    Affiliation as printed

    Radiology department , Leiden University Medical Center , Albinusdreef 2 , Leiden , 2333 ZA , South Holland , The Netherlands

Cited by 0 stored of 0

No patents citing this paper on Lens.org (checked 2026-10-11).

References 0