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

TL;DR

This paper introduces a diffusion-based liver vessel segmentation method that explicitly models vessel connectivity and focuses on small vessels using graph-attention, achieving superior results on public datasets.

Contribution

The paper presents a novel diffusion-based segmentation model with multi-scale graph-attention to improve vessel connectivity and small vessel detection.

Findings

Outperforms eight state-of-the-art methods on two datasets

Effectively models vessel connectivity and small vessel detection

Achieves higher accuracy and completeness in liver vessel segmentation

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.