用扩散模型+图注意力，提升肝脏小血管连通性与完整性分割
Continuous and complete liver vessel segmentation with graph-attention guided diffusion
- 引入图注意力模块建模血管几何，增强连续性
- 多尺度图注意力聚焦小血管，提升完整度
- 在两个数据集上超越8个先进方法，适合医学图像分割
肝脏血管分割中连通性和完整性是最大挑战，尤其对细小血管而言。这需要同时学习血管的连续几何结构并精准检测小血管。然而现有方法未显式解决上述问题，且在标注不一致时泛化能力差。本文利用扩散模型的强泛化能力，显式整合连通性与完整性：设计图注意力模块注入血管几何先验以增强连续性；并在多尺度上应用图注意力，专注小血管检测。该方法在3D-ircadb-01和LiVS两个公开数据集上优于8个最先进的医学分割方法。代码已开源：https://github.com/ZhangXiaotong015/GATSegDiff。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。