VasGuideNet: Vascular Topology-Guided Couinaud Liver Segmentation with Structural Contrastive Loss

TL;DR

VasGuideNet introduces a vascular topology-guided framework for Couinaud liver segmentation, utilizing graph-based features and a novel contrastive loss to improve boundary accuracy and anatomical consistency.

Contribution

It is the first to explicitly incorporate vascular topology features into liver segmentation, enhancing accuracy and robustness over existing intensity-based methods.

Findings

Achieves higher Dice scores than baseline models.

Demonstrates improved anatomical consistency in segmentation.

Outperforms state-of-the-art methods on multiple datasets.

Abstract

Accurate Couinaud liver segmentation is critical for preoperative surgical planning and tumor localization.However, existing methods primarily rely on image intensity and spatial location cues, without explicitly modeling vascular topology. As a result, they often produce indistinct boundaries near vessels and show limited generalization under anatomical variability.We propose VasGuideNet, the first Couinaud segmentation framework explicitly guided by vascular topology. Specifically, skeletonized vessels, Euclidean distance transform (EDT)--derived geometry, and k-nearest neighbor (kNN) connectivity are encoded into topology features using Graph Convolutional Networks (GCNs). These features are then injected into a 3D encoder--decoder backbone via a cross-attention fusion module. To further improve inter-class separability and anatomical consistency, we introduce a Structural Contrastive Loss (SCL) with a global memory bank.On Task08_HepaticVessel and our private LASSD dataset, VasGuideNet achieves Dice scores of 83.68% and 76.65% with RVDs of 1.68 and 7.08, respectively. It consistently outperforms representative baselines including UNETR, Swin UNETR, and G-UNETR++, delivering higher Dice/mIoU and lower RVD across datasets, demonstrating its effectiveness for anatomically consistent segmentation. Code is available at https://github.com/Qacket/VasGuideNet.git.