Two-stream MeshCNN for key anatomical segmentation on the liver surface.

Abstract

Purpose: Accurate preoperative segmentation of key anatomical regions on the liver surface is essential for enabling intraoperative navigation and position monitoring. However, current automatic segmentation methods face challenges due to the liver's drastic shape variations and limited data availability. This study aims to develop a two-stream mesh convolutional network (TSMCN) that integrates both global geometric and local topological information to achieve accurate, automatic segmentation of key anatomical regions.

Methods: We propose TSMCN, which consists of two parallel streams: the E-stream focuses on extracting topological information from liver mesh edges, while the P-stream captures spatial relationships from coordinate points. These single-perspective features are adaptively fused through a fine-grained aggregation (FGA)-based attention mechanism, generating a robust pooled mesh that preserves task-relevant edges and topological structures. This fusion enhances the model's understanding of the liver mesh and facilitates discriminative feature extraction on the newly pooled mesh.

Results: TSMCN was evaluated on 200 manually annotated 3D liver mesh datasets. It outperformed point-based (PointNet++) and edge feature-based (MeshCNN) methods, achieving superior segmentation results on the liver ridge and falciform ligament. The model significantly reduced the 3D Chamfer distance compared to other methods, with particularly strong performance in falciform ligament segmentation.

Conclusion: TSMCN provides an effective approach to liver surface segmentation by integrating complementary geometric features. Its superior performance highlights the potential to enhance AR-guided liver surgery through automatic and precise preoperative segmentation of critical anatomical regions.