Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation

TL;DR

This paper introduces DSCNet, a novel segmentation network that employs dynamic snake convolution, multi-view feature fusion, and a topological continuity loss to improve the accuracy and topological correctness of tubular structure segmentation.

Contribution

The paper proposes a new dynamic snake convolution, a multi-view feature fusion strategy, and a topological continuity loss based on persistent homology for enhanced tubular structure segmentation.

Findings

Outperforms existing methods in accuracy on 2D and 3D datasets.

Improves topological continuity of segmented structures.

Effective in capturing slender and tortuous local features.

Abstract

Accurate segmentation of topological tubular structures, such as blood vessels and roads, is crucial in various fields, ensuring accuracy and efficiency in downstream tasks. However, many factors complicate the task, including thin local structures and variable global morphologies. In this work, we note the specificity of tubular structures and use this knowledge to guide our DSCNet to simultaneously enhance perception in three stages: feature extraction, feature fusion, and loss constraint. First, we propose a dynamic snake convolution to accurately capture the features of tubular structures by adaptively focusing on slender and tortuous local structures. Subsequently, we propose a multi-view feature fusion strategy to complement the attention to features from multiple perspectives during feature fusion, ensuring the retention of important information from different global morphologies. Finally, a continuity constraint loss function, based on persistent homology, is proposed to constrain the topological continuity of the segmentation better. Experiments on 2D and 3D datasets show that our DSCNet provides better accuracy and continuity on the tubular structure segmentation task compared with several methods. Our codes will be publicly available.