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

[NEWS!]This paper has been accepted by ICCV 2023!

[NOTE!!]The code will be gradually and continuously opened!

Brief introduction

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.

Paper

Dynamic Snake Convolution based on Topological Geometric Constraints for Tubular Structure Segmentation
Yaolei Qi, Yuting He, Xiaoming Qi, Yuan Zhang, Guanyu Yang* Southeast University
IEEE/CVF Conference on International Conference on Computer Vision 2023

Model - The easiest and fastest way to reproduce!

(We will update other contents in the next 4 weeks ...)

Model - Introduction of our code!

Citation

(Please wait for updating ...)

Ackowledgements

(Please wait for updating ...)