PASC-Net:Plug-and-play Shape Self-learning Convolutions Network with Hierarchical Topology Constraints for Vessel Segmentation

2025-07-05

AI Summary

Existing vascular segmentation methods struggle to accurately detect low-contrast, fine-scale vessel branches and often produce discontinuities—particularly at complex topological structures such as bifurcations—leading to degraded connectivity and structural integrity. To address these limitations, we propose a novel segmentation framework featuring: (1) a plug-and-play shape self-learning convolutional module that enhances tubular feature representation via learnable stripe convolutions; and (2) a three-level topological regularization mechanism—operating on line-, surface-, and volume-level structures—to enforce hierarchical topological consistency. Our method is architecture-agnostic and seamlessly integrates with mainstream backbones including U-Net and nnUNet. Evaluated across multiple public benchmarks, it achieves substantial improvements in fine-vessel recall and topological connectivity. Relative to nnUNet, it establishes new state-of-the-art performance, with significant gains in key metrics—including Average Distance (AVD), Hausdorff Distance, and Topological F1-score.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Non-convex Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Accurate vessel segmentation is crucial to assist in clinical diagnosis by medical experts. However, the intricate tree-like tubular structure of blood vessels poses significant challenges for existing segmentation algorithms. Small vascular branches are often overlooked due to their low contrast compared to surrounding tissues, leading to incomplete vessel segmentation. Furthermore, the complex vascular topology prevents the model from accurately capturing and reconstructing vascular structure, resulting in incorrect topology, such as breakpoints at the bifurcation of the vascular tree. To overcome these challenges, we propose a novel vessel segmentation framework called PASC Net. It includes two key modules: a plug-and-play shape self-learning convolutional (SSL) module that optimizes convolution kernel design, and a hierarchical topological constraint (HTC) module that ensures vascular connectivity through topological constraints. Specifically, the SSL module enhances adaptability to vascular structures by optimizing conventional convolutions into learnable strip convolutions, which improves the network's ability to perceive fine-grained features of tubular anatomies. Furthermore, to better preserve the coherence and integrity of vascular topology, the HTC module incorporates hierarchical topological constraints-spanning linear, planar, and volumetric levels-which serve to regularize the network's representation of vascular continuity and structural consistency. We replaced the standard convolutional layers in U-Net, FCN, U-Mamba, and nnUNet with SSL convolutions, leading to consistent performance improvements across all architectures. Furthermore, when integrated into the nnUNet framework, our method outperformed other methods on multiple metrics, achieving state-of-the-art vascular segmentation performance.

Problem

• Segments intricate tree-like vascular structures accurately
• Addresses low contrast in small vascular branches
• Ensures vascular connectivity and correct topology

Innovation

• Plug-and-play shape self-learning convolutional module
• Hierarchical topological constraint for vascular connectivity
• Learnable strip convolutions enhance tubular feature perception