Rethinking the Detail-Preserved Completion of Complex Tubular Structures based on Point Cloud: a Dataset and a Benchmark

2025-08-25

AI Summary

To address point cloud fragmentation in medical image segmentation of complex tubular structures—particularly coronary arteries affected by stenosis or occlusion—this paper introduces the first clinically oriented coronary artery point cloud completion task and establishes the real-world, clinical-driven PC-CAC dataset. We propose TSRNet, a novel architecture featuring a detail-preserving feature extractor and multi-level dense refinement modules, jointly optimized via a global-to-local loss function and a multi-stage optimization strategy to ensure both structural continuity and geometric fidelity. Extensive experiments demonstrate that TSRNet consistently outperforms state-of-the-art methods across three vascular point cloud benchmarks—PC-CAC, PC-ImageCAS, and PC-PTR—achieving new SOTA performance on key metrics including Chamfer Distance (CD) and F-Score. This work establishes the first dedicated benchmark for tubular structure completion in the point cloud domain, bridging a critical gap between clinical requirements and geometric deep learning.

Technology Category

• Computer Vision: Segmentation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Complex tubular structures are essential in medical imaging and computer-assisted diagnosis, where their integrity enhances anatomical visualization and lesion detection. However, existing segmentation algorithms struggle with structural discontinuities, particularly in severe clinical cases such as coronary artery stenosis and vessel occlusions, which leads to undesired discontinuity and compromising downstream diagnostic accuracy. Therefore, it is imperative to reconnect discontinuous structures to ensure their completeness. In this study, we explore the tubular structure completion based on point cloud for the first time and establish a Point Cloud-based Coronary Artery Completion (PC-CAC) dataset, which is derived from real clinical data. This dataset provides a novel benchmark for tubular structure completion. Additionally, we propose TSRNet, a Tubular Structure Reconnection Network that integrates a detail-preservated feature extractor, a multiple dense refinement strategy, and a global-to-local loss function to ensure accurate reconnection while maintaining structural integrity. Comprehensive experiments on our PC-CAC and two additional public datasets (PC-ImageCAS and PC-PTR) demonstrate that our method consistently outperforms state-of-the-art approaches across multiple evaluation metrics, setting a new benchmark for point cloud-based tubular structure reconstruction. Our benchmark is available at https://github.com/YaoleiQi/PCCAC.

Problem

• Completing discontinuous tubular structures in medical imaging
• Addressing segmentation gaps in coronary arteries and vessels
• Reconnecting structures to improve diagnostic accuracy

Innovation

• Point cloud-based coronary artery completion dataset
• Tubular Structure Reconnection Network with detail preservation
• Global-to-local loss function ensuring structural integrity