Trexplorer Super: Topologically Correct Centerline Tree Tracking of Tubular Objects in CT Volumes

2025-07-14

AI Summary

This work addresses topological errors—such as branch duplication and premature termination—in centerline tree tracing of tubular structures (e.g., vessels, airways) in CT images. We propose Trexplorer Super, a recursive neural network framework that explicitly models branching relationships via a novel topology-aware loss function and incorporates a dynamic termination mechanism to adaptively determine tracking endpoints. To standardize evaluation, we introduce three publicly available benchmark datasets with progressively increasing difficulty, comprising both synthetic and real-world CT scans. Experiments demonstrate that our method consistently outperforms existing state-of-the-art approaches across all benchmarks. Notably, high performance achieved on synthetic data does not directly transfer to real CT volumes, underscoring the critical need for validation on authentic clinical data. The source code and datasets are openly released to foster reproducibility and further research.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Ensemble Methods

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Topic discovery and tracking

Abstract

Tubular tree structures, such as blood vessels and airways, are essential in human anatomy and accurately tracking them while preserving their topology is crucial for various downstream tasks. Trexplorer is a recurrent model designed for centerline tracking in 3D medical images but it struggles with predicting duplicate branches and terminating tracking prematurely. To address these issues, we present Trexplorer Super, an enhanced version that notably improves performance through novel advancements. However, evaluating centerline tracking models is challenging due to the lack of public datasets. To enable thorough evaluation, we develop three centerline datasets, one synthetic and two real, each with increasing difficulty. Using these datasets, we conduct a comprehensive evaluation of existing state-of-the-art (SOTA) models and compare them with our approach. Trexplorer Super outperforms previous SOTA models on every dataset. Our results also highlight that strong performance on synthetic data does not necessarily translate to real datasets. The code and datasets are available at https://github.com/RomStriker/Trexplorer-Super.

Problem

• Accurately tracking tubular tree structures in CT volumes
• Preventing duplicate branches and premature tracking termination
• Lack of public datasets for centerline tracking evaluation

Innovation

• Enhanced recurrent model for centerline tracking
• Developed synthetic and real evaluation datasets
• Outperforms state-of-the-art models consistently