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

TL;DR

Trexplorer Super is an advanced recurrent model for topologically accurate centerline tracking of tubular structures in 3D CT images, addressing previous limitations and providing comprehensive evaluation datasets.

Contribution

It introduces Trexplorer Super with novel improvements and develops three new datasets for thorough evaluation of centerline tracking models.

Findings

Trexplorer Super outperforms SOTA models on all datasets.

Synthetic data performance does not always predict real data success.

Three new datasets enable better evaluation of tubular structure 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.