Reflecting Topology Consistency and Abnormality via Learnable Attentions for Airway Labeling

TL;DR

This paper introduces a novel method for airway labeling that enhances topological consistency and abnormality detection using learnable attentions, significantly improving accuracy and robustness in challenging cases with airway deformities.

Contribution

It proposes two modules, SSC and ABS, to improve topological consistency and abnormal branch detection, advancing airway labeling accuracy and reliability.

Findings

Achieves 91.4% accuracy at segmental level

Attains 83.7% accuracy at subsegmental level

Improves topological consistency by 3.1%

Abstract

Accurate airway anatomical labeling is crucial for clinicians to identify and navigate complex bronchial structures during bronchoscopy. Automatic airway anatomical labeling is challenging due to significant individual variability and anatomical variations. Previous methods are prone to generate inconsistent predictions, which is harmful for preoperative planning and intraoperative navigation. This paper aims to address these challenges by proposing a novel method that enhances topological consistency and improves the detection of abnormal airway branches. We propose a novel approach incorporating two modules: the Soft Subtree Consistency (SSC) and the Abnormal Branch Saliency (ABS). The SSC module constructs a soft subtree to capture clinically relevant topological relationships, allowing for flexible feature aggregation within and across subtrees. The ABS module facilitates the interaction between node features and prototypes to distinguish abnormal branches, preventing the erroneous aggregation of features between normal and abnormal nodes. Evaluated on a challenging dataset characterized by severe airway distortion and atrophy, our method achieves superior performance compared to state-of-the-art approaches. Specifically, it attains a 91.4% accuracy at the segmental level and an 83.7% accuracy at the subsegmental level, representing a 1.4% increase in subsegmental accuracy and a 3.1% increase in topological consistency. Notably, the method demonstrates reliable performance in cases with disease-induced airway deformities, ensuring consistent and accurate labeling.