BifDet: A 3D Bifurcation Detection Dataset for Airway-Tree Modeling

TL;DR

This paper introduces BifDet, the first publicly available 3D airway bifurcation detection dataset from CT scans, enabling development of automated detection tools for respiratory disease analysis.

Contribution

The paper provides a novel annotated dataset for 3D airway bifurcation detection and demonstrates its use with fine-tuned RetinaNet and DETR models.

Findings

BifDet dataset covers airway bifurcations with detailed annotations.

RetinaNet and DETR achieve baseline detection performance.

Results vary across different bounding box size categories.

Abstract

Thoracic Computed Tomography (CT) scans offer detailed insights into the intricate branching network of the airway tree, which is essential for understanding various respiratory diseases. Airway bifurcations, where airway branches split, are crucial landmarks for understanding lung physiology, disease mechanisms and lesion localization. Despite the significance of bifurcation analysis, a notable lack of datasets annotated for this task hinders the development of advanced automated specialized detection or segmentation tools. In this paper, we introduce BifDet, the first publicly-available dataset specialized for 3D airway bifurcation detection, filling a critical gap in existing resources. Our dataset comprises carefully annotated CT scans from the ATM22 open-access cohort with bifurcation bounding boxes covering the parent and daughter branches. As a use-case for demonstrating the potential of BifDet, we fine-tune and evaluate RetinaNet and DETR for 3D airway bifurcations detection on CT scans. We provide detailed pipelines, including preprocessing steps and specific implementation design choices. Results are detailed over various categories of minimal bounding box sizes to serve as baseline to benchmark future research.