RepAir: A Framework for Airway Segmentation and Discontinuity Correction in CT
This work addresses the need for reliable airway segmentation for quantitative lung analysis in medical imaging, representing an incremental improvement over existing U-Net-based methods.
The paper tackles the problem of disconnected airway segmentation in chest CT scans, which hinders biomarker extraction, by introducing RepAir, a three-stage framework that combines nnU-Net-based segmentation with topology correction, resulting in outperforming existing methods on voxel-level and topological metrics across healthy and pathological datasets.
Accurate airway segmentation from chest computed tomography (CT) scans is essential for quantitative lung analysis, yet manual annotation is impractical and many automated U-Net-based methods yield disconnected components that hinder reliable biomarker extraction. We present RepAir, a three-stage framework for robust 3D airway segmentation that combines an nnU-Net-based network with anatomically informed topology correction. The segmentation network produces an initial airway mask, after which a skeleton-based algorithm identifies potential discontinuities and proposes reconnections. A 1D convolutional classifier then determines which candidate links correspond to true anatomical branches versus false or obstructed paths. We evaluate RepAir on two distinct datasets: ATM'22, comprising annotated CT scans from predominantly healthy subjects and AeroPath, encompassing annotated scans with severe airway pathology. Across both datasets, RepAir outperforms existing 3D U-Net-based approaches such as Bronchinet and NaviAirway on both voxel-level and topological metrics, and produces more complete and anatomically consistent airway trees while maintaining high segmentation accuracy.