Progressive Curriculum Learning with Scale-Enhanced U-Net for Continuous Airway Segmentation

TL;DR

This paper introduces a progressive curriculum learning approach with a Scale-Enhanced U-Net for improved continuous airway segmentation in chest CT images, effectively addressing intra-class imbalance and airway discontinuities.

Contribution

It proposes a novel multi-stage training pipeline, a scale-enhanced network architecture, and an adaptive loss function to enhance airway segmentation accuracy and continuity.

Findings

Outperforms existing methods on multiple datasets

Significantly improves small airway segmentation

Enhances airway tree completeness

Abstract

Continuous and accurate segmentation of airways in chest CT images is essential for preoperative planning and real-time bronchoscopy navigation. Despite advances in deep learning for medical image segmentation, maintaining airway continuity remains a challenge, particularly due to intra-class imbalance between large and small branches and blurred CT scan details. To address these challenges, we propose a progressive curriculum learning pipeline and a Scale-Enhanced U-Net (SE-UNet) to enhance segmentation continuity. Specifically, our progressive curriculum learning pipeline consists of three stages: extracting main airways, identifying small airways, and repairing discontinuities. The cropping sampling strategy in each stage reduces feature interference between airways of different scales, effectively addressing the challenge of intra-class imbalance. In the third training stage, we present an Adaptive Topology-Responsive Loss (ATRL) to guide the network to focus on airway continuity. The progressive training pipeline shares the same SE-UNet, integrating multi-scale inputs and Detail Information Enhancers (DIEs) to enhance information flow and effectively capture the intricate details of small airways. Additionally, we propose a robust airway tree parsing method and hierarchical evaluation metrics to provide more clinically relevant and precise analysis. Experiments on both in-house and public datasets demonstrate that our method outperforms existing approaches, significantly improving the accuracy of small airways and the completeness of the airway tree. The code will be released upon publication.