Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT

TL;DR

This paper introduces a novel CNN-based approach for pulmonary airway and artery-vein segmentation in CT scans, emphasizing sensitivity to small structures and addressing class imbalance with specialized modules and anatomical priors.

Contribution

The proposed method integrates feature recalibration, attention distillation, and anatomical priors to improve tubular structure segmentation in CT images, outperforming existing techniques.

Findings

Enhanced sensitivity to peripheral bronchioles, arterioles, and venules.

More detailed and extensive branch extraction compared to state-of-the-art.

Maintained competitive overall segmentation performance.

Abstract

Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background. We present a CNNs-based method for accurate airway and artery-vein segmentation in non-contrast computed tomography. It enjoys superior sensitivity to tenuous peripheral bronchioles, arterioles, and venules. The method first uses a feature recalibration module to make the best use of features learned from the neural networks. Spatial information of features is properly integrated to retain relative priority of activated regions, which benefits the subsequent channel-wise recalibration. Then, attention distillation module is introduced to reinforce representation learning of tubular objects. Fine-grained details in high-resolution attention maps are passing down from one layer to its previous layer recursively to enrich context. Anatomy prior of lung context map and distance transform map is designed and incorporated for better artery-vein differentiation capacity. Extensive experiments demonstrated considerable performance gains brought by these components. Compared with state-of-the-art methods, our method extracted much more branches while maintaining competitive overall segmentation performance. Codes and models are available at http://www.pami.sjtu.edu.cn/News/56