Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT
- 26 February 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (6), 1603-1617
- https://doi.org/10.1109/tmi.2021.3062280
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.Keywords
Funding Information
- National Natural Science Foundation of China (62003208, 61661010, 61977046)
- National Key Research and Development Program of China (2019YFB1311503)
- Committee of Science and Technology, Shanghai, China (19411963900, 19510711200)
- Shanghai Sailing Program (20YF1420800)
- Shanghai Municipal of Science and Technology Project (20JC1419500)
- Major Project (2021SHZDZX0102)
- International Research Project METISLAB, Program PHC-Cai Yuanpei 2018 (41400TC)
- China Scholarship Council (201906230173)
This publication has 53 references indexed in Scilit:
- Delayed Adverse Reaction to Contrast-enhanced CT: A Prospective Single-Center Study Comparison to Control Group without EnhancementRadiology, 2010
- Automatic multiscale enhancement and segmentation of pulmonary vessels in CT pulmonary angiography images for CAD applicationsMedical Physics, 2007
- User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliabilityNeuroImage, 2006
- Pulmonary Airways: 3-D Reconstruction From Multislice CT and Clinical InvestigationIEEE Transactions on Medical Imaging, 2004
- Airway and blood vessel interaction during lung developmentJournal of Anatomy, 2002
- The role of small airways in lung diseaseRespiratory Medicine, 2002
- Fast approximate energy minimization via graph cutsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
- Automated anatomical labeling of the bronchial branch and its application to the virtual bronchoscopy systemIEEE Transactions on Medical Imaging, 2000
- Building Skeleton Models via 3-D Medial Surface Axis Thinning AlgorithmsCVGIP: Graphical Models and Image Processing, 1994
- Relationship between bronchial and arterial diameters in normal human lungs.Thorax, 1979