Abstract
Intrathoracic airway segmentation from computed tomography images is a frequent prerequisite for further quantitative lung analyses. Due to low contrast and noise, especially at peripheral branches, it is often challenging for automatic methods to strike a balance between extracting deeper airway branches and avoiding leakage to the surrounding parenchyma. Meanwhile, manual annotations are extremely time consuming for the airway tree, which inhibits automated methods requiring training data. To address this, we introduce a 3D deep learning-based workflow able to produce high-quality airway segmentation from incompletely labeled training data generated without manual intervention. We first train a 3D fully convolutional network (FCN) based on the fact that 3D spatial information is crucial for small highly anisotropic tubular structures such as airways. For training the 3D FCN, we develop a domain-specific sampling scheme that strategically uses incomplete labels from a previous highly specific segmentation method, aiming to retain similar specificity while boosting sensitivity. Finally, to address local discontinuities of the coarse 3D FCN output, we apply a graph-based refinement incorporating fuzzy connectedness segmentation and robust curve skeletonization. Evaluations on the EXACT’09 and LTRC datasets demonstrate considerable improvements in airway extraction while maintaining reasonable leakage compared with a state-of-art method and the dataset reference standard.
Keywords
Z. Xu—This work is supported by the Intramural Research Program of the National Institutes of Health, Clinical Center and the National Institute of Allergy and Infectious Diseases. We also thank Nvidia for the donation of a Tesla K40 GPU.
The rights of this work are transferred to the extent transferable according to title 17 § 105 U.S.C.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kuwano, K., Bosken, C.H., Paré, P.D., Bai, T.R., Wiggs, B.R., Hogg, J.C.: Small airways dimensions in asthma and in chronic obstructive pulmonary disease. Am. Rev. Respir. Dis. 148(5), 1220–1225 (1993)
Tschirren, J., Yavarna, T., Reinhardt, J.M.: Airway segmentation framework for clinical environments. In: Second International Workshop on Pulmonary Image Analysis, London, UK, pp. 227–238 (2009)
Van Rikxoort, E.M., Baggerman, W., van Ginneken, B.: Automatic segmentation of the airway tree from thoracic CT scans using a multi-threshold approach. In: Second International Workshop on Pulmonary Image Analysis, pp. 341–349 (2009)
Xu, Z., Bagci, U., Foster, B., Mansoor, A., Udupa, J.K., Mollura, D.J.: A hybrid method for airway segmentation and automated measurement of bronchial wall thickness on CT. Med. Imag. Anal. 24(1), 1–17 (2015)
Lo, P., Sporring, J., Ashraf, H., Pedersen, J.J., de Bruijne, M.: Vessel-guided airway tree segmentation: a voxel classification approach. Med. Imag. Anal. 14(4), 527–538 (2010)
Charbonnier, J.P., van Rikxoort, E.M., Setio, A.A., Schaefer-Prokop, C.M., van Ginneken, B., Ciompi, F.: Improving airway segmentation in computed tomography using leak detection with convolutional networks. Med. Imag. Anal. 36, 52–60 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556 (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, June 2016
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). doi:10.1007/978-3-319-24574-4_28
Merkow, J., Marsden, A., Kriegman, D., Tu, Z.: Dense volume-to-volume vascular boundary detection. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 371–379. Springer, Cham (2016). doi:10.1007/978-3-319-46726-9_43
Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016). doi:10.1007/978-3-319-46723-8_49
Jin, D., Iyer, K.S., Chen, C., Hoffman, E.A., Saha, P.K.: A robust and efficient curve skeletonization algorithm for tree-like objects using minimum cost paths. Pattern Recogn. Lett. 76, 32–40 (2016)
Lo, P., Van Ginneken, B., Reinhardt, J.M., et al.: Extraction of airways from CT (EXACT’09). IEEE Trans. Med. Imaging 31(11), 2093–2107 (2012)
Karwoski, R.A., Bartholmai, B., Zavaletta, V.A., Holmes, D., Robb, R.A.: Processing of CT images for analysis of diffuse lung disease in the lung tissue research consortium. In: Proceedings of SPIE 6916, Medical Imaging 2008: Physiology, Function, and Structure from Medical Images (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG (outside the USA)
About this paper
Cite this paper
Jin, D., Xu, Z., Harrison, A.P., George, K., Mollura, D.J. (2017). 3D Convolutional Neural Networks with Graph Refinement for Airway Segmentation Using Incomplete Data Labels. In: Wang, Q., Shi, Y., Suk, HI., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2017. Lecture Notes in Computer Science(), vol 10541. Springer, Cham. https://doi.org/10.1007/978-3-319-67389-9_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-67389-9_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-67388-2
Online ISBN: 978-3-319-67389-9
eBook Packages: Computer ScienceComputer Science (R0)