Abstract
Several chronic lung diseases, like idiopathic pulmonary fibrosis (IPF) are characterised by abnormal dilatation of the airways. Quantification of airway features on computed tomography (CT) can help characterise disease severity and progression. Physics based airway measurement algorithms that have been developed have met with limited success, in part due to the sheer diversity of airway morphology seen in clinical practice. Supervised learning methods are not feasible due to the high cost of obtaining precise airway annotations. We propose synthesising airways by style transfer using perceptual losses to train our model: Airway Transfer Network (ATN). We compare our ATN model with a state-of-the-art GAN-based network (simGAN) using a) qualitative assessment; b) assessment of the ability of ATN and simGAN based CT airway metrics to predict mortality in a population of 113 patients with IPF. ATN was shown to be quicker and easier to train than simGAN. ATN-based airway measurements showed consistently stronger associations with mortality than simGAN-derived airway metrics on IPF CTs. Airway synthesis by a transformation network that refines synthetic data using perceptual losses is a realistic alternative to GAN-based methods for clinical CT analyses of idiopathic pulmonary fibrosis. Our source code can be found at https://github.com/ashkanpakzad/ATN that is compatible with the existing open-source airway analysis framework, AirQuant.
Keywords
- Generative model evaluation
- Style transfer
- Computed tomography
- Airway measurement
- Bronchiectasis
- Idiopathic pulmonary fibrosis
This is a preview of subscription content, access via your institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
- 2.
Segments are considered to be oriented from the centre of the lung to the periphery. Accordingly, measurement of the airway origin beings at the end closest to the trachea.
- 3.
higher activation layers are considered in the supplementary material.
References
Biewald, L.: Experiment tracking with weights and biases (2020). https://www.wandb.com/, software available from wandb.com
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255, June 2009. https://doi.org/10.1109/CVPR.2009.5206848
Estépar, R.S.J., Washko, G.G., Silverman, E.K., Reilly, J.J., Kikinis, R., Westin, C.-F.: Accurate airway wall estimation using phase congruency. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 125–134. Springer, Heidelberg (2006). https://doi.org/10.1007/11866763_16
Flaherty, K.R., et al.: Idiopathic pulmonary fibrosis. Am. J. Respir. Crit. Care Med. 174(7), 803–809 (2006). https://doi.org/10.1164/rccm.200604-488OC
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style (2015). https://doi.org/10.48550/ARXIV.1508.06576, https://arxiv.org/abs/1508.06576
Goodfellow, I.J., et al.: Generative adversarial networks. arXiv:1406.2661 [cs, stat] (June 2014). http://arxiv.org/abs/1406.2661
Gu, S., et al.: Computerized identification of airway wall in CT examinations using a 3D active surface evolution approach. Med. Image Anal. 17(3), 283–296 (2013). https://doi.org/10.1016/j.media.2012.11.003
Harrell Jr., F.E., Lee, K.L., Mark, D.B.: Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat. Med. 15(4), 361–387 (1996). https://doi.org/10.1002/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, December 2015. https://doi.org/10.48550/arXiv.1512.03385
Hofmanninger, J., Prayer, F., Pan, J., Röhrich, S., Prosch, H., Langs, G.: Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem. Eur. Radiol. Exp. 4(1), 1–13 (2020). https://doi.org/10.1186/s41747-020-00173-2
Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution, March 2016. https://doi.org/10.48550/arXiv.1603.08155
Kiraly, A.P., Reinhardt, J.M., Hoffman, E.A., McLennan, G., Higgins, W.E.: Virtual bronchoscopy for quantitative airway analysis. In: Amini, A.A., Manduca, A. (eds.) Medical Imaging 2005: Physiology, Function, and Structure from Medical Images, vol. 5746, p. 369. International Society for Optics and Photonics, April 2005. https://doi.org/10.1117/12.595283
Kluvanec, D., Phillips, T.B., McCaffrey, K.J.W., Moubayed, N.A.: Using orientation to distinguish overlapping chromosomes, March 2022. https://doi.org/10.48550/arXiv.2203.13004
Kuo, W., Perez-Rovira, A., Tiddens, H., de Bruijne, M.: Airway tapering: an objective image biomarker for bronchiectasis. Eur. Radiol. 30(5), 2703–2711 (2019). https://doi.org/10.1007/s00330-019-06606-w
Lederer, D.J., Martinez, F.J.: Idiopathic pulmonary fibrosis. N. Engl. J. Med. 378(19), 1811–1823 (2018). https://doi.org/10.1056/NEJMra1705751
Nardelli, P., Ross, J.C., San José Estépar, R.: Generative-based airway and vessel morphology quantification on chest CT images. Med. Image Anal. 63, 101691 (2020). https://doi.org/10.1016/j.media.2020.101691
Pakzad, A., et al.: Evaluation of automated airway morphological quantification for assessing fibrosing lung disease. Technical report, November 2021. arXiv:2111.10443, arXiv. https://doi.org/10.48550/ARXIV.2111.10443
Pakzad, A., Jacob, J.: Radiology of bronchiectasis. Clin. Chest Med. 43(1), 47–60 (2022). https://doi.org/10.1016/j.ccm.2021.11.004
Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates, Inc. (2019). http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf
Quan, K., et al.: Tapering analysis of airways with bronchiectasis. In: Angelini, E.D., Landman, B.A. (eds.) Medical Imaging 2018: Image Processing, vol. 10574, p. 87. SPIE, March 2018. https://doi.org/10.1117/12.2292306
Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training (2017). https://doi.org/10.48550/ARXIV.1612.07828, https://arxiv.org/abs/1612.07828
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 [cs] (April 2015). https://doi.org/10.48550/ARXIV.1409.1556
Weibel, E.R.: Morphometry of the Human Lung. Springer, Berlin, Heidelberg (1963). https://doi.org/10.1007/978-3-642-87553-3_6
Willemink, M.J., et al.: Preparing medical imaging data for machine learning. Radiology 295(1), 4–15 (2020). https://doi.org/10.1148/radiol.2020192224
Xie, M., Liu, X., Cao, X., Guo, M., Li, X.: Trends in prevalence and incidence of chronic respiratory diseases from 1990 to 2017. Respir. Res. 21(1), 1–13 (2020). https://doi.org/10.1186/s12931-020-1291-8
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. Image Anal. 24(1), 1–17 (2015). https://doi.org/10.1016/j.media.2015.05.003
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122 [cs] (April 2016). https://doi.org/10.48550/ARXIV.1511.07122
Acknowledgements
This research was funded in whole or in part by the Wellcome Trust [209553/Z/17/Z]. For the purpose of open access, the author has applied a CC-BY public copyright licence to any author accepted manuscript version arising from this submission. AP is funded jointly by the Cystic Fibrosis Trust and EPSRC i4health, centre for doctoral training studentship. JJ was supported by a Wellcome Trust Clinical Research Career Development Fellowship and the NIHR UCLH Biomedical Research Centre, UK.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pakzad, A. et al. (2022). Airway Measurement by Refinement of Synthetic Images Improves Mortality Prediction in Idiopathic Pulmonary Fibrosis. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds) Deep Generative Models. DGM4MICCAI 2022. Lecture Notes in Computer Science, vol 13609. Springer, Cham. https://doi.org/10.1007/978-3-031-18576-2_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-18576-2_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18575-5
Online ISBN: 978-3-031-18576-2
eBook Packages: Computer ScienceComputer Science (R0)
-
Published in cooperation with
http://miccai.org/
