Abstract
Hyperpolarized gas MRI enables visualization of regional lung ventilation with high spatial resolution. Segmentation of the ventilated lung is required to calculate clinically relevant biomarkers. Recent research in deep learning (DL) has shown promising results for numerous segmentation problems. In this work, we evaluate a 3D V-Net to segment ventilated lung regions on hyperpolarized gas MRI scans. The dataset consists of 743 helium-3 (3He) or xenon-129 (129Xe) volumetric scans and corresponding expert segmentations from 326 healthy subjects and patients with a wide range of pathologies. We evaluated segmentation performance for several DL experimental methods via overlap, distance and error metrics and compared them to conventional segmentation methods, namely, spatial fuzzy c-means (SFCM) and K-means clustering. We observed that training on combined 3He and 129Xe MRI scans outperformed other DL methods, achieving a mean ± SD Dice of 0.958 ± 0.022, average boundary Hausdorff distance of 2.22 ± 2.16 mm, Hausdorff 95th percentile of 8.53 ± 12.98 mm and relative error of 0.087 ± 0.049. Moreover, no difference in performance was observed between 129Xe and 3He scans in the testing set. Combined training on 129Xe and 3He yielded statistically significant improvements over the conventional methods (p < 0.0001). The DL approach evaluated provides accurate, robust and rapid segmentations of ventilated lung regions and successfully excludes non-lung regions such as the airways and noise artifacts and is expected to eliminate the need for, or significantly reduce, subsequent time-consuming manual editing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fain, S.B., Korosec, F.R., Holmes, J.H., O’Halloran, R., Sorkness, R.L., Grist, T.M.: Functional lung imaging using hyperpolarized gas MRI. J. Magn. Reson. Imaging: Off. J. Int. Soc. Magn. Reson. Med. 25, 910–923 (2007)
Woodhouse, N., et al.: Combined helium-3/proton magnetic resonance imaging measurement of ventilated lung volumes in smokers compared to never-smokers. J. Magn. Reson. Imaging 21, 365–369 (2005)
Tustison, N.J., et al.: Ventilation-based segmentation of the lungs using hyperpolarized (3)He MRI. J. Magn. Reson. Imaging 34, 831–841 (2011)
Kirby, M., et al.: Hyperpolarized He-3 magnetic resonance functional imaging semiautomated segmentation. Acad. Radiol. 19, 141–152 (2011)
Hughes, P.J.C., Horn, F.C., Collier, G.J., Biancardi, A., Marshall, H., Wild, J.M.: Spatial fuzzy c-means thresholding for semiautomated calculation of percentage lung ventilated volume from hyperpolarized gas and (1)H MRI. J. Magn. Reson. Imaging 47, 640–646 (2018)
Bakator, M., Radosav, D.: Deep learning and medical diagnosis: a review of literature. Multimodal Technol. Interact. 2, 47 (2018)
Lundervold, A.S., Lundervold, A.: An overview of deep learning in medical imaging focusing on MRI. Zeitschrift für Medizinische Physik 29, 102–127 (2019)
Tajbakhsh, N., et al.: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans. Med. Imaging 35, 1299–1312 (2016)
Zha, W., Fain, S.B., Schiebler, M.L., Evans, M.D., Nagle, S.K., Liu, F.: Deep convolutional neural networks with multiplane consensus labeling for lung function quantification using UTE proton MRI. J. Magn. Reson. Imaging 50, 1169–1181 (2019)
Tustison, N.J., et al.: Convolutional neural networks with template-based data augmentation for functional lung image quantification. Acad. Radiol. 26, 412–423 (2019)
Horn, F.C., et al.: Lung ventilation volumetry with same-breath acquisition of hyperpolarized gas and proton MRI. NMR Biomed. 27, 1461–1467 (2014)
Stewart, N.J., Norquay, G., Griffiths, P.D., Wild, J.M.: Feasibility of human lung ventilation imaging using highly polarized naturally abundant xenon and optimized three-dimensional steady-state free precession. Magn. Reson. Med. 74, 346–352 (2015)
Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: Proceedings of 2016 Fourth International Conference on 3D Vision, pp. 565–571 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International Conference on Computer Vision (ICCV 2015), vol. 1502 (2015)
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)
Gibson, E., et al.: NiftyNet: a deep-learning platform for medical imaging. Comput. Methods Programs Biomed. 158, 113–122 (2018)
Abadi, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)
Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26, 297–302 (1945)
Beauchemin, M., Thomson, K.P.B., Edwards, G.: On the hausdorff distance used for the evaluation of segmentation results. Can. J. Remote. Sens. 24, 3–8 (1998)
Shapiro, M.D., Blaschko, M.B.: On hausdorff distance measures. Computer Vision Laboratory University of Massachusetts, Amherst, vol. 1003 (2004)
Biancardi, A.M., Wild, J.M.: New disagreement metrics incorporating spatial detail – applications to lung imaging. In: Valdés Hernández, M., González-Castro, V. (eds.) MIUA 2017. CCIS, vol. 723, pp. 804–814. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-60964-5_70
Acknowledgements
This work was supported by Yorkshire Cancer Research (S406BT), Weston Park Cancer Charity, National Institute of Health Research, the Medical Research Council and GlaxoSmithKline (BIDS3000032592). The authors also acknowledge access to high-performance computing equipment available via an Engineering and Physical Sciences Research Council Equipment Grant (EP/P020275/1; Joint Academic Data Science Endeavour) and support provided for this equipment grant via Research Software Engineering Sheffield.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Astley, J.R. et al. (2020). 3D Deep Convolutional Neural Network-Based Ventilated Lung Segmentation Using Multi-nuclear Hyperpolarized Gas MRI. In: Petersen, J., et al. Thoracic Image Analysis. TIA 2020. Lecture Notes in Computer Science(), vol 12502. Springer, Cham. https://doi.org/10.1007/978-3-030-62469-9_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-62469-9_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62468-2
Online ISBN: 978-3-030-62469-9
eBook Packages: Computer ScienceComputer Science (R0)