Abstract
Accurate prediction of airflow distribution and aerosol transport in the human lungs, which are difficult to be measured in vivo but important to understand the structure and function relationship, is challenging. It is because the interplay between them spans more than two orders of magnitude in dimension from the trachea to alveoli. This chapter reviews the techniques and strategies for modeling lungs both within and between subjects, viz., subject specificity versus generalization from individuals to populations, with both exhibiting multiscale characteristics. For “within-subject” modeling, a computed tomography (CT)-derived subject-specific computational fluid dynamics (CFD) lung model is presented. The pipeline for building such an imaging-based lung model is composed of image segmentation and processing, geometrical modeling labeled with anatomical information, image registration, three-dimensional (accurate) and one-dimensional (approximate) coupling techniques, and a high-fidelity turbulent flow model. The subject-specific model is essential in predicting local structural and functional interactions. For “between subjects” modeling, machine learning is employed to identify homogeneous subpopulations (clusters), among healthy and diseased populations, aiming to bridge individual and population scales. For this purpose, three major issues need to be addressed. They are intersubject variability (due to, e.g., gender, age, and height), inter-site variability (due to scanner and imaging protocol differences), and definition of quantitative CT imaging-based metrics at multiple scales (due to alterations at different disease stages) needed for clustering. The use of the cluster membership to select representative subjects for detailed CFD analysis enables an examination of the cluster-specific structural and functional relationships.
References
Burgel P-R, Roche N, Paillasseur J-L et al (2012) Clinical COPD phenotypes identified by cluster analysis: validation with mortality. Eur Respir J 40:495–496
Busacker A, Newell JD, Keefe T et al (2009) A multivariate analysis of risk factors for the air-trapping asthmatic phenotype as measured by quantitative CT analysis. Chest 135:48–56
Busse WW, Lemanske RF Jr (2001) Asthma. N Engl J Med 344:350–362
Cho MH, Washko GR, Hoffmann TJ, et al (2010) Cluster analysis in severe emphysema subjects using phenotype and genotype data: an exploratory investigation. Respir Res. 11:30. https://doi.org/10.1186/1465-9921-11-30
Choi J (2011) Multiscale numerical analysis of airflow in CT-based subject specific breathing human lungs. The University of Iowa, Iowa City
Choi J, Tawhai MH, Hoffman EA, Lin CL (2009) On intra- and intersubject variabilities of airflow in the human lungs. Phys Fluids 21(10):101901. Epub 2009 Oct 13
Choi J, Xia G, Tawhai MH et al (2010) Numerical study of high-frequency oscillatory air flow and convective mixing in a CT-based human airway model. Ann Biomed Eng 38(12):3550–3571. https://doi.org/10.1007/s10439-010-0110-7. Epub 2010 Jul 8
Choi J, Hoffman EA, Lee CH et al (2013a) MDCT-based image matching for assessment of heterogeneity of regional ventilation and methacholine response in asthmatics. American Thoracic Society International Conference, May 17–22, Philadelphia, PA. Am J Respir Crit Care Med 187:A3740
Choi J, Yin Y, Hoffman EA et al (2013b) Airflow in a multiscale subject-specific breathing human lung model. 66th APS division of fluid dynamics gallery of fluid motion, Nov. 24–26, Pittsburgh, PA. arXiv:1310.5057 [physics.flu-dyn]
Choi S, Hoffman EA, Wenzel SE et al (2013c) Registration-based assessment of regional lung function via volumetric CT images of normal subjects vs. severe asthmatics. J Appl Physiol 115:730–742
Choi S, Hoffman EA, Wenzel SE et al (2014) Improved CT-based estimate of pulmonary gas trapping accounting for scanner and lung volume variations in a multi-center study. J Appl Physiol 117:593–603
Choi S, Hoffman EA, Wenzel SE et al (2015) Quantitative assessment of multiscale structural and functional alterations in asthmatic populations. J Appl Physiol 118:1286–1298
Choi S, Choi J, Hoffman EA et al (2016) Relationship between pulmonary airflow and resistance in patients with airway narrowing using an 1-D network resistance and compliance model. 69th APS Division of Fluid Dynamics, Nov. 20–22, Portland
Choi J, Hoffman EA, Lin CL et al (2017a) Quantitative computed tomography determined regional lung mechanics in normal nonsmokers, normal smokers and metastatic sarcoma subjects. PLoS One 12(7):e0179812. https://doi.org/10.1371/journal.pone.0179812
Choi S, Hoffman EA, Wenzel SE et al (2017b) Quantitative computed tomographic imaging-based clustering differentiates asthmatic subgroups with distinctive clinical phenotypes. J Allergy Clin Immunol 140:690–700 e698
Choi S, Haghighi B, Choi J et al (2017c) Differentiation of quantitative CT imaging phenotypes in asthma versus COPD. BMJ Open Resp Res 4(1):e000252
Choi S, Choi J, Lin CL (2018) Contributions of kinetic energy and viscous dissipation to airway resistance in pulmonary inspiratory and expiratory airflows in successive symmetric airway models with various bifurcation angles. J Biomech Eng 140(1):011010
Collins FS, Varmus H (2015) A new initiative on precision medicine. N Engl J Med 372(9):793–795. https://doi.org/10.1056/NEJMp1500523. Epub 2015 Jan 30
Couper D, LaVange LM, Han M et al (2014) Design of the subpopulations and intermediate outcomes in COPD study (SPIROMICS). Thorax 69(5):491–494. https://doi.org/10.1136/thoraxjnl-2013-203897. Epub 2013 Sep 12
Crum WR, Hartkens T, Hill DL (2004) Non-rigid image registration: theory and practice. Br J Radiol 77 Spec No 2:S140–S153
De Marco R, Pesce G, Marcon A et al (2013) The coexistence of asthma and chronic obstructive pulmonary disease (COPD): prevalence and risk factors in young, middle-aged and elderly people from the general population. PLoS One 8:e62985
Deo RC (2015) Machine learning in medicine. Circulation 132:1920–1930
Ellingwood ND, Yin Y, Smith M, Lin CL (2016) Efficient methods for implementation of multi-level nonrigid mass-preserving image registration on GPUs and multi-threaded CPUs. Comput Methods Prog Biomed 127:290–300. https://doi.org/10.1016/j.cmpb.2015.12.018. Epub 2016 Jan 6
Fuld MK, Halaweish AF, Newell JD Jr et al (2013) Optimization of dual-energy xenon-computed tomography for quantitative assessment of regional pulmonary ventilation. Investig Radiol 48(9):629–637. https://doi.org/10.1097/RLI.0b013e31828ad647
Galban CJ, Han MK, Boes JL (2012) Computed tomography-based biomarker provides unique signature for diagnosis of COPD phenotypes and disease progression. Nat Med 18(11):1711–1715. https://doi.org/10.1038/nm.2971
Garcia-Aymerich J, Gómez FP, Benet M et al (2011) Identification and prospective validation of clinically relevant chronic obstructive pulmonary disease (COPD) subtypes. Thorax 66:430–437
Gibson P, Simpson J (2009) The overlap syndrome of asthma and COPD: what are its features and how important is it? Thorax 64:728–735
Gupta S, Hartley R, Khan UT et al (2014) Quantitative computed tomography-derived clusters: redefining airway remodeling in asthmatic patients. J Allergy Clin Immunol 133:729–738
Haghighi B, Ellingwood N, Yin Y et al (2017a) A GPU-based symmetric non-rigid image registration method in human lung. Med Biol Eng Comput. https://doi.org/10.1007/s11517-017-1690-2. Epub 2017 Aug 1 [ahead of print]
Haghighi B, Choi J, Choi S, et al. (2017b) Cluster-specific small airway modeling for imaging-based CFD analysis of pulmonary air flow and particle deposition in COPD smokers. 70th APS Division of Fluid Dynamics, Nov. 19–21, 2017, Denver
Hoffman EA, Chon D (2005) Computed tomography studies of lung ventilation and perfusion. Proc Am Thorac Soc 2(6):492–498, 506
Hoffman EA, McLennan G (1997) Assessment of the pulmonary structure-function relationship and clinical outcomes measures: quantitative volumetric CT of the lung. Acad Radiol 4(11):758–776
Hoffman EA, Lynch DA, Barr RG et al (2016) Pulmonary CT and MRI phenotypes that help explain chronic pulmonary obstruction disease pathophysiology and outcomes. J Magn Reson Imaging 43(3):544–557. https://doi.org/10.1002/jmri.25010. Epub 2015 Jul 22
Iyer KS, Newell JD Jr, Jin D et al (2016) Quantitative dual-energy computed tomography supports a vascular etiology of smoking-induced inflammatory lung disease. Am J Respir Crit Care Med 193(6):652–661. https://doi.org/10.1164/rccm.201506-1196OC
Jahani N, Yin Y, Hoffman EA, Lin CL (2014) Assessment of regional non-linear tissue deformation and air volume change of human lungs via image registration. J Biomech 47(7):1626–1633. https://doi.org/10.1016/j.jbiomech.2014.02.040. Epub 2014 Mar 13
Jahani N, Choi S, Choi J et al (2015) Assessment of regional ventilation and deformation using 4D-CT imaging for healthy human lungs during tidal breathing. J Appl Physiol 119(10):1064–1074. https://doi.org/10.1152/japplphysiol.00339.2015. Epub 2015 Aug 27
Jahani N, Choi S, Choi J et al (2017) A four-dimensional computed tomography comparison of healthy and asthmatic human lungs. J Biomech 56:102–110. https://doi.org/10.1016/j.jbiomech.2017.03.012. Epub 2017 Mar 18
Kleinstreuer C, Zhang Z (2003) Laminar-to-turbulent fluid-particle flows in a human airway model. Int J Multiphase Flow 29(2):271–289
Kohonen T (1998) The self-organizing map. Neurocomputing 21(1):1–6. https://doi.org/10.1016/S0925-2312(98)00030-7
Lambert AR, O’Shaughnessy PT, Tawhai MH et al (2011) Regional deposition of particles in an image-based airway model: large-eddy simulation and left-right lung ventilation asymmetry. Aerosol Sci Technol 45(1):11–25. https://doi.org/10.1080/02786826.2010.517578
Ledford H (2016) Obama’s science legacy: betting big on biomedical science. Nature 536(7617):385–386. https://doi.org/10.1038/536385a
Lin CL, Tawhai MH, McLennan G, Hoffman EA (2007) Characteristics of the turbulent laryngeal jet and its effect on airflow in the human intra-thoracic airways. Respir Physiol Neurobiol 157(2–3):295–309. https://doi.org/10.1016/j.resp.2007.02.006. Epub 2007 Feb 14
Lin CL, Tawhai MH, McLennan G, Hoffman EA (2009) Computational fluid dynamics: multiscale simulation of gas flow in subject-specific models of the human lung. IEEE Eng Med Biol Mag 28(3):25–33. https://doi.org/10.1109/memb.2009.932480
Lin CL, Tawhai MH, Hoffman EA (2013) Multiscale image-based modeling and simulation of gas flow and particle transport in the human lungs. Wiley Interdiscip Rev Syst Biol Med 5(5):643–655. https://doi.org/10.1002/wsbm.1234. Epub 2013 Jul 10
Longest PW, Tian G, Walenga RL, Hindle M (2012) Comparing MDI and DPI aerosol deposition using in vitro experiments and a new stochastic individual path (SIP) model of the conducting airways. Pharm Res 29(6):1670–1688
Magoulas GD, Prentza A (2001) Machine learning in medical applications. Mach. Learning Appl. (Lecture Notes Comput. Sci.). Berlin/Heidelberg, Springer, 2049:300--307
Mesko B (2017) The role of artificial intelligence in precision medicine. Expert Rev Precis Med Drug Dev 2(5):239–241. https://doi.org/10.1080/23808993.2017.1380516
Miyawaki S, Tawhai MH, Hoffman EA, Lin CL (2012) Effect of carrier gas properties on aerosol distribution in a CT-based human airway numerical model. Ann Biomed Eng 40(7):1495–1507
Miyawaki S, Choi S, Hoffman EA, Lin CL (2016a) A 4DCT imaging-based breathing lung model with relative hysteresis. J Comput Phys 326:76–90. https://doi.org/10.1016/j.jcp.2016.08.039. Epub 2016 Aug 31
Miyawaki S, Hoffman EA, Lin CL (2016b) Effect of static vs. dynamic imaging on particle transport in CT-based numerical models of human central airways. J Aerosol Sci 100:129–139. https://doi.org/10.1016/j.jaerosci.2016.07.006. Epub 2016 Jul 16
Miyawaki S, Tawhai MH, Hoffman EA et al (2017a) Automatic construction of subject-specific human airway geometry including trifurcations based on a CT-segmented airway skeleton and~surface. Biomech Model Mechanobiol 16:583–596. https://doi.org/10.1007/s10237-016-0838-6
Miyawaki S, Hoffman EA, Lin CL (2017b) Numerical simulations of aerosol delivery to the human lung with an idealized laryngeal model, image-based airway model, and automatic meshing algorithm. Comput Fluids 148:1–9. https://doi.org/10.1016/j.compfluid.2017.02.008. Epub 2017 Feb 10
Montaudon M, Lederlin M, Reich S et al (2009) Bronchial measurements in patients with asthma: comparison of quantitative thin-section CT findings with those in healthy subjects and correlation with pathologic findings. Radiology 253:844–853
Paoletti M, Camiciottoli G, Meoni E et al (2009) Explorative data analysis techniques and unsupervised clustering methods to support clinical assessment of chronic obstructive pulmonary disease (COPD) phenotypes. J Biomed Inform 42:1013–1021
Sieren JP, Newell JD Jr, Barr RG et al (2016) SPIROMICS protocol for multicenter quantitative computed tomography to phenotype the lungs. Am J Respir Crit Care Med 194(7):794–806
Tawhai MH, Lin CL (2011) Airway gas flow. Compr Physiol 1:1135–1157
Tawhai MH, Pullan AJ, Hunter PJ (2000) Generation of an anatomically based three-dimensional model of the conducting airways. Ann Biomed Eng 28(7):793–802. https://doi.org/10.1114/1.1289457
Tawhai MH, Hunter P, Tschirren J et al (2004) CT-based geometry analysis and finite element models of the human and ovine bronchial tree. J Appl Physiol 97(6):2310–2321. https://doi.org/10.1152/japplphysiol.00520.2004. Epub 2004 Aug 20
Tawhai MH, Hoffman EA, Lin CL (2009) The lung physiome: merging imaging-based measures with predictive computational models of structure and function. Wiley Interdiscip Rev Syst Biol Med 1(1):61–72
Uppaluri R, Mitsa T, Sonka M et al (1997) Quantification of pulmonary emphysema from lung computed tomography images. Am J Respir Crit Care Med 156(1):248–254
Uppaluri R, Hoffman EA, Sonka M et al (1999) Computer recognition of regional lung disease patterns. Am J Respir Crit Care Med 160(2):648–254
van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9:2579–2605
Wenzel SE, Busse WW (2007) Severe asthma: lessons from the severe asthma research program. J Allergy Clin Immunol 119:14–21
Wongviriyawong C, Harris RS, Greenblatt E et al (2013) Peripheral resistance: a link between global airflow obstruction and regional ventilation distribution. J Appl Physiol 114(4):504–514
Wu D, Tawhai MH, Hoffman EA, Lin CL (2014) A numerical study of heat and water vapor transfer in MDCT-based human airway models. Ann Biomed Eng 42(10):2117–2131. https://doi.org/10.1007/s10439-014-1074-9
Wu D, Miyawaki S, Tawhai MH et al (2015) A numerical study of water loss rate distributions in MDCT-based human airway models. Ann Biomed Eng 43(11):2708–2721. https://doi.org/10.1007/s10439-015-1318-3. Epub 2015 Apr 14
Xu Y, Sonka M, McLennan G et al (2006a) MDCT-based 3-D texture classification of emphysema and early smoking related lung pathologies. IEEE Trans Med Imaging 25(4):464–475
Xu Y, van Beek EJ, Hwanjo Y et al (2006b) Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). Acad Radiol 13(8):969–978
Yang X, Pei J, Shi J (2014) Inverse consistent non-rigid image registration based on robust point set matching. Biomed Eng Online. 13 Suppl 2:S2. https://doi.org/10.1186/1475-925X-13-S2-S2. Epub 2014 Dec 11
Yin Y, Hoffman EA, Lin CL (2009) Mass preserving nonrigid registration of CT lung images using cubic B-spline. Med Phys 36:4213–4222
Yin Y, Choi J, Hoffman EA et al (2010) Simulation of pulmonary air flow with a subject-specific boundary condition. J Biomech 43(11):2159–2163. https://doi.org/10.1016/j.jbiomech.2010.03.048
Yin Y, Choi J, Hoffman EA et al (2013) A multiscale MDCT image-based breathing lung model with time-varying regional ventilation. J Comput Phys 244:168–192
Zhang Z, Kleinstreuer C, Kim CS (2002) Micro-particle transport and deposition in a human oral airway model. J Aerosol Sci 33(12):1635–1652
Acknowledgments
This work was supported in part by NIH grants U01-HL114494, R01 HL094315, R01-HL112986, and S10-RR022421 as well as Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2017R1D1A1B03034157). We also thank the San Diego Supercomputer Center (SDSC), the Texas Advanced Computing Center (TACC), and XSEDE sponsored by the National Science Foundation for the computer time.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this entry
Cite this entry
Lin, CL., Choi, S., Haghighi, B., Choi, J., Hoffman, E.A. (2018). Cluster-Guided Multiscale Lung Modeling via Machine Learning. In: Andreoni, W., Yip, S. (eds) Handbook of Materials Modeling. Springer, Cham. https://doi.org/10.1007/978-3-319-50257-1_98-1
Download citation
DOI: https://doi.org/10.1007/978-3-319-50257-1_98-1
Received:
Accepted:
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50257-1
Online ISBN: 978-3-319-50257-1
eBook Packages: Springer Reference Physics and AstronomyReference Module Physical and Materials ScienceReference Module Chemistry, Materials and Physics