Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Application of artificial intelligence in quantifying lung deposition dose of black carbon in people with exposure to ambient combustion particles

Journal of Exposure Science & Environmental Epidemiology (2023)Cite this article

Abstract

Background

Understanding lung deposition dose of black carbon is critical to fully reconcile epidemiological evidence of combustion particles induced health effects and inform the development of air quality metrics concerning black carbon. Macrophage carbon load (MaCL) is a novel cytology method that quantifies lung deposition dose of black carbon, however it has limited feasibility in large-scale epidemiological study due to the labor-intensive manual counting.

Objective

To assess the association between MaCL and episodic elevation of combustion particles; to develop artificial intelligence based counting algorithm for MaCL assay.

Methods

Sputum slides were collected during episodic elevation of ambient PM2.5 (n = 49, daily PM2.5 > 10 µg/m3 for over 2 weeks due to wildfire smoke intrusion in summer and local wood burning in winter) and low PM2.5 period (n = 39, 30-day average PM2.5 < 4 µg/m3) from the Lovelace Smokers cohort.

Results

Over 98% individual carbon particles in macrophages had diameter <1 µm. MaCL levels scored manually were highly responsive to episodic elevation of ambient PM2.5 and also correlated with lung injury biomarker, plasma CC16. The association with CC16 became more robust when the assessment focused on macrophages with higher carbon load. A Machine-Learning algorithm for Engulfed cArbon Particles (MacLEAP) was developed based on the Mask Region-based Convolutional Neural Network. MacLEAP algorithm yielded excellent correlations with manual counting for number and area of the particles. The algorithm produced associations with ambient PM2.5 and plasma CC16 that were nearly identical in magnitude to those obtained through manual counting.

Impact statement

Understanding lung black carbon deposition is crucial for comprehending health effects of combustion particles. We developed “Machine-Learning algorithm for Engulfed cArbon Particles (MacLEAP)”, the first artificial intelligence algorithm for quantifying airway macrophage black carbon. Our study bolstered the algorithm with more training images and its first use in air pollution epidemiology. We revealed macrophage carbon load as a sensitive biomarker for heightened ambient combustion particles due to wildfires and residential wood burning.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Pipeline for the development of the Machine-Learning algorithm for Engulfed cArbon Particles (MacLEAP) algorithm.
Fig. 2: Episodic elevation of PM2.5 and areas of the particles in macrophages.
Fig. 3: MaCL and lung injury biomarker CC16.
Fig. 4: Correlations between manual and MacLEAP counting for NoPs and AoPs.

Similar content being viewed by others

Data availability

Sputum images and MaCL measures were submitted to the Lovelace Smokers cohort with Dr. Steven A. Belinsky as the Principal Investigator for the cohort. The Lovelace Respiratory Research Institute owns the cohort and manages all data and tissue request to ensure compliance with the Institutional Review Board protocol, consent form, institutional regulations, as well as related National Institute of Health policies. Ms. Maria Picchi as the data manager for the Lovelace Smokers cohort is the contact person for handling any request for data and samples from the Lovelace Smokers cohort. Researchers who would like to request training script and masking images of macrophages and black carbons need to reach out to Ms. Picchi and correspondence authors. Finalized weigh file for MacLEAP algorithm and quantification/application script are now shared via GitHub Platform (https://github.com/yuxz99/MacLEAP).

References

  1. Cordero RR, Sepúlveda E, Feron S, Damiani A, Fernandoy F, Neshyba S, et al. Black carbon footprint of human presence in Antarctica. Nat Commun. 2022;13:984.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  2. The Lancet Public H. Mitigating climate change must be a priority for public health. Lancet Public Health. 2021;6:e620.

    Article  Google Scholar 

  3. Dedoussi IC, Eastham SD, Monier E, Barrett SRH. Premature mortality related to United States cross-state air pollution. Nature. 2020;578:261–5.

    Article  CAS  PubMed  Google Scholar 

  4. Thurston GD, Ito K, Lall R. A source apportionment of U.S. fine particulate matter air pollution. Atmos Environ (1994). 2011;45:3924–36.

    Article  CAS  PubMed  Google Scholar 

  5. Disparities in the Impact of Air Pollution. https://www.lung.org/clean-air/outdoors/who-is-at-risk/disparities.

  6. Rogalsky DK, Mendola P, Metts TA, Martin WJ 2nd. Estimating the number of low-income americans exposed to household air pollution from burning solid fuels. Environ Health Perspect. 2014;122:806–10.

    Article  PubMed  PubMed Central  Google Scholar 

  7. Noonan CW, Ward TJ, Semmens EO. Estimating the number of vulnerable people in the United States exposed to residential wood smoke. Environ Health Perspect. 2015;123:A30.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Rogalsky DK, Mendola P, Metts TA, Martin WJ 2nd. Estimating the number of vulnerable people in the United States exposed to residential wood smoke: Rogalsky et al. respond. Environ Health Perspect. 2015;123:A30–31.

    Article  PubMed  PubMed Central  Google Scholar 

  9. WHO. WHO global air quality guidelines. Particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. Geneva: World Health Organization; 2021.

  10. Janssen NA, Hoek G, Simic-Lawson M, Fischer P, van Bree L, ten Brink H, et al. Black carbon as an additional indicator of the adverse health effects of airborne particles compared with PM10 and PM2.5. Environ Health Perspect. 2011;119:1691–9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Grahame TJ, Klemm R, Schlesinger RB. Public health and components of particulate matter: the changing assessment of black carbon. J Air Waste Manag Assoc. 2014;64:620–60.

    Article  CAS  PubMed  Google Scholar 

  12. Aguilera R, Corringham T, Gershunov A, Benmarhnia T. Wildfire smoke impacts respiratory health more than fine particles from other sources: observational evidence from Southern California. Nat Commun. 2021;12:1493.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  13. Thurston GD, Burnett RT, Turner MC, Shi Y, Krewski D, Lall R, et al. Ischemic heart disease mortality and long-term exposure to source-related components of U.S. fine particle air pollution. Environ Health Perspect. 2016;124:785–94.

    Article  CAS  PubMed  Google Scholar 

  14. Ostro B, Hu J, Goldberg D, Reynolds P, Hertz A, Bernstein L, et al. Associations of mortality with long-term exposures to fine and ultrafine particles, species and sources: results from the California Teachers Study Cohort. Environ Health Perspect. 2015;123:549–56.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Beelen R, Hoek G, Raaschou-Nielsen O, Stafoggia M, Andersen ZJ, Weinmayr G, et al. Natural-cause mortality and long-term exposure to particle components: an analysis of 19 European cohorts within the multi-center ESCAPE project. Environ Health Perspect. 2015;123:525–33.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Hime NJ, Marks GB, Cowie CT. A comparison of the health effects of ambient particulate matter air pollution from five emission sources. Int J Environ Res Public Health. 2018;15:1206.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Martenies SE, Keller JP, WeMott S, Kuiper G, Ross Z, Allshouse WB, et al. A spatiotemporal prediction model for black carbon in the Denver metropolitan area, 2009–2020. Environ Sci Technol. 2021;55:3112–23.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Jung KH, Goodwin KE, Perzanowski MS, Chillrud SN, Perera FP, Miller RL, et al. Personal exposure to black carbon at school and levels of fractional exhaled nitric oxide in New York City. Environ Health Perspect. 2021;129:97005.

    Article  CAS  PubMed  Google Scholar 

  19. Cassee FR, Heroux ME, Gerlofs-Nijland ME, Kelly FJ. Particulate matter beyond mass: recent health evidence on the role of fractions, chemical constituents and sources of emission. Inhal Toxicol. 2013;25:802–12.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Nagappan A, Park SB, Lee SJ, Moon Y. Mechanistic implications of biomass-derived particulate matter for immunity and immune disorders. Toxics. 2021;9:18.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Bunn HJ, Dinsdale D, Smith T, Grigg J. Ultrafine particles in alveolar macrophages from normal children. Thorax. 2001;56:932–4.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Bai Y, Bove H, Nawrot TS, Nemery B. Carbon load in airway macrophages as a biomarker of exposure to particulate air pollution; a longitudinal study of an international Panel. Part Fibre Toxicol. 2018;15:14.

    Article  PubMed  PubMed Central  Google Scholar 

  23. Orr A, Migliaccio CAL, Buford M, Ballou S, Migliaccio CT. Sustained effects on lung function in community members following exposure to hazardous PM2.5 levels from wildfire smoke. Toxics. 2020;8:53.

    Article  PubMed  PubMed Central  Google Scholar 

  24. Bai Y, Brugha RE, Jacobs L, Grigg J, Nawrot TS, Nemery B. Carbon loading in airway macrophages as a biomarker for individual exposure to particulate matter air pollution - a critical review. Environ Int. 2015;74:32–41.

    Article  CAS  PubMed  Google Scholar 

  25. Cheng W, Liu Y, Tang J, Duan H, Wei X, Zhang X, et al. Carbon content in airway macrophages and genomic instability in Chinese carbon black packers. Arch Toxicol. 2020;94:761–71.

    Article  CAS  PubMed  Google Scholar 

  26. Jacobs L, Emmerechts J, Mathieu C, Hoylaerts MF, Fierens F, Hoet PH, et al. Air pollution related prothrombotic changes in persons with diabetes. Environ Health Perspect. 2010;118:191–6.

    Article  CAS  PubMed  Google Scholar 

  27. Kulkarni N, Pierse N, Rushton L, Grigg J. Carbon in airway macrophages and lung function in children. N Engl J Med. 2006;355:21–30.

    Article  CAS  PubMed  Google Scholar 

  28. Eguiluz-Gracia I, Schultz HH, Sikkeland LI, Danilova E, Holm AM, Pronk CJ, et al. Long-term persistence of human donor alveolar macrophages in lung transplant recipients. Thorax. 2016;71:1006–11.

    Article  PubMed  Google Scholar 

  29. Nayak DK, Zhou F, Xu M, Huang J, Tsuji M, Hachem R, et al. Long-term persistence of donor alveolar macrophages in human lung transplant recipients that influences donor-specific immune responses. Am J Transpl. 2016;16:2300–11.

    Article  CAS  Google Scholar 

  30. Bai Y, Casas L, Scheers H, Janssen BG, Nemery B, Nawrot TS. Mitochondrial DNA content in blood and carbon load in airway macrophages. A panel study in elderly subjects. Environ Int. 2018;119:47–53.

    Article  CAS  PubMed  Google Scholar 

  31. Cao X, Lin L, Sood A, Ma Q, Zhang X, Liu Y, et al. Small airway wall thickening assessed by computerized tomography is associated with low lung function in Chinese carbon black packers. Toxicol Sci. 2020;178:26–35.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Liu H, Li J, Ma Q, Tang J, Jiang M, Cao X, et al. Chronic exposure to diesel exhaust may cause small airway wall thickening without lumen narrowing: a quantitative computerized tomography study in Chinese diesel engine testers. Part Fibre Toxicol. 2021;18:14.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Miri M, Rezaei H, Momtaz SM, Najafi ML, Adli A, Pajohanfar NS, et al. Determinants of carbon load in airway macrophages in pregnant women. Environ Pollut. 2022;297:118765.

    Article  CAS  PubMed  Google Scholar 

  34. Kulkarni NS, Prudon B, Panditi SL, Abebe Y, Grigg J. Carbon loading of alveolar macrophages in adults and children exposed to biomass smoke particles. Sci Total Environ. 2005;345:23–30.

    Article  CAS  PubMed  Google Scholar 

  35. Stirling DR, Swain-Bowden MJ, Lucas AM, Carpenter AE, Cimini BA, Goodman A. CellProfiler 4: improvements in speed, utility and usability. BMC Bioinforma. 2021;22:433.

    Article  Google Scholar 

  36. MacLEAP: machine-learning approach for recognition and quantification of carbon content in airway macrophages. In: Society of Toxicology 61st Annual Meeting. San Diego: Oxford University Press; 2022.

  37. He K, Gkioxari G, Dollár P, Girshick R. Mask R-CNN. In: IEEE International Conference on Computer Vision (ICCV). Venice: IEEE; 2017. p. 2980–8.

  38. Waleed A. Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow. GitHub repository; 2017. https://github.com/matterport/Mask_RCNN.

  39. Download Daily Data. https://www.epa.gov/outdoor-air-quality-data/download-daily-data.

  40. Martenies SE, Hoskovec L, Wilson A, Allshouse WB, Adgate JL, Dabelea D, et al. Assessing the impact of wildfires on the use of black carbon as an indicator of traffic exposures in environmental epidemiology studies. GeoHealth. 2021;5:e2020GH000347.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  41. Glojek K, Močnik G, Alas HDC, Cuesta-Mosquera A, Drinovec L, Gregorič A, et al. The impact of temperature inversions on black carbon and particle mass concentrations in a mountainous area. Atmos Chem Phys. 2022;22:5577–601.

    Article  CAS  Google Scholar 

  42. Stidley CA, Picchi MA, Leng S, Willink R, Crowell RE, Flores KG, et al. Multivitamins, folate, and green vegetables protect against gene promoter methylation in the aerodigestive tract of smokers. Cancer Res. 2010;70:568–74.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Leng S, Stidley CA, Willink R, Bernauer A, Do K, Picchi MA, et al. Double-strand break damage and associated DNA repair genes predispose smokers to gene methylation. Cancer Res. 2008;68:3049–56.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  44. Tejwani V, Woo H, Liu C, Tillery AK, Gassett AJ, Kanner RE, et al. Black carbon content in airway macrophages is associated with increased severe exacerbations and worse COPD morbidity in SPIROMICS. Respir Res. 2022;23:310.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Daisey JM, Mahanama KR, Hodgson AT. Toxic volatile organic compounds in simulated environmental tobacco smoke: emission factors for exposure assessment. J Expo Anal Environ Epidemiol. 1998;8:313–34.

    CAS  PubMed  Google Scholar 

  46. Hildemann LM, Markowski GR, Cass GR. Chemical composition of emissions from urban sources of fine organic aerosol. Environ Sci Technol. 1991;25:744–59.

    Article  CAS  Google Scholar 

  47. Bruse S, Sood A, Petersen H, Liu Y, Leng S, Celedon JC, et al. New Mexican Hispanic smokers have lower odds of chronic obstructive pulmonary disease and less decline in lung function than non-Hispanic whites. Am J Respir Crit Care Med. 2011;184:1254–60.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Leng S, Picchi MA, Meek PM, Jiang M, Bayliss SH, Zhai T, et al. Wood smoke exposure affects lung aging, quality of life, and all-cause mortality in New Mexican smokers. Respir Res. 2022;23:236.

    Article  PubMed  PubMed Central  Google Scholar 

  49. Petersen H, Leng S, Belinsky SA, Miller BE, Tal-Singer R, Owen CA, et al. Low plasma CC16 levels in smokers are associated with a higher risk for chronic bronchitis. Eur Respir J. 2015;46:1501–3.

    Article  PubMed  Google Scholar 

  50. Silfies JS, Schwartz S, Davidson MW. The diffraction barrier in optical microscopy. https://www.microscopyu.com/techniques/super-resolution/the-diffraction-barrier-in-optical-microscopy.

  51. Wang H, Duan H, Meng T, Yang M, Cui L, Bin P, et al. Local and systemic inflammation may mediate diesel engine exhaust-induced lung function impairment in a Chinese occupational cohort. Toxicol Sci. 2018;162:372–82.

    Article  CAS  PubMed  Google Scholar 

  52. Shijubo N, Itoh Y, Yamaguchi T, Shibuya Y, Morita Y, Hirasawa M, et al. Serum and BAL Clara cell 10 kDa protein (CC10) levels and CC10-positive bronchiolar cells are decreased in smokers. Eur Respir J. 1997;10:1108–14.

    Article  CAS  PubMed  Google Scholar 

  53. Hoffmann B, Boogaard H, de Nazelle A, Andersen ZJ, Abramson M, Brauer M, et al. WHO Air Quality Guidelines 2021-aiming for healthier air for all: a joint statement by medical, public health, scientific societies and patient representative organisations. Int J Public Health. 2021;66:1604465.

    Article  PubMed  PubMed Central  Google Scholar 

  54. Yin G, Wu X, Wu Y, Li H, Gao L, Zhu X, et al. Evaluating carbon content in airway macrophages as a biomarker of personal exposure to fine particulate matter and its acute respiratory effects. Chemosphere. 2021;283:131179.

    Article  CAS  PubMed  Google Scholar 

  55. Thomas ED, Ramberg RE, Sale GE, Sparkes RS, Golde DW. Direct evidence for a bone marrow origin of the alveolar macrophage in man. Science. 1976;192:1016–8.

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

Our initial work of establishing the MacLEAP: Machine-Learning algorithm for Engulfed cArbon Particles was presented as an abstract and in details as an ePoster at the Society of Toxicology 61st Annual Meeting in San Diego 2022. The ePoster is attached as a supplementary material for this article.

Funding

Supported by National Cancer Institute grant P30 CA118100 (Leng), National Institute of General Medical Sciences U54 GM104944 (Leng), National Institute of Environmental Health grant NM-INSPIRES P30 ES032755 (Yu) and UNM-METALS P42ES025589 (Yu and Lin), and National Institute on Minority Health and Health Disparities  P50MD015706 (Lin).

Author information

Author notes

  1. These authors contributed equally: Menghui Jiang, Chelin Jamie Hu.

  2. These authors jointly supervised this work: Xiaozhong Yu, Shuguang Leng.

Authors and Affiliations

  1. School of Medicine, University of New Mexico, Albuquerque, NM, USA

    Menghui Jiang, Cassie L. Rowe, Huining Kang, Jialiang Wang, Akshay Sood, Yan Guo, Yiliang Zhu & Shuguang Leng

  2. College of Nursing, University of New Mexico College of Nursing, Albuquerque, NM, USA

    Chelin Jamie Hu & Xiaozhong Yu

  3. University of New Mexico Comprehensive Cancer Center, Albuquerque, NM, USA

    Huining Kang, Yan Guo, Steven A. Belinsky & Shuguang Leng

  4. Department of Geography & Environmental Studies, University of New Mexico, Albuquerque, NM, USA

    Xi Gong & Yan Lin

  5. Lung Cancer Program, Lovelace Biomedical Research Institute, Albuquerque, NM, USA

    Christopher P. Dagucon, Steven A. Belinsky & Shuguang Leng

  6. Miners Colfax Medical Center, Raton, NM, USA

    Akshay Sood

  7. Center for Environmental Medicine Asthma and Lung Biology, School of Medicine, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA

    Neil E. Alexis

  8. Keck School of Medicine, University of Southern California, Los Angeles, CA, USA

    Frank D. Gilliland

Authors
  1. Menghui Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chelin Jamie Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Cassie L. Rowe
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Huining Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xi Gong
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Christopher P. Dagucon
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jialiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Yan Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Akshay Sood
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Yan Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yiliang Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Neil E. Alexis
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Frank D. Gilliland
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Steven A. Belinsky
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Xiaozhong Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Shuguang Leng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

XY and SL conceived of and designed the study; CJH, CLR, CPD, and JW performed the data collection and management; CJH, HK, and SL conducted data analyses and tabulated the results; CJH, HK, and SL interpreted the results and drafted the manuscript; and MJ, XG, YL, AS, YG, YZ, NEL, FDG, SAB, XY and SL critically edited the manuscript. All authors have read the manuscript and approved its submission.

Corresponding authors

Correspondence to Xiaozhong Yu or Shuguang Leng.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval and consent to participate

This study (1054101) was approved by the Western Institutional Review Board and all participants signed consent forms.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiang, M., Hu, C.J., Rowe, C.L. et al. Application of artificial intelligence in quantifying lung deposition dose of black carbon in people with exposure to ambient combustion particles. J Expo Sci Environ Epidemiol (2023). https://doi.org/10.1038/s41370-023-00607-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41370-023-00607-0

Keywords

Search

Advanced search

Quick links