Skip to main content

Advertisement

SpringerLink
Log in

Artificial Intelligence in Lung Ultrasound

  • REVIEW
  • Published:
Current Pulmonology Reports Aims and scope Submit manuscript

Abstract

Purpose of Review

We summarize and review recent artificial intelligence (AI) and deep learning (DL) innovations within the field of lung point-of-care ultrasound (LUS).

Recent Findings

Many recent DL models in LUS have been developed to aid in diagnosis of COVID-19 pneumonia, pulmonary edema, pneumothorax, and pediatric pneumonia. Publicly available data sets of patients with these pathologies have been curated, annotated, and developed to train DL models to not only detect these pathologies but also quantify severity, guide users, and act as a prognostic tool to risk stratify.

Summary

The increased use of AI in LUS has the potential to enhance medical education and to expand the field of LUS into limited resource areas such as prehospital care, disaster response, and global health. Despite the diagnostic potential of DL-enhanced LUS applications, we believe the ability of human providers to synthesize information at bedside cannot be replaced by AI.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Data Availability

No data sets were generated or analyzed during the current study.

References

Papers of particular interest, published recently, have been highlighted as: • Of importance •• Of major importance

  1. Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge, MA: MIT Press; 2016.

    Google Scholar 

  2. LeCun YA, Bengio Y, Hinton GE. Deep learning. Nature. 2015;521:436–44.

    Article  ADS  CAS  PubMed  Google Scholar 

  3. Suzuki K. Overview of deep learning in medical imaging. Radiol Phys Technol. 2017;10:257–73.

    Article  PubMed  Google Scholar 

  4. Wang H, Uraco AM, Stover J, Hollis N. Novel 4W (when-where-what-what) approach of training point-of-care ultrasound (POCUS) application in resuscitation with high-fidelity simulator. Cureus. 2020;12(7). https://doi.org/10.7759/cureus.9353. Published 2020 Jul 23.

    Article  PubMed  PubMed Central  Google Scholar 

  5. Shokoohi H, LeSaux MA, Roohani YH, Liteplo A, Huang C, Blaivas M. Enhanced point-of-care ultrasound applications by integrating automated feature-learning systems using deep learning. J Ultrasound Med. 2019;38(7):1887–97. https://doi.org/10.1002/jum.14860.

    Article  PubMed  Google Scholar 

  6. Wang H, Uraco AM, Hughes J. Artificial intelligence application on point-of-care ultrasound. J Cardiothorac Vasc Anesth. 2021;35(11):3451–2. https://doi.org/10.1053/j.jvca.2021.02.064.

    Article  PubMed  Google Scholar 

  7. Lichtenstein D. Lung ultrasound in the critically ill. Ann Intensive Care. 2014;4:1.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Copetti R. Is lung ultrasound the stethoscope of the new millennium? Definitely yes Acta Med Acad. 2016;45:80–1.

    Article  PubMed  Google Scholar 

  9. Ebrahimi A, Yousefifard M, Mohammad Kazemi H, et al. Diagnostic accuracy of chest ultrasonography versus chest radiography for identification of pneumothorax: a systematic review and meta-analysis. Tanaffos. 2014;13(4):29–40.

    PubMed  PubMed Central  Google Scholar 

  10. Alrajhi K, Woo MY, Vaillancourt C. Test characteristics of ultrasonography for the detection of pneumothorax: a systematic review and meta-analysis. Chest. 2012;141(3):703–8. https://doi.org/10.1378/chest.11-0131.

    Article  PubMed  Google Scholar 

  11. Wilkerson RG, Stone MB. Sensitivity of bedside ultrasound and supine anteroposterior chest radiographs for the identification of pneumothorax after blunt trauma. Acad Emerg Med. 2010;17(1):11–7. https://doi.org/10.1111/j.1553-2712.2009.00628.x.

    Article  PubMed  Google Scholar 

  12. Grimberg A, Shigueoka DC, Atallah AN, Ajzen S, Iared W. Diagnostic accuracy of sonography for pleural effusion: systematic review. Sao Paulo Med J. 2010;128(2):90–5. https://doi.org/10.1590/s1516-31802010000200009.

    Article  PubMed  Google Scholar 

  13. Liteplo AS, Marill KA, Villen T, et al. Emergency thoracic ultrasound in the differentiation of the etiology of shortness of breath (ETUDES): sonographic B-lines and N-terminal pro-brain-type natriuretic peptide in diagnosing congestive heart failure. Acad Emerg Med. 2009;16(3):201–10. https://doi.org/10.1111/j.1553-2712.2008.00347.x.

    Article  PubMed  Google Scholar 

  14. Liteplo AS, Murray AF, Kimberly HH, Noble VE. Real-time resolution of sonographic B-lines in a patient with pulmonary edema on continuous positive airway pressure. Am J Emerg Med. 2010;28(4):541.e5-541.e5.41E8. https://doi.org/10.1016/j.ajem.2009.08.013.

    Article  PubMed  Google Scholar 

  15. Noble VE, Murray AF, Capp R, Sylvia-Reardon MH, Steele DJR, Liteplo A. Ultrasound assessment for extravascular lung water in patients undergoing hemodialysis. Time course for resolution Chest. 2009;135(6):1433–9. https://doi.org/10.1378/chest.08-1811.

    Article  PubMed  Google Scholar 

  16. Li Q, Guan X, Wu P, Wang X, Zhou L, Tong Y, Ren R, Leung KSM, Lau EHY, Wong JY, et al. Early transmission dynamics in Wuhan, China, of novel coronavirus–infected pneumonia. N Engl J Med. 2020;382:1199–207.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Sultan LR, Sehgal CM. A review of early experience in lung ultrasound (LUS) in the diagnosis and management of COVID-19. Ultrasound Med Biol. 2020;46:2530–45.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Heyne TF, Negishi K, Choi DS, Al Saud AA, Marinacci LX, Smithedajkul PY, Devaraj LR, Little BP, Mendoza DP, Flores EJ, Petranovic M, Toal SP, Shokoohi H, Liteplo AS, Geisler BP. Handheld lung ultrasound to detect COVID-19 pneumonia in inpatients: a prospective cohort study. POCUS J. 2023;8(2):175–83. https://doi.org/10.24908/pocus.v8i2.16484. PMID: 38099168; PMCID: PMC10721309.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Wang J, Yang X, Zhou B, et al. Review of machine learning in lung ultrasound in COVID-19 pandemic. J Imaging. 2022;8(3):65. https://doi.org/10.3390/jimaging8030065. Published 2022 Mar 5.

    Article  PubMed  PubMed Central  Google Scholar 

  20. Duggan NM, Liteplo AS, Shokoohi H, Goldsmith AJ. Using lung point-of-care ultrasound in suspected COVID-19: case series and proposed triage algorithm. Clin Pract Cases Emerg Med. 2020;4(3):289–94. https://doi.org/10.5811/cpcem.2020.7.47912. PMID: 32926669; PMCID: PMC7434229.

    Article  PubMed  PubMed Central  Google Scholar 

  21. ACR, “ACR recommendations for the use of chest radiography and computed tomography (CT) for suspected COVID-19 infection,” 2024. https://www.acr.org/Advocacy-and-Economics.

  22. Lomoro P, Verde F, Zerboni F, Simonetti I, Borghi C, Fachinetti C, Natalizi A, Martegani A. COVID-19 pneumonia manifestations at the admission on chest ultrasound, radiographs, and CT: single-center study and comprehensive radiologic literature review. Eur J Radiol Open. 2020;7: 100231.

    Article  PubMed  PubMed Central  Google Scholar 

  23. van Sloun RJG, Demi L. Localizing B-lines in lung ultrasonography by weakly supervised deep learning, in-vivo results. IEEE J Biomed Health Inform. 2020;24:957–64.

    Article  PubMed  Google Scholar 

  24. Chardoli M, Sabbaghan Kermani S, Abdollahzade Manqoutaei S, Loesche MA, Duggan NM, Schulwolf S, Tofighi R, Yadegari S, Shokoohi H. Lung ultrasound in predicting COVID-19 clinical outcomes: a prospective observational study. J Am Coll Emerg Physicians Open. 2021;2(6): e12575. https://doi.org/10.1002/emp2.12575. PMID: 34755148.

    Article  PubMed  PubMed Central  Google Scholar 

  25. Arntfield R, VanBerlo B, Alaifan T, et al. Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study. BMJ Open. 2021;11(3):e045120. Published 2021 Mar 5. https://doi.org/10.1136/bmjopen-2020-045120.

  26. • Born J, Wiedemann N, Cossio M, et al. Accelerating detection of lung pathologies with explainable ultrasound image analysis. Appl Sci. 2021;11(2):672. This was one of the first publicly available LUS data set comprising clips of patients with COVID-19, bacterial pneumonia, and non-COVID-19 viral pneumonia.

    Article  CAS  Google Scholar 

  27. Zoph B, Vasudevan V, Shlens J, Le QV. “Learning transferable architectures for scalable image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8697–8710, 2018.

  28. Zhou Z, Sodha V, Siddiquee MM, et al. “Models genesis: generic autodidactic models for 3D medical image analysis,” in International Conference on Medical Image Computing and Computer Assisted Intervention, pp. 384–393, Springer, 2019.

  29. Awasthi N, Dayal A, Cenkeramaddi LR, Yalavarthy PK. Mini-COVIDNet: efficient lightweight deep neural network for ultrasound based point-of-care detection of COVID-19. IEEE Trans Ultrason Ferroelectr Freq Control. 2021;68(6):2023–37. https://doi.org/10.1109/TUFFC.2021.3068190.

    Article  PubMed  Google Scholar 

  30. Roy S, Menapace W, Oei S, et al. Deep learning for classification and localization of COVID-19 markers in point of care lung ultrasound. IEEE Trans Med Imaging. 2020;39(8):2676–87.

    Article  PubMed  Google Scholar 

  31. Hu Z, Liu Z, Dong Y, et al. Evaluation of lung involvement in COVID-19 pneumonia based on ultrasound images. Biomed Eng Online. 2021;20(1):1–15.

    Article  Google Scholar 

  32. •• Born J, Brändle G, Cossio M, et al. “POCOVID-Net: automatic detection of COVID-19 from a new lung ultrasound imaging dataset (POCUS),” 2020. https://arxiv.org/abs/2004.12084. Describes an open-access web service called POCOVIDScreen which deploys an accessible predictive DL model allowing both rapid screening of new data or baseline comparison to a new DL architecture.

  33. Horry MJ, Chakraborty S, Paul M, et al. COVID-19 detection through transfer learning using multimodal imaging data. IEEE Access. 2020;8:149808–24.

    Article  PubMed  Google Scholar 

  34. Kuroda Y, Kaneko T, Yoshikawa H, et al. Artificial intelligence-based point-of-care lung ultrasound for screening COVID-19 pneumoniae: comparison with CT scans. PLoS One. 2023;18(3):e0281127. https://doi.org/10.1371/journal.pone.0281127. Published 2023 Mar 16.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Short J, Acebes C, Rodriguez-de-Lema G, et al. Visual versus automatic ultrasound scoring of lung B-lines: reliability and consistency between systems. Med Ultrason. 2019;21(1):45–9. https://doi.org/10.11152/mu-1885.

    Article  PubMed  Google Scholar 

  36. Baloescu C, Toporek G, Kim S, et al. Automated lung ultrasound B-line assessment using a deep learning algorithm. IEEE Trans Ultrason Ferroelectr Freq Control. 2020;67(11):2312–20. https://doi.org/10.1109/TUFFC.2020.3002249.

    Article  PubMed  Google Scholar 

  37. • Gottlieb M, Patel D, Viars M, Tsintolas J, Peksa GD, Bailitz J. Comparison of artificial intelligence versus real-time physician assessment of pulmonary edema with lung ultrasound. Am J Emerg Med. 2023;70:109–12. https://doi.org/10.1016/j.ajem.2023.05.029. Demonstrated both physicians and AI software are highly sensitive for B-line detection though physicians are more specific, suggesting the greatest utility of AI for the assessment of B-lines may be for ruling out presence of pulmonary edema.

    Article  PubMed  Google Scholar 

  38. Lucassen RT, Jafari MH, Duggan NM, et al. Deep learning for detection and localization of B-lines in lung ultrasound. IEEE J Biomed Health Inform. 2023;27(9):4352–61. https://doi.org/10.1109/JBHI.2023.3282596.

    Article  PubMed  Google Scholar 

  39. •• Goldsmith AJ, Jin M, Lucassen R, et al. Comparison of pulmonary congestion severity using artificial intelligence-assisted scoring versus clinical experts: a secondary analysis of BLUSHED-AHF. Eur J Heart Fail. 2023;25(7):1166–9. https://doi.org/10.1002/ejhf.2881. Demonstrated the ability of an AI-automated LUS congestion score to correlate well with interpretations of B-line quantification by human experts, suggesting that AI could be used as a prognostic tool to risk stratify heart failure patients and guide therapy.

    Article  PubMed  Google Scholar 

  40. Galvagno SM Jr, Nahmias JT, Young DA. Advanced Trauma Life Support® update 2019: management and applications for adults and special populations. Anesthesiol Clin. 2019;37(1):13–32. https://doi.org/10.1016/j.anclin.2018.09.009.

    Article  PubMed  Google Scholar 

  41. Lichtenstein DA, Menu Y. A bedside ultrasound sign ruling out pneumothorax in the critically ill. Lung sliding Chest. 1995;108(5):1345–8. https://doi.org/10.1378/chest.108.5.1345.

    Article  CAS  PubMed  Google Scholar 

  42. Mercer CB, Ball M, Cash RE, Rivard MK, Chrzan K, Panchal AR. Ultrasound use in the prehospital setting for trauma: a systematic review. Prehosp Emerg Care. 2021;25(4):566–82.

    Article  PubMed  Google Scholar 

  43. Savell SC, Baldwin DS, Blessing A, Medelllin KL, Savell CB, Maddry JK. Military use of point of care ultrasound (POCUS). J SpecOperMed. 2021;21(2):35–42.

    Google Scholar 

  44. Mehanian C, Kulhare S, Millin R, Zheng X, Gregory C, Zhu M, Xie H, Jones J, Lazar J, Halse A, et al., Deep learning-based pneumothorax detection in ultrasound videos, in: Smart ultrasound imaging and perinatal, preterm and paediatric image analysis, Springer, 2019, pp. 74–82.

  45. Jaščur M, Bundzel M, Malík M, Dzian A, Ferenčík N, Babič F. Detecting the absence of lung sliding in lung ultrasounds using deep learning. Appl Sci. 2021;11(15):6976. https://doi.org/10.3390/app11156976.

    Article  CAS  Google Scholar 

  46. Montgomery S, Li F, Funk C, et al. Detection of pneumothorax on ultrasound using artificial intelligence. J Trauma Acute Care Surg. 2023;94(3):379–84. https://doi.org/10.1097/TA.0000000000003845.

    Article  PubMed  Google Scholar 

  47. • Boice EN, Hernandez Torres SI, Knowlton ZJ, et al. Training ultrasound image classification deep-learning algorithms for pneumothorax detection using a synthetic tissue phantom apparatus. J Imaging. 2022;8(9):249. https://doi.org/10.3390/jimaging8090249. Published 2022 Sep 11. Highlight the utility of an easy-to-produce, simple-to-modify synthetic tissue phantom in developing virtually limitless image collection to aid in training future AI applications.

    Article  PubMed  PubMed Central  Google Scholar 

  48. Van Berlo B, Wu D, Li B, et al. Accurate assessment of the lung sliding artefact on lung ultrasonography using a deep learning approach. Comput Biol Med. 2022;148:105953.

    Article  Google Scholar 

  49. • Kim K, Macruz F, Wu D, Bridge C, McKinney S, Al Saud AA, Sharaf E, Pely A, Danset P, Duffy T, Dhatt D, Buch V, Liteplo A, Li Q. Point-of-care AI-assisted stepwise ultrasound pneumothorax diagnosis. Phys Med Biol. 2023. https://doi.org/10.1088/1361-6560/acfb70. PMID: 37726013. Highlights the potential of AI not only to diagnose pneumothorax but also to guide providers in the LUS process.

    Article  PubMed  PubMed Central  Google Scholar 

  50. Orso D, Ban A, Guglielmo N. Lung ultrasound in diagnosing pneumonia in childhood: a systematic review and meta-analysis. J Ultrasound. 2018;21(3):183–95. https://doi.org/10.1007/s40477-018-0306-5.

    Article  PubMed  PubMed Central  Google Scholar 

  51. Kharasch S, Duggan NM, Cohen AR, Shokoohi H. Lung ultrasound in children with respiratory tract infections: viral, bacterial or COVID-19? A narrative review. Open Access Emerg Med. 2020;14(12):275–85. https://doi.org/10.2147/OAEM.S238702. PMID: 33116963; PMCID: PMC7569078.

    Article  Google Scholar 

  52. Doniger. Pediatric emergency critical care and ultrasound. New York, NY: Cambridge University Press; 2013.

  53. • Nti B, Lehmann AS, Haddad A, Kennedy SK, Russell FM. Artificial intelligence-augmented pediatric lung POCUS: a pilot study of novice learners. J Ultrasound Med. 2022;41(12):2965–72. https://doi.org/10.1002/jum.15992. Introduced a novel concept using AI-enhanced pleural sweep to generate complete panoramic LUS views of pediatric lungs then demonstrated its accuracy among novice providers in identifying pneumonia.

    Article  PubMed  PubMed Central  Google Scholar 

  54. Correa M, Zimic M, Barrientos F, et al. Automatic classification of pediatric pneumonia based on lung ultrasound pattern recognition. PLoS One. 2018;13(12):e0206410. https://doi.org/10.1371/journal.pone.0206410. Published 2018 Dec 5.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  55. Wu Y, Zhao S, Yang X, et al. Ultrasound lung image under artificial intelligence algorithm in diagnosis of neonatal respiratory distress syndrome. Comput Math Methods Med. 2022;2022:1817341. https://doi.org/10.1155/2022/1817341. Published 2022 Mar 27. [retracted in: Comput Math Methods Med. 2023 Dec 13;2023:9853713].

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Emergency Medicine, Massachusetts General Hospital, 55 Fruit Street, Boston, MA, 02114, USA

    David Chu, Andrew Liteplo, Ainsley B. Hutchinson & Hamid Shokoohi

  2. Department of Emergency Medicine, Brigham and Women’s Hospital, 75 Francis Street, Boston, MA, 02115, USA

    David Chu & Nicole Duggan

Authors
  1. David Chu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrew Liteplo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nicole Duggan
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ainsley B. Hutchinson
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hamid Shokoohi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

D.C. performed a literature search, wrote the main manuscript text, and completed the requested revisions. A.L., N.D., A.H., and H.S. provided substantial revisions to the manuscript. All authors reviewed the manuscript.

Corresponding author

Correspondence to David Chu.

Ethics declarations

Conflict of Interest

D Chu declares that he has no conflicts of interest. A Liteplo declares that he has no conflicts of interest. A Hutchinson declares that she has no conflicts of interest. N Duggan declares that she has no conflicts of interest. H Shokoohi declares that he has no conflicts of interest.

Human and Animal Rights and Informed Consent

This article does not contain any studies with human or animal subjects performed by any of the authors.

Additional information

Publisher's Note

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

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

Chu, D., Liteplo, A., Duggan, N. et al. Artificial Intelligence in Lung Ultrasound. Curr Pulmonol Rep (2024). https://doi.org/10.1007/s13665-024-00344-1

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s13665-024-00344-1

Keywords

Search

Navigation