Skip to main content

Advertisement

SpringerLink
Log in

Using Deep Learning to Detect the Presence and Location of Hemoperitoneum on the Focused Assessment with Sonography in Trauma (FAST) Examination in Adults

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

Abdominal ultrasonography has become an integral component of the evaluation of trauma patients. Internal hemorrhage can be rapidly diagnosed by finding free fluid with point-of-care ultrasound (POCUS) and expedite decisions to perform lifesaving interventions. However, the widespread clinical application of ultrasound is limited by the expertise required for image interpretation. This study aimed to develop a deep learning algorithm to identify the presence and location of hemoperitoneum on POCUS to assist novice clinicians in accurate interpretation of the Focused Assessment with Sonography in Trauma (FAST) exam. We analyzed right upper quadrant (RUQ) FAST exams obtained from 94 adult patients (44 confirmed hemoperitoneum) using the YoloV3 object detection algorithm. Exams were partitioned via fivefold stratified sampling for training, validation, and hold-out testing. We assessed each exam image-by-image using YoloV3 and determined hemoperitoneum presence for the exam using the detection with highest confidence score. We determined the detection threshold as the score that maximizes the geometric mean of sensitivity and specificity over the validation set. The algorithm had 95% sensitivity, 94% specificity, 95% accuracy, and 97% AUC over the test set, significantly outperforming three recent methods. The algorithm also exhibited strength in localization, while the detected box sizes varied with a 56% IOU averaged over positive cases. Image processing demonstrated only 57-ms latency, which is adequate for real-time use at the bedside. These results suggest that a deep learning algorithm can rapidly and accurately identify the presence and location of free fluid in the RUQ of the FAST exam in adult patients with hemoperitoneum.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data Availability

The ultrasound images and datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

References

  1. Savell SC, Baldwin DS, Blessing A, Medelllin KL, Savell CB, Maddry JK. Military use of point of care ultrasound (POCUS). J Spec Oper Med. 2021 Summer;21(2):35–42. https://doi.org/10.55460/AJTO-LW17.

  2. Myers MA, Chin EJ, Billstrom AR, Cohen JL, Van Arnem KA, Schauer SG. Ultrasound at the Role 1: An analysis of after-action reviews from the prehospital trauma registry. Med J (Ft Sam Houst Tex). 2021 Jul-Sep;(PB 8–21–07/08/09):20–24.

  3. Liang T, Roseman E, Gao M, Sinert R. The Utility of the Focused Assessment With Sonography in Trauma Examination in Pediatric Blunt Abdominal Trauma: A Systematic Review and Meta-Analysis. Pediatr Emerg Care. 2021 Feb 1;37(2):108-118. https://doi.org/10.1097/PEC.0000000000001755.

    Article  PubMed  Google Scholar 

  4. Fornari MJ, Lawson SL. Pediatric Blunt Abdominal Trauma and Point-of-Care Ultrasound. Pediatr Emerg Care. 2021 Dec 1;37(12):624-629. https://doi.org/10.1097/PEC.0000000000002573.

    Article  PubMed  Google Scholar 

  5. Chaijareenont C, Krutsri C, Sumpritpradit P, Singhatas P, Thampongsa T, Lertsithichai P, Choikrua P, Poprom N. FAST accuracy in major pelvic fractures for decision-making of abdominal exploration: Systematic review and meta-analysis. Ann Med Surg (Lond). 2020 Oct 24;60:175-181. https://doi.org/10.1016/j.amsu.2020.10.018.

    Article  Google Scholar 

  6. van der Weide L, Popal Z, Terra M, Schwarte LA, Ket JCF, Kooij FO, Exadaktylos AK, Zuidema WP, Giannakopoulos GF. Prehospital ultrasound in the management of trauma patients: Systematic review of the literature. Injury. 2019 Dec;50(12):2167-2175. https://doi.org/10.1016/j.injury.2019.09.034. Epub 2019 Sep 28.

    Article  PubMed  Google Scholar 

  7. Qi X, Tian J, Sun R, Zhang H, Han J, Jin H, Lu H. Focused Assessment with Sonography in Trauma for Assessment of Injury in Military Settings: A Meta-analysis. Balkan Med J. 2019 Dec 20;37(1):3-8. https://doi.org/10.4274/balkanmedj.galenos.2019.2019.8.79. Epub 2019 Oct 9.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Netherton S, Milenkovic V, Taylor M, Davis PJ. Diagnostic accuracy of eFAST in the trauma patient: a systematic review and meta-analysis. CJEM. 2019 Nov;21(6):727-738. https://doi.org/10.1017/cem.2019.381.

    Article  PubMed  Google Scholar 

  9. Stengel D, Leisterer J, Ferrada P, Ekkernkamp A, Mutze S, Hoenning A. Point-of-care ultrasonography for diagnosing thoracoabdominal injuries in patients with blunt trauma. Cochrane Database Syst Rev. 2018 Dec 12;12(12):CD012669. https://doi.org/10.1002/14651858.CD012669.pub2.

  10. Quinn AC, Sinert R. What is the utility of the Focused Assessment with Sonography in Trauma (FAST) exam in penetrating torso trauma? Injury. 2011 May;42(5):482-7. https://doi.org/10.1016/j.injury.2010.07.249.

    Article  PubMed  Google Scholar 

  11. ATLS Subcommittee; American College of Surgeons’ Committee on Trauma; International ATLS working group. Advanced trauma life support (ATLS®): the ninth edition. J Trauma Acute Care Surg. 2013 May;74(5):1363–6. https://doi.org/10.1097/TA.0b013e31828b82f5.

  12. Melniker LA, Leibner E, McKenney MG, Lopez P, Briggs WM, Mancuso CA. Randomized controlled clinical trial of point-of-care, limited ultrasonography for trauma in the emergency department: the first sonography outcomes assessment program trial. Ann Emerg Med. 2006 Sep;48(3):227-35. https://doi.org/10.1016/j.annemergmed.2006.01.008. Epub 2006 Mar 24.

    Article  PubMed  Google Scholar 

  13. Pearl WS, Todd KH. Ultrasonography for the initial evaluation of blunt abdominal trauma: A review of prospective trials. Ann Emerg Med. 1996 Mar;27(3):353-61. https://doi.org/10.1016/s0196-0644(96)70273-1.

    Article  CAS  PubMed  Google Scholar 

  14. Stowell JR, Kessler R, Lewiss RE, Barjaktarevic I, Bhattarai B, Ayutyanont N, Kendall JL. Critical care ultrasound: A national survey across specialties. J Clin Ultrasound. 2018 Mar;46(3):167-177. https://doi.org/10.1002/jcu.22559. Epub 2017 Nov 13. PMID: 29131347.

    Article  PubMed  Google Scholar 

  15. Lewiss RE, Saul T, Del Rios M. Acquiring credentials in bedside ultrasound: a cross-sectional survey. BMJ Open. 2013 Aug 30;3(8):e003502. https://doi.org/10.1136/bmjopen-2013-003502. PMID: 23996824; PMCID: PMC3758970.

  16. Ma OJ, Gaddis G. Anechoic stripe size influences accuracy of FAST examination interpretation. Acad Emerg Med. 2006 Mar;13(3):248-53. https://doi.org/10.1197/j.aem.2005.09.012. Epub 2006 Feb 22. PMID: 16495421.

    Article  PubMed  Google Scholar 

  17. Boniface KS, Shokoohi H, Smith ER, Scantlebury K. Tele-ultrasound and paramedics: real-time remote physician guidance of the Focused Assessment With Sonography for Trauma examination. Am J Emerg Med. 2011 Jun;29(5):477-81. https://doi.org/10.1016/j.ajem.2009.12.001. Epub 2010 Apr 13.

    Article  PubMed  Google Scholar 

  18. Drake AE, Hy J, MacDougall GA, Holmes B, Icken L, Schrock JW, Jones RA. Innovations with tele-ultrasound in education sonography: the use of tele-ultrasound to train novice scanners. Ultrasound J. 2021 Feb 14;13(1):6. https://doi.org/10.1186/s13089-021-00210-0.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Pokaprakarn T, Prieto JC, Price JT, et al. AI estimation of gestational age from blind ultrasound sweeps in low-resource settings. NEJM Evidence 2022 March 28;1(5). https://doi.org/10.1056/EVIDoa2100058

  20. Laumer F, Di Vece D, Cammann VL, et al. Assessment of artificial intelligence in echocardiography diagnostics in differentiating takotsubo syndrome from myocardial infarction. JAMA Cardiol. 2022 May 1;7(5):494-503. https://doi.org/10.1001/jamacardio.2022.0183.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Van Sloun RJG, Cohen R, Eldar YC., Deep learning in ultrasound Imaging. Proc IEEE 2020;108(1). https://doi.org/10.1109/JPROC.2019.2932116.

  22. Diniz PHB, Yin Y, Collins S. Deep Learning strategies for ultrasound in pregnancy. Eur Med J Reprod Health. 2020 Aug;6(1):73-80. Epub 2020 Aug 25.

    PubMed  PubMed Central  Google Scholar 

  23. Liu S, Wang Y, Yang X, et al. Deep learning in medical ultrasound analysis: a review. Engineering 2019;5(Generic):261–275. https://doi.org/10.1016/j.eng.2018.11.020.

  24. Akkus Z, Cai J, Boonrod A, et al. A Survey of deep-learning applications in ultrasound: artificial intelligence-powered ultrasound for improving clinical workflow. J Am Coll Radiol. 2019 Sep;16(9 Pt B):1318–1328. https://doi.org/10.1016/j.jacr.2019.06.004.

  25. Kornblith AE, Addo N, Dong R, et al. Development and validation of a deep learning strategy for automated view classification of pediatric focused assessment with sonography for trauma. J Ultrasound Med. 2022 Aug;41(8):1915-1924. https://doi.org/10.1002/jum.15868. Epub 2021 Nov 6.

    Article  PubMed  Google Scholar 

  26. Cheng CY, Chiu IM, Hsu MY, Pan HY, Tsai CM, Lin CR. Deep learning assisted detection of abdominal free fluid in morison’s pouch during focused assessment with sonography in Trauma. Front Med (Lausanne). 2021 Sep 23;8:707437. https://doi.org/10.3389/fmed.2021.707437.

  27. Taye M, Morrow D, Cull J, Smith DH, Hagan M. Deep Learning for FAST Quality Assessment. J Ultrasound Med. 2023 Jan;42(1):71-79. https://doi.org/10.1002/jum.16045. Epub 2022 Jun 30. PMID: 35770928

    Article  PubMed  Google Scholar 

  28. Lin Z, Li Z, Cao P, et al. Deep learning for emergency ascites diagnosis using ultrasonography images. J Appl Clin Med Phys. 2022 Jul;23(7):e13695. https://doi.org/10.1002/acm2.13695. Epub 2022 Jun 20.

  29. Redmon J, Farhadi A. Yolov3: An incremental improvement. arXiv preprint arXiv:180402767 2018.

  30. Diwan, T., Anirudh, G. and Tembhurne, J.V., 2022. Object detection using YOLO: Challenges, architectural successors, datasets and applications. Multimedia Tools and Applications, pp.1–33.

  31. Lobo V, Hunter-Behrend M, Cullnan E, et al. Caudal Edge of the Liver in the Right Upper Quadrant (RUQ) view is the most sensitive area for free fluid on the FAST exam. West J Emerg Med. 2017 Feb;18(2):270-280. https://doi.org/10.5811/westjem.2016.11.30435. Epub 2017 Jan 19.

    Article  PubMed  PubMed Central  Google Scholar 

  32. Ultrasound Guidelines: Emergency, Point-of-Care and Clinical Ultrasound Guidelines in Medicine. Ann Emerg Med. 2017 May;69(5):e27-e54. https://doi.org/10.1016/j.annemergmed.2016.08.457.

    Article  Google Scholar 

  33. Yadav, S. and Shukla, S., 2016, February. Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. In 2016 IEEE 6th International conference on advanced computing (IACC) (pp. 78–83). IEEE.

  34. Azadi, S. and Karimi-Jashni, A., 2016. Verifying the performance of artificial neural network and multiple linear regression in predicting the mean seasonal municipal solid waste generation rate: A case study of Fars province, Iran. Waste management, 48, pp.14-23.

    Article  PubMed  Google Scholar 

  35. Lu, H.J., Zou, N., Jacobs, R., Afflerbach, B., Lu, X.G. and Morgan, D., 2019. Error assessment and optimal cross-validation approaches in machine learning applied to impurity diffusion. Computational Materials Science, 169, p.109075.

    Article  Google Scholar 

  36. Sejuti, Z.A. and Islam, M.S., 2023. A hybrid CNN–KNN approach for identification of COVID-19 with 5-fold cross validation. Sensors International, 4, p.100229.

    Article  PubMed  PubMed Central  Google Scholar 

  37. Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. International conference on machine learning: PMLR; 2015. p. 448–456.

  38. Han, R., Liu, X. and Chen, T., 2022, October. Yolo-SG: Salience-Guided Detection Of Small Objects In Medical Images. In 2022 IEEE International Conference on Image Processing (ICIP) (pp. 4218–4222). IEEE.

  39. Bengio Y, Courville A, Vincent P. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence 2013;35(8):1798-1828. https://doi.org/10.1109/TPAMI.2013.50.

    Article  PubMed  Google Scholar 

  40. Lin T-Y, Maire M, Belongie S, et al. Microsoft coco: Common objects in context. European conference on computer vision: Springer; 2014. P. 740-755.

    Google Scholar 

  41. Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980 2014.

  42. Dey P, Gopal M, Pradhan P, et al. On robustness of radial basis function network with input perturbation. Neural Comput & Applic 31, 523–537 (2019). https://doi.org/10.1007/s00521-017-3086-5.

    Article  Google Scholar 

  43. Krogh A, Hertz J. A simple weight decay can improve generalization. Advances in neural information processing systems. Proceedings of the 4th International Conference on Neural Information Processing Systems, 950–957 (1991).

  44. Fawcett T. An introduction to ROC analysis. Pattern recognition letters 2006;27(8):861-874.

    Article  Google Scholar 

  45. Redmon J, Farhadi A.YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517–6525. https://doi.org/10.1109/CVPR.2017.690.

  46. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine learning in Python. the Journal of machine Learning research 2011;12:2825–2830.

  47. Harris PA, Delacqua G, Taylor R, Pearson S, Fernandez M, Duda SN. The REDCap Mobile Application: a data collection platform for research in regions or situations with internet scarcity. JAMIA Open Jul 2021;4(3):ooab078.

  48. Wu, C.C., Cheng, C.Y., Chen, H.C., Hung, C.H., Chen, T.Y., Lin, C.H.R. and Chiu, I.M., 2022. Development and validation of an end-to-end deep learning pipeline to measure pericardial effusion in echocardiography. medRxiv, pp.2022–08.

  49. Sjogren AR, Leo MM, Feldman J, Gwin JT. Image segmentation and machine learning for detection of abdominal free fluid in focused assessment with sonography for trauma examinations: a Pilot study. J Ultrasound Med Nov 2016;35(11):2501–2509. https://doi.org/10.7863/ultra.15.11017.

  50. Jiang P, Ergu D, Liu F, Cai Y, Ma B. A review of yolo algorithm developments. Procedia Computer Science 2022;199:1066-1073.

    Article  Google Scholar 

  51. Liu M, Wang X, Zhou A, Fu X, Ma Y, Piao C. UAV-YOLO: Small object detection on unmanned aerial vehicle perspective. Sensors (Basel). 2020 Apr 15;20(8):2238. https://doi.org/10.3390/s20082238.

    Article  PubMed  PubMed Central  Google Scholar 

  52. Hou Y, Li Q, Zhang C, et al. The state-of-the-art review on applications of intrusive sensing, image processing techniques, and machine learning methods in pavement monitoring and analysis. Engineering 2021;7(6):845-856.

    Article  Google Scholar 

  53. Hosseinzadeh Kassani S, Hosseinzadeh Kassani P. A comparative study of deep learning architectures on melanoma detection. Tissue Cell. 2019 Jun;58:76-83. https://doi.org/10.1016/j.tice.2019.04.009. Epub 2019 Apr 22.

    Article  PubMed  Google Scholar 

  54. Mishra D, Chaudhury S, Sarkar M, Manohar S, Soin AS. Segmentation of vascular regions in ultrasound images: A deep learning approach. 2018 IEEE International Symposium on Circuits and Systems (ISCAS): IEEE; 2018. p. 1–5.

  55. Cheong H, Devalla SK, Pham TH, et al. Deshadowgan: a deep learning approach to remove shadows from optical coherence tomography images. Translational Vision Science & Technology 2020;9(2):23-23.

    Article  Google Scholar 

  56. Tablet-based Ultrasound Trial Shows Lifesaving Potential in Emergency Services. Journal of mHealth, 2014. 1(6): p. 17.

  57. Kolbe, N., et al., Point of care ultrasound (POCUS) telemedicine project in rural Nicaragua and its impact on patient management. J Ultrasound, 2015. 18(2): p. 179-85.

    Article  PubMed  Google Scholar 

  58. Ferreira, A.C., et al., Teleultrasound: historical perspective and clinical application. Int J Telemed Appl, 2015. 2015: p. 306259.

    PubMed  PubMed Central  Google Scholar 

  59. Levine, A.R., et al., Tele-intensivists can instruct non-physicians to acquire high-quality ultrasound images. J Crit Care, 2015.

  60. Georgescu, M., et al., Remote Sonography in Routine Clinical Practice Between Two Isolated Medical Centers and the University Hospital Using a Robotic Arm: A 1-Year Study. Telemed J E Health, 2015.

  61. Heegaard, W., et al., Prehospital ultrasound by paramedics: results of field trial. Acad Emerg Med, 2010. 17(6): p. 624-30.

    Article  PubMed  Google Scholar 

  62. Shwe S, Witchey L, Lahham S, Kunstadt E, Shniter I, Fox JC. Retrospective analysis of eFAST ultrasounds performed on trauma activations at an academic level-1 trauma center. World J Emerg Med. 2020;11(1):12-17. https://doi.org/10.5847/wjem.j.1920-8642.2020.01.002.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

We thank the Department of Surgery Section of Trauma and Acute Care Surgery and Ms. Heidi A. Wing, Trauma Registry Supervisor at Boston Medical Center, as well as research assistants Samantha Roberts, MPH, Tyler Pina, Shinelle Kirk, and Haley Connelly and all the research staff, who contributed countless hours to this study. Ms. Ijeoma Okafur MPH assisted in the data analysis.

Funding

Research reported in this publication was supported by the National Institute of General Medical Sciences of the National Institutes of Health under Award Number R44GM123821. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. The National Center for Advancing Translational Sciences, National Institutes of Health, through BU-CTSI Grant Number 1UL1TR001430, provided support for this study through the REDCap electronic data capture tools hosted at Boston University. Dr. Feldman is supported in part by UL1TR001430.

Author information

Authors and Affiliations

  1. Boston University School of Medicine, Boston, MA, USA

    Megan M. Leo & James A. Feldman

  2. Department of Emergency Medicine, Boston Medical Center, BCD Building, 800 Harrison Ave1St Floor, Boston, MA, 02118, USA

    Megan M. Leo & James A. Feldman

  3. BioSensics, LLC, Newton, MA, USA

    Ilkay Yildiz Potter, Mohsen Zahiri & Ashkan Vaziri

  4. Division of Emergency Ultrasound, Department of Emergency Medicine, John H. Stroger Jr. Hospital of Cook County, Chicago, IL, USA

    Christine F. Jung

  5. Department of Emergency Medicine, Chicago Medical School of Rosalind, Franklin University of Medical Sciences, Chicago, IL, USA

    Christine F. Jung

  6. Department of Emergency Medicine, Rush Medical College, Chicago, IL, USA

    Christine F. Jung

Authors
  1. Megan M. Leo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ilkay Yildiz Potter
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohsen Zahiri
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ashkan Vaziri
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Christine F. Jung
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. James A. Feldman
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All of the listed authors have participated actively in the entire study project, including study design, data acquisition, analysis, and manuscript preparation. ML, AV, and JF developed the design and conduct of the study. ML, IYP, AV, MZ, JF, and CJ participated in the data analysis, interpretation, and manuscript preparation. ML, IYP, and JF drafted the original manuscript. All authors participated in and approved the final submission. ML assumes responsibility for the paper as a whole.

Corresponding author

Correspondence to Megan M. Leo.

Ethics declarations

Ethics Approval

The study was deemed exempt from review by the institutional review board of Boston Medical Center/Boston University Medical Campus.

Conflict of Interest

Dr. Megan M. Leo is a paid consultant for BioSensics, LLC, for expert opinion and product development that is not related to the content presented in this manuscript. Dr. Ilkay Yildiz Potter, Dr. Mohsen Zahiri, and Dr. Christine Jung declare that they have no financial interests. Dr. Ashkan Vaziri and Dr. James Feldman received the research grants funding this work as investigators.

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

Leo, M.M., Potter, I.Y., Zahiri, M. et al. Using Deep Learning to Detect the Presence and Location of Hemoperitoneum on the Focused Assessment with Sonography in Trauma (FAST) Examination in Adults. J Digit Imaging 36, 2035–2050 (2023). https://doi.org/10.1007/s10278-023-00845-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-023-00845-6

Keywords

Search

Navigation