Skip to main content
SpringerLink
Log in

An Automated Heart Shunt Recognition Pipeline Using Deep Neural Networks

  • Published:
Journal of Imaging Informatics in Medicine Aims and scope Submit manuscript

Abstract

Automated recognition of heart shunts using saline contrast transthoracic echocardiography (SC-TTE) has the potential to transform clinical practice, enabling non-experts to assess heart shunt lesions. This study aims to develop a fully automated and scalable analysis pipeline for distinguishing heart shunts, utilizing a deep neural network–based framework. The pipeline consists of three steps: (1) chamber segmentation, (2) ultrasound microbubble localization, and (3) disease classification model establishment. The study’s normal control group included 91 patients with intracardiac shunts, 61 patients with extracardiac shunts, and 84 asymptomatic individuals. Participants’ SC-TTE images were segmented using the U-Net model to obtain cardiac chambers. The segmentation results were combined with ultrasound microbubble localization to generate multivariate time series data on microbubble counts in each chamber. A classification model was then trained using this data to distinguish between intracardiac and extracardiac shunts. The proposed framework accurately segmented heart chambers (dice coefficient = 0.92 ± 0.1) and localized microbubbles. The disease classification model achieved high accuracy, sensitivity, specificity, F1 score, kappa value, and AUC value for both intracardiac and extracardiac shunts. For intracardiac shunts, accuracy was 0.875 ± 0.008, sensitivity was 0.891 ± 0.002, specificity was 0.865 ± 0.012, F1 score was 0.836 ± 0.011, kappa value was 0.735 ± 0.017, and AUC value was 0.942 ± 0.014. For extracardiac shunts, accuracy was 0.902 ± 0.007, sensitivity was 0.763 ± 0.014, specificity was 0.966 ± 0.008, F1 score was 0.830 ± 0.012, kappa value was 0.762 ± 0.017, and AUC value was 0.916 ± 0.006. The proposed framework utilizing deep neural networks offers a fast, convenient, and accurate method for identifying intracardiac and extracardiac shunts. It aids in shunt recognition and generates valuable quantitative indices, assisting clinicians in diagnosing these conditions.

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

Similar content being viewed by others

References

  1. S. Velthuis, E. Buscarini, M. W. F. van Gent, P. Gazzaniga, G. Manfredi, C. Danesino, W. J. Schonewille, C. J. J. Westermann, R. J. Snijder, J. J. Mager, and M. C. Post. Grade of Pulmonary Right-to-Left Shunt on Contrast Echocardiography and Cerebral Complications, Chest 542–548, 2013.

  2. P. Y. Ng, A. K.-Y. Ng, B. Subramaniam, S. M. Burns, F. Herisson, F. P. Timm, C. Med, M. I. Rudolph, C. Med, F. Scheffenbichler, C. Med, S. Friedrich, C. Med, T. T. Houle, D. L. Bhatt, and M. Eikermann. Association of Preoperatively Diagnosed Patent Foramen Ovale With Perioperative Ischemic Stroke. JAMA 319(5):452–462, 2018

    Article  PubMed  PubMed Central  Google Scholar 

  3. Giblett JP, Williams LK, Kyranis S, Shapiro LM, Calvert PA. Patent Foramen Ovale Closure: State of the Art. Interv Cardiol 15:e15, 2020

    Article  PubMed  PubMed Central  Google Scholar 

  4. Miranda B, Fonseca AC, Ferro JM. Patent foramen ovale and stroke. J Neurol 265(8):1943–1949,2018

    Article  PubMed  Google Scholar 

  5. J.-L. Mas, L. Derex, P. Guérin, B. Guillon, G. Habib, J.-M. Juliard, E. Marijon, E. Massardier, N. Meneveau, and F. Vuillier. Transcatheter closure of patent foramen ovale to prevent stroke recurrence in patients with otherwise unexplained ischaemic stroke: Expert consensus of the French Neurovascular Society and the French Society of Cardiology. Arch Cardiovasc Dis 12(8-9):532–542, 2019

    Article  Google Scholar 

  6. J.-M. Vedrinne, S. Duperret, C. Magnin, J. Motin, T. Bizollon, C. Trepo, and C. Ducerf. Comparison of transesophageal and transthoracic contrast echocardiography for detection of an intrapulmonary shunt in liver disease. Chest 111(5):1236–1240, 1997

    Article  CAS  PubMed  Google Scholar 

  7. M. J. Krowka, M. B. Fallon, S. M. Kawut, V. Fuhrmann, J. K. Heimbach, M. A. E. Ramsay, O. Sitbon, and R. J. Sokol. International Liver Transplant Society Practice Guidelines: Diagnosis and Management of Hepatopulmonary Syndrome and Portopulmonary Hypertension. Transplantation 100(7):1440–1452, 2016

    Article  PubMed  Google Scholar 

  8. J.-L. Mas, G. Derumeaux, B. Guillon, E. Massardier, H. Hosseini, L. Mechtouff, C. Arquizan, Y. Béjot, F. Vuillier, O. Detante, C. Guidoux, S. Canaple, C. Vaduva, N. Dequatre-Ponchelle, I. Sibon, P. Garnier, A. Ferrier, S. Timsit, E. Robinet-Borgomano, D. Sablot, J.-C. Lacour, M. Zuber, P. Favrole, J.-F. Pinel, M. Apoil, P. Reiner, C. Lefebvre, P. Guérin, C. Piot, R. Rossi, J.-L. Dubois-Randé, J.-C. Eicher, N. Meneveau, J.-R. Lusson, B. Bertrand, J.-M. Schleich, F. Godart, J.-B. Thambo, L. Leborgne, P. Michel, L. Pierard, G. Turc, M. Barthelet, A. Charles-Nelson, C. Weimar, T. Moulin, J.-M. Juliard, and G. Chatellier. Patent Foramen Ovale Closure or Anticoagulation vs. Antiplatelets after Stroke. N Engl J Med 377(11):1011–1021, 2017

    Article  CAS  PubMed  Google Scholar 

  9. D. M. Kent, I. J. Dahabreh, R. Ruthazer, A. J. Furlan, M. Reisman, J. D. Carroll, J. L. Saver, R. W. Smalling, P. Jüni, H. P. Mattle, B. Meier, and D. E. Thaler. Device Closure of Patent Foramen Ovale After Stroke: Pooled Analysis of Completed Randomized Trials. J Am Coll Cardiol 67(8):907–917, 2016

    Article  PubMed  PubMed Central  Google Scholar 

  10. Gramiak R, Shah PM. Echocardiography of the aortic root. Invest Radiol 3:356–66, 1968

    Article  CAS  PubMed  Google Scholar 

  11. Gramiak R, Shah PM, Kramer DH. Ultrasound cardiography: contrast studies in anatomy and function. Radiology 92:939–48, 1969

    Article  CAS  PubMed  Google Scholar 

  12. Seward JB, Tajik AJ, Spangler JG, Ritter DG. Echocardiographic contrast studies: initial experience. Mayo Clin Proc 50:163–92, 1975

    CAS  PubMed  Google Scholar 

  13. Shub C, Tajik AJ, Seward JB, Dines DE. Detecting intrapulmonary right-to-left shunt with contrast echocardiography. Observations in a patient with diffuse pulmonary arteriovenous fistulas. Mayo Clin Proc 51(2):81–84,1976

    CAS  PubMed  Google Scholar 

  14. F. E. Silvestry, M. S. Cohen, L. B. Armsby, N. J. Burkule, C. E. Fleishman, Z. M. Hijazi, R. M. Lang, J. J. Rome, and Y. Wang. Guidelines for the Echocardiographic Assessment of Atrial Septal Defect and Patent Foramen Ovale: From the American Society of Echocardiography and Society for Cardiac Angiography and Interventions. J Am Soc Echocardiogr 28(8):910–958, 2015

    Article  PubMed  Google Scholar 

  15. Bernard S, Churchill TW, Namasivayam M, Bertrand PB. Agitated Saline Contrast Echocardiography in the Identification of Intra- and Extracardiac Shunts: Connecting the Dots. J Am Soc Echocardiogr Oct 23:S0894–7317(20)30615–5, 2020

  16. Attaran RR, Ata I, Kudithipudi V, Foster L, Sorrell VL. Protocol for optimal detection and exclusion of a patent foramen ovale using transthoracic echocardiography with agitated saline microbubbles. Echocardiography 23:616–22,2006

    Article  PubMed  Google Scholar 

  17. Woods T, Ramamurthy S. Small pulmonary arteriovenous malformations identified by saline contrast echocardiography are associated with migraine headache. American College of Chest Physicians Scientific Sessions 128;4(Suppl):288S (abstract), 2005

  18. Freeman JA, Woods TD. Use of saline contrast echo timing to distinguish intracardiac and extracardiac shunts: failure of the 3- to 5-beat rule. Echocardiography 25(10):1127–30, 2008

    Article  PubMed  Google Scholar 

  19. Rasalingam R, Novak E, Rifkin RD. Improved differential diagnosis of intracardiac and extracardiac shunts using acoustic intensity mapping of saline contrast studies. Eur Heart J Cardiovasc Imaging 21(3):307–317, 2020

    PubMed  Google Scholar 

  20. Kroon S, Van Thor MCJ, Vorselaars VMM, Hosman AE, Swaans MJ, Snijder RJ, Mager HJ, Post MC. The use of echo density to quantify pulmonary right-to-left shunt in transthoracic contrast echocardiography. Eur Heart J Cardiovasc Imaging 22(10):1190–1196, 2021

    Article  PubMed  Google Scholar 

  21. Narula S, Shameer K, Salem Omar AM, Dudley JT, Sengupta PP. Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography. J Am Coll Cardiol 68(21):2287–2295, 2016

  22. F. Laumer, D. Di Vece, V. L. Cammann, M. Würdinger, V. Petkova, M. Schönberger, A. Schönberger, J. C. Mercier, D. Niederseer, B. Seifert, M. Schwyzer, R. Burkholz, L. Corinzia, A. S. Becker, F. Scherff, S. Brouwers, A. P. Pazhenkottil, S. Dougoud, M. Messerli, F. C. Tanner, T. Fischer, V. Delgado, P. C. Schulze, C. Hauck, L. S. Maier, H. Nguyen, S. Y. Surikow, J. Horowitz, K. Liu, R. Citro, J. Bax, F. Ruschitzka, J.-R. Ghadri, J. M. Buhmann, and C. Templin. Assessment of Artificial Intelligence in Echocardiography Diagnostics in Differentiating Takotsubo Syndrome From Myocardial Infarction. JAMA Cardiol 7(5):494–503, 2022

    Article  PubMed  PubMed Central  Google Scholar 

  23. E. Zhao, Y. Zhang, C. Kang, H. Niu, J. Zhao, L. Sun, and B. Liu. Influence of the Valsalva maneuver on cardiac hemodynamics and right to left shunt in patients with patent foramen ovale . Sci Rep 7: 44280, 2017

    Article  ADS  PubMed  PubMed Central  Google Scholar 

  24. Lynch JJ, Schuchard GH, Gross CM, Wann LS. Prevalence of right-to-left atrial shunting in a healthy population: detection by Valsalva maneuver contrast echocardiography. Am J Cardiol 53(10):1478–80, 1984

    Article  CAS  PubMed  Google Scholar 

  25. Ronneberg Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. Lect Notes Comput Sci 9351:234–241, 2015

    Article  Google Scholar 

  26. S. R. Bisht, V. V. Trivedi, R. Bhardwaj, C. K. Jha, D. Ghosh and H. Shekhar. Pulsing and Detection Strategies for Contrast-Enhanced Ultrasound: A Narrative Review. IEEE O J Ultrason Ferroelectr FreqControl 3:56–69, 2023

    Article  Google Scholar 

  27. Ackermann D, Schmitz G. Detection and Tracking of Multiple Microbubbles in Ultrasound B-Mode Images. IEEE Trans Ultrason Ferroelectr Freq Control 63(1):72–82, 2016

    Article  PubMed  Google Scholar 

  28. Christensen-Jeffries K, Browning RJ, Tang MX, Dunsby C, Eckersley RJ. In vivo acoustic super-resolution and super-resolved velocity mapping using microbubbles. IEEE Trans Med Imaging 34(2):433–440, 2015

    Article  PubMed  Google Scholar 

  29. M. Siepmann, G. Schmitz, J. Bzyl, M. Palmowski, and F. Kiessling. Imaging tumor vascularity by tracing single microbubbles. Proc. IEEE Int. Ultrason. Symp. (IUS) 38:1906–1908, 2011

    Google Scholar 

  30. Heiles B, Chavignon A, Hingot V, Lopez P, Teston E, Couture O. Performance benchmarking of microbubble-localization algorithms for ultrasound localization microscopy. Nat Biomed Eng 6(5):605–616, 2022

    Article  PubMed  Google Scholar 

  31. Karim F, Majumdar S, Darabi H, Harford S. Multivariate LSTM-FCNs for time series classification. Neural Netw 116:237–245,2019

    Article  PubMed  Google Scholar 

  32. R. J. G. van Sloun, O. Solomon, M. Bruce, Z. Z. Khaing, H. Wijkstra, Y. C. Eldar, and M. Mischi. Super-Resolution Ultrasound Localization Microscopy Through Deep Learning. IEEE Trans Med Imaging 40(3):829–839, 2021

    Article  PubMed  Google Scholar 

  33. Y. Shu, C. Han, M. Lv, and X. Liu. Fast super-resolution ultrasound imaging with compressed sensing reconstruction method and single plane wave transmission. IEEE Access 6:39298–39306, 2018

    Article  Google Scholar 

  34. Couture O, Hingot V, Heiles B, Muleki-Seya P, Tanter M. Ultrasound Localization Microscopy and Super-Resolution: A State of the Art. IEEE Trans Ultrason Ferroelectr Freq Control 65(8):1304–1320, 2018

    Article  PubMed  Google Scholar 

  35. Shokoohi-Yekta, M., Wang, J., & Keogh, E. On the Non-Trivial Generalization of Dynamic Time Warping to the Multi-Dimensional Case. Proceedings of the 2015 SIAM International Conference on Data Mining 289–297, 2015

  36. Zhang, X., Gao, Y., Lin, J., & Lu, C.-T. TapNet: Multivariate Time Series Classification with Attentional Prototypical Network. Proceedings of the AAAI Conference on Artificial Intelligence 34(04), 6845–6852, 2021

    Article  Google Scholar 

  37. Leclerc, S., Smistad, E., Pedrosa, J., Ostvik, A., Cervenansky, F., Espinosa, F., Espeland, T., Berg, E. A. R., Jodoin, P. M., Grenier, T., Lartizien, C., Dhooge, J., Lovstakken, L., & Bernard. Deep Learning for Segmentation Using an Open Large-Scale Dataset in 2D Echocardiography. IEEE Trans Med Imaging 38(9), 2198–2210, 2019

  38. P. Kora, C. P. Ooi, O. Faust, U. Raghavendra, A. Gudigar, W. Y. Chan, K. Meenakshi, K. Swaraja, P. Plawiak, and U. Rajendra Acharya. Transfer learning techniques for medical image analysis: A review. Biocybern Biomed Eng 79–107, 2022

  39. Darcy AM, Louie AK, Roberts LW. Machine Learning and the Profession of Medicine. JAMA 315(6):551–552, 2016

    Article  CAS  PubMed  Google Scholar 

  40. Quer G, Arnaout R, Henne M, Arnaout R. Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review. J Am Coll Cardiol 77(3):300–313, 2021

    Article  PubMed  PubMed Central  Google Scholar 

  41. Bernard S, Churchill TW, Namasivayam M, Bertrand PB. Agitated Saline Contrast Echocardiography in the Identification of Intra- and Extracardiac Shunts: Connecting the Dots. J Am Soc Echocardiogr S0894–7317(20)30615–5, 2020

    Google Scholar 

  42. Kroon S, Van Thor MCJ, Vorselaars VMM, Hosman AE, Swaans MJ, Snijder RJ, Mager HJ, Post MC. The use of echo density to quantify pulmonary right-to-left shunt in transthoracic contrast echocardiography. Eur Heart J Cardiovasc Imaging 20;22(10):1190–1196.,2021

Download references

Acknowledgements

The author expresses gratitude to all the participants and patients who took part in this study. Additionally, special thanks are extended to the Department of Cardiovascular Ultrasound at Sichuan Provincial People’s Hospital of the University of Electronic Science and Technology of China, and the High-performance Computing Center at Southwest Petroleum University for their invaluable assistance.

Funding

The study is funded in part by a research grant from the Natural Science Foundation of Sichuan Province (2022NSFSC0833) and the Sichuan Nanchong Science and Technology Bureau (SXHZ019). The study is funded in part by a research grant from the Natural Science Foundation of Sichuan Project (2022NSFSC0605) and the Sichuan Provincial Science and Technology Plan (2023YFQ0006).

Author information

Authors and Affiliations

  1. School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu, Sichuan, China

    Weidong Wang & Bo Peng

  2. Department of Cardiovascular Ultrasound, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, Chengdu, Sichuan, China

    Hongme Zhang, Yizhen Li, Yi Wang, Qingfeng Zhang, Geqi Ding, Lixue Yin & Bo Peng

  3. Department of Health Administration and Policy, College of Public Health, George Mason University, Fairfax, USA

    Jinshan Tang

Authors
  1. Weidong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hongme Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yizhen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yi Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Qingfeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Geqi Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Lixue Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jinshan Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Bo Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors discussed the original idea. Bo Peng and Hongmei Zhang constructed the overall study design with support from Lexue Yin and Jinshan Tang. Weidong Wang performed programming. Weidong Wang, Bo Peng, and Hongmei Zhang conducted data analysis and drafted this manuscript. Hongmei Zhang, Yizhen Li, Yi Wang, Qingfeng Zhang, Geqi Ding, and Lexue Yin were responsible for data collection and clinical result interpretation. All authors read and approved the final version of the manuscript.

Corresponding authors

Correspondence to Hongme Zhang or Bo Peng.

Ethics declarations

Ethical Approval

This study has obtained approval from the Medical Ethics Committee of Sichuan Provincial People’s Hospital.

Consent to Participate

All participants in this study provided informed consent forms.

Conflict of Interest

The authors declare no competing interests.

Consent for Publication

The author confirms the publishing consent of all participants.

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

Wang, W., Zhang, H., Li, Y. et al. An Automated Heart Shunt Recognition Pipeline Using Deep Neural Networks. J Digit Imaging. Inform. med. (2024). https://doi.org/10.1007/s10278-024-01047-4

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10278-024-01047-4

Keywords

Search

Navigation