SpringerLink
Log in

A deep learning method for the automated assessment of paradoxical pulsation after myocardial infarction using multicenter cardiac MRI data

  • Cardiac
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objective

The current study aimed to explore a deep convolutional neural network (DCNN) model that integrates multidimensional CMR data to accurately identify LV paradoxical pulsation after reperfusion by primary percutaneous coronary intervention with isolated anterior infarction.

Methods

A total of 401 participants (311 patients and 90 age-matched volunteers) were recruited for this prospective study. The two-dimensional UNet segmentation model of the LV and classification model for identifying paradoxical pulsation were established using the DCNN model. Features of 2- and 3-chamber images were extracted with 2-dimensional (2D) and 3D ResNets with masks generated by a segmentation model. Next, the accuracy of the segmentation model was evaluated using the Dice score and classification model by receiver operating characteristic (ROC) curve and confusion matrix. The areas under the ROC curve (AUCs) of the physicians in training and DCNN models were compared using the DeLong method.

Results

The DCNN model showed that the AUCs for the detection of paradoxical pulsation were 0.97, 0.91, and 0.83 in the training, internal, and external testing cohorts, respectively (p < 0.001). The 2.5-dimensional model established using the end-systolic and end-diastolic images combined with 2-chamber and 3-chamber images was more efficient than the 3D model. The discrimination performance of the DCNN model was better than that of physicians in training (p < 0.05).

Conclusions

Compared to the model trained by 2-chamber or 3-chamber images alone or 3D multiview, our 2.5D multiview model can combine the information of 2-chamber and 3-chamber more efficiently and obtain the highest diagnostic sensitivity.

Clinical relevance statement

A deep convolutional neural network model that integrates 2-chamber and 3-chamber CMR images can identify LV paradoxical pulsation which correlates with LV thrombosis, heart failure, ventricular tachycardia after reperfusion by primary percutaneous coronary intervention with isolated anterior infarction.

Key Points

• The epicardial segmentation model was established using the 2D UNet based on end-diastole 2- and 3-chamber cine images.

• The DCNN model proposed in this study had better performance for discriminating LV paradoxical pulsation accurately and objectively using CMR cine images after anterior AMI compared to the diagnosis of physicians in training.

• The 2.5-dimensional multiview model combined the information of 2- and 3-chamber efficiently and obtained the highest diagnostic sensitivity.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Germany)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Abbreviations

2D UNet:

Two-dimensional UNet

AMI:

Acute myocardial infarction

BNPmax :

Peak brain natriuretic peptide

CK-MBmax :

Peak creatinine kinase-MB

CMR:

Cardiac magnetic resonance

CRPmax :

Peak C-creative protein

cTnImax :

Peak troponin I

DCNN:

Deep convolutional neural network

HF:

Heart failure

IMH:

Intramyocardial hemorrhage

LAD:

Left anterior descending

LGE:

Late Gadolinium enhancement

LVEF:

Left ventricular ejection fraction

LVT:

Left ventricular thrombosis

MVO:

Microvascular obstruction

NT-proBNP:

N-terminal pro-brain natriuretic peptide

SSFP:

Steady-state free-precession

T2WI-STIR:

T2-weighted short-tau triple inversion recovery

References

  1. Kidambi A, Motwani M, Uddin A et al (2017) Myocardial extracellular volume estimation by CMR predicts functional recovery following acute MI. JACC Cardiovasc Imaging 10:989–999

    Article  PubMed  PubMed Central  Google Scholar 

  2. D’Elia N, D’Hooge J, Marwick TH (2015) Association between myocardial mechanics and ischemic LV remodeling. JACC Cardiovasc Imaging 8:1430–1443

    Article  PubMed  Google Scholar 

  3. Cabin HS, Roberts WC (1980) Left ventricular aneurysm, intraaneurysmal thrombus and systemic embolus in coronary heart disease. Chest 77:586–590

    Article  CAS  PubMed  Google Scholar 

  4. Konen E, Merchant N, Gutierrez C et al (2005) True versus false left ventricular aneurysm: differentiation with MR imaging–initial experience. Radiology 236:65–70

    Article  PubMed  Google Scholar 

  5. Meizlish J, Berger H, Plankey M, Errico D, Levy W, Zaret B (1984) Functional left ventricular aneurysm formation after acute anterior transmural myocardial infarction. Incidence, natural history, and prognostic implications. N Engl J Med 311:1001–1006

    Article  CAS  PubMed  Google Scholar 

  6. Shen W, Tribouilloy C, Mirode A, Dufossé H, Lesbre J (1992) Left ventricular aneurysm and prognosis in patients with first acute transmural anterior myocardial infarction and isolated left anterior descending artery disease. Eur Heart J 13:39–44

    Article  CAS  PubMed  Google Scholar 

  7. Heatlie GJ, Mohiaddin R (2005) Left ventricular aneurysm: comprehensive assessment of morphology, structure and thrombus using cardiovascular magnetic resonance. Clin Radiol 60:687–692

    Article  CAS  PubMed  Google Scholar 

  8. Lam C, Gale H, Drake E (1964) Surgical treatment of left ventricular aneurysms. JAMA 187:1-3

  9. Matsumoto M, Watanabe F, Goto A et al (1985) Left ventricular aneurysm and the prediction of left ventricular enlargement studied by two-dimensional echocardiography: quantitative assessment of aneurysm size in relation to clinical course. Circulation 72:280–286

    Article  CAS  PubMed  Google Scholar 

  10. Zhou H, Li L, Liu Z et al (2021) Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images. Eur Radiol 31:3931–3940

    Article  PubMed  Google Scholar 

  11. Montalt-Tordera J, Quail M, Steeden JA, Muthurangu V (2021) Reducing contrast agent dose in cardiovascular MR angiography with deep learning. J Magn Reson Imaging 54:795–805

    Article  PubMed  PubMed Central  Google Scholar 

  12. Hamilton JI, Currey D, Rajagopalan S, Seiberlich N (2021) Deep learning reconstruction for cardiac magnetic resonance fingerprinting T1 and T2 map**. Magn Reson Med 85:2127–2135

    Article  PubMed  Google Scholar 

  13. Ghadimi S, Auger DA, Feng X et al (2021) Fully-automated global and segmental strain analysis of DENSE cardiovascular magnetic resonance using deep learning for segmentation and phase unwrap**. J Cardiovasc Magn Reson 23:20

    Article  PubMed  PubMed Central  Google Scholar 

  14. Duan J, Bello G, Schlemper J et al (2019) Automatic 3D bi-ventricular segmentation of cardiac images by a shape-refined multi-task deep learning approach. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2019.2894322

    Article  PubMed  PubMed Central  Google Scholar 

  15. Litjens G, Ciompi F, Wolterink JM et al (2019) State-of-the-art deep learning in cardiovascular image analysis. JACC Cardiovasc Imaging 12:1549–1565

    Article  PubMed  Google Scholar 

  16. Chen C, Qin C, Qiu H et al (2020) Deep learning for cardiac image segmentation: a review. Front Cardiovasc Med 7:25

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Martini N, Aimo A, Barison A et al (2020) Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance. J Cardiovasc Magn Reson 22:84

    Article  PubMed  PubMed Central  Google Scholar 

  18. Goldfarb JW, Craft J, Cao JJ (2019) Water-fat separation and parameter map** in cardiac MRI via deep learning with a convolutional neural network. J Magn Reson Imaging. https://doi.org/10.1002/jmri.26658

    Article  PubMed  Google Scholar 

  19. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444

    Article  CAS  PubMed  Google Scholar 

  20. Thygesen K, Alpert JS, Jaffe AS et al (2018) Fourth universal definition of myocardial infarction (2018). J Am Coll Cardiol 72:2231–2264

    Article  PubMed  Google Scholar 

  21. Douglas PZ, Peter L, Robert OB, Douglas LM, Gordon FT, Eugene B (2018) Braunwald’s heart disease: a textbook of cardiovascular medicine, 11th Edition. Elsevier, Canada. BMH Med J:3067–3069

  22. Joyce E, Hoogslag GE, Leong DP et al (2014) Association between left ventricular global longitudinal strain and adverse left ventricular dilatation after ST-segment-elevation myocardial infarction. Circ Cardiovasc Imaging 7:74–81

    Article  PubMed  Google Scholar 

  23. Geras KJ, Wolfson S, Shen Y et al (2017) High-resolution breast cancer screening with multiview deep convolutional neural networks. ar**v preprint ar**v:1703.07047. https://arxiv.org/abs/1703.07047. Accessed 19 June 2023

  24. Juarez-Orozco LE, Martinez-Manzanera O, van der Zant FM, Knol RJJ, Knuuti J (2020) Deep learning in quantitative PET myocardial perfusion imaging: a study on cardiovascular event prediction. JACC Cardiovasc Imaging 13:180–182

    Article  PubMed  Google Scholar 

  25. Mehta RH, Harjai KJ, Cox D et al (2003) Clinical and angiographic correlates and outcomes of suboptimal coronary flow inpatients with acute myocardial infarction undergoing primary percutaneous coronary intervention. J Am Coll Cardiol 42:1739–1746

    Article  PubMed  Google Scholar 

  26. Writing Group M, Mozaffarian D, Benjamin EJ et al (2016) Heart disease and stroke statistics-2016 update: a report from the American Heart Association. Circulation 133:e38-360

    Google Scholar 

  27. Gupta KB, Ratcliffe MB, Fallert MA, Edmunds LH Jr, Bogen DK (1994) Changes in passive mechanical stiffness of myocardial tissue with aneurysm formation. Circulation 89:2315–2326

    Article  CAS  PubMed  Google Scholar 

  28. Goldberg RJ, Konstam MA (1999) Assessing the population burden from heart failure: need for sentinel population-based surveillance systems. Arch Intern Med 159:15–17

    Article  CAS  PubMed  Google Scholar 

  29. Shah AM, Solomon SD (2010) A unified view of ventricular remodelling. Eur J Heart Fail 12:779–781

    Article  PubMed  Google Scholar 

  30. Pezel T, Viallon M, Croisille P et al (2021) Imaging Interstitial fibrosis, left ventricular remodeling, and function in stage A and B heart failure. JACC Cardiovasc Imaging 14:1038–1052

    Article  PubMed  Google Scholar 

  31. Tao Q, Yan W, Wang Y et al (2019) Deep learning-based method for fully automatic quantification of left ventricle function from cine mr images: a multivendor, multicenter study. Radiology 290:81–88

    Article  PubMed  Google Scholar 

  32. Zhang N, Yang G, Gao Z et al (2019) Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac Cine MRI. Radiology 291:606–617

    Article  PubMed  Google Scholar 

  33. Kusunose K, Abe T, Haga A et al (2020) A deep learning approach for assessment of regional wall motion abnormality from echocardiographic images. JACC Cardiovasc Imaging 13:374–381

    Article  PubMed  Google Scholar 

  34. Pandey A, Kagiyama N, Yanamala N et al (2021) Deep-Learning models for the echocardiographic assessment of diastolic dysfunction. JACC Cardiovasc Imaging 14:1887–1900

    Article  PubMed  Google Scholar 

  35. Heras M, Sanz G, Betriu A, Mont L, de Flores T, Navarro-López F (1990) Does left ventricular aneurysm influence survival after acute myocardial infarction? Eur Heart J 11:441–446

  36. Gong FF, Vaitenas I, Malaisrie SC, Maganti K (2021) Mechanical complications of acute myocardial infarction: a review. JAMA Cardiol 6:341–349

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We are very grateful to the Philips Healthcare team for their support in image analysis and deep learning methods. We appreciate the support of Yan Zhou in providing a research platform for this study. We appreciate Jun Pu and Meng Jiang made a great contribution to the study, mainly including patient recruitment, baseline clinical data collection, diagnosis, and standardized treatment.

Funding

Supported by National Natural Science Foundation of China (No. 81873886, 81873887, and 82171884); National Natural Science Foundation of China Youth project (No. 82101981); Shanghai Science and Technology Innovation Action Plan, Technology Standard Project Grant numbers (No. 19DZ2203800); Shanghai Science and technology innovation action plan, technology standard project (No. 19DZ2203800); Shanghai Municipal Education Commission-Gaofeng Clinical Medicine Grant: Shanghai Jiao Tong University school of medicine Double hundred outstanding person project (No. 20191904); Shanghai Jiao Tong University Medical Engineering Cross Project (No. YG2022QN016).

Author information

Author notes

  1. Bing-Hua Chen, Chong-Wen Wu, Dong-Aolei An, ChaoLu Feng, Meng Jiang, Jun Pu, Lian-Ming Wu contributed equally to this work.

Authors and Affiliations

  1. Department of Radiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No.160 PuJian Road, Shanghai, 200127, China

    Bing-Hua Chen, Chong-Wen Wu, Dong-Aolei An, Ling-Zhan Yu, Jian-Rong Xu & Lian-Ming Wu

  2. Philips Healthcare, Shanghai, 201103, China

    Ji-Lei Zhang, Yi-Hong Zhang & Wei-Bo Chen

  3. Department of Radiology, Wayne State University, Detroit, MI, 48201, USA

    Kennedy Watson, Luke Wesemann & Jiani Hu

  4. Department of Radiololgy, Bei**g Anzhen Hospital, Capital Medical University, Bei**g, 100029, China

    Lei Zhao

  5. Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, No.195, Chuangxin Road, Hunnan District, Shenyang, 110819, Liaoning, China

    ChaoLu Feng

  6. Department of Cardiology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, No.160 PuJian Road, Shanghai, 200127, China

    Meng Jiang & Jun Pu

Authors
  1. Bing-Hua Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chong-Wen Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dong-Aolei An
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ji-Lei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yi-Hong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Ling-Zhan Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Kennedy Watson
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Luke Wesemann
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Jiani Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Wei-Bo Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Jian-Rong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Lei Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. ChaoLu Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Meng Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Jun Pu
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Lian-Ming Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to ChaoLu Feng, Meng Jiang, Jun Pu or Lian-Ming Wu.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Lian-Ming Wu.

Conflict of interest

The authors state that there neither exists a conflict of interest nor that there is financial information to disclose.

Statistics and biometry

Lian-Ming Wu kindly provided statistical advice for this manuscript.

Informed consent

Written informed consent was obtained from all participants in this study.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

Study subjects or cohorts have not been previously reported.

Methodology

• Prospective

• Observational

• Multicentre study

Additional information

Publisher's note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (PDF 899 KB)

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

Chen, BH., Wu, CW., An, DA. et al. A deep learning method for the automated assessment of paradoxical pulsation after myocardial infarction using multicenter cardiac MRI data. Eur Radiol 33, 8477–8487 (2023). https://doi.org/10.1007/s00330-023-09807-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09807-6

Keywords

Search

Navigation