Skip to main content

Advertisement

SpringerLink
Log in

Automatic quantification of myocardium and pericardial fat from coronary computed tomography angiography: a multicenter study

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To develop a deep learning–based method for simultaneous myocardium and pericardial fat quantification from coronary computed tomography angiography (CCTA) for the diagnosis and treatment of cardiovascular disease (CVD).

Methods

We retrospectively identified CCTA data obtained between May 2008 and July 2018 in a multicenter (six centers) CVD study. The proposed method was evaluated on 422 patients’ data by two studies. The first overall study involves training model on CVD patients and testing on non-CVD patients, as well as training on non-CVD patients and testing on CVD patients. The second study was performed using the leave-center-out approach. The method performance was evaluated using Dice similarity coefficient (DSC), Jaccard index (JAC), 95% Hausdorff distance (HD95), mean surface distance (MSD), residual mean square distance (RMSD), and the center of mass distance (CMD). The robustness of the proposed method was tested using the nonparametric Kruskal-Wallis test and post hoc test to assess the equality of distribution of DSC values among different tests.

Results

The automatic segmentation achieved a strong correlation with contour (ICC and R > 0.97, p value < 0.001 throughout all tests). The accuracy of the proposed method remained high through all the tests, with the median DSC higher than 0.88 for pericardial fat and 0.96 for myocardium. The proposed method also resulted in mean MSD, RMSD, HD95, and CMD of less than 1.36 mm for pericardial fat and 1.00 mm for myocardium.

Conclusions

The proposed deep learning–based segmentation method enables accurate simultaneous quantification of myocardium and pericardial fat in a multicenter study.

Key Points

• Deep learning–based myocardium and pericardial fat segmentation method tested on 422 patients’ coronary computed tomography angiography in a multicenter study.

• The proposed method provides segmentations with high volumetric accuracy (ICC and R > 0.97, p value < 0.001) and similar shape as manual annotation by experienced radiologists (median Dice similarity coefficient ≥ 0.88 for pericardial fat and 0.96 for myocardium).

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

Similar content being viewed by others

Abbreviations

3D:

Three-dimensional

CNN:

Convolutional neural network

CVD:

Cardiovascular disease

DSC:

Dice similarity coefficient

HD:

Hausdorff distance

MSD:

Mean surface distance

RMSD:

Residual mean square distance

SD:

Standard deviation

References

  1. WHO (2017) Cardiovascular diseases (CVDs). Available via https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds). Fact sheet. Accessed 17 May 2017

  2. Min JK, Leipsic J, Pencina MJ et al (2012) Diagnostic accuracy of fractional flow reserve from anatomic CT angiography. JAMA 308:1237–1245

    Article  CAS  Google Scholar 

  3. SCOT-HEART investigators (2015) CT coronary angiography in patients with suspected angina due to coronary heart disease (SCOT-HEART): an open-label, parallel-group, multicentre trial (vol 385, pg 2383, 2015). Lancet 385:2354–2354

  4. Singh G, Al’Aref SJ, Van Assen M et al (2018) Machine learning in cardiac CT: basic concepts and contemporary data. J Cardiovasc Comput Tomogr 12:192–201

    Article  Google Scholar 

  5. Kwan AC, Cater G, Vargas J, Bluemke DA (2013) Beyond coronary stenosis: coronary computed tomographic angiography for the assessment of atherosclerotic plaque burden. Curr Cardiovasc Imaging Rep 6:89–101

    Article  Google Scholar 

  6. Guaricci AI, Pontone G, Fusini L et al (2017) Additional value of inflammatory biomarkers and carotid artery disease in prediction of significant coronary artery disease as assessed by coronary computed tomography angiography. Eur Heart J Cardiovasc Imaging 18:1049–1056

    Article  Google Scholar 

  7. Investigators S-H (2018) Coronary CT angiography and 5-year risk of myocardial infarction. N Engl J Med 379:924–933

    Article  Google Scholar 

  8. Motoyama S, Sarai M, Narula J, Ozaki Y (2013) Coronary CT angiography and high-risk plaque morphology. Cardiovasc Interv Ther 28:1–8

    Article  CAS  Google Scholar 

  9. Sarin S, Wenger C, Marwaha A et al (2008) Clinical significance of epicardial fat measured using cardiac multislice computed tomography. Am J Cardiol 102:767–771

    Article  Google Scholar 

  10. Ding J, Hsu FC, Harris TB et al (2009) The association of pericardial fat with incident coronary heart disease: the Multi-Ethnic Study of Atherosclerosis (MESA). Am J Clin Nutr 90:499–504

    Article  CAS  Google Scholar 

  11. Greif M, Becker A, von Ziegler F et al (2009) Pericardial adipose tissue determined by dual source CT is a risk factor for coronary atherosclerosis. Arterioscler Thromb Vasc Biol 29:781–U369

    Article  CAS  Google Scholar 

  12. Iacobellis G, Ribaudo MC, Zappaterreno A, Iannucci CV, Leonetti F (2004) Relation between epicardial adipose tissue and left ventricular mass. Am J Cardiol 94:1084–1087

    Article  Google Scholar 

  13. Sacks HS, Fain JN (2007) Human epicardial adipose tissue: a review. Am Heart J 153:907–917

    Article  CAS  Google Scholar 

  14. Iacobellis G, Ribaudo MC, Assael F et al (2003) Echocardiographic epicardial adipose tissue is related to anthropometric and clinical parameters of metabolic syndrome: a new indicator of cardiovascular risk. J Clin Endocrinol Metab 88:5163–5168

    Article  CAS  Google Scholar 

  15. Aliyari Ghasabeh M, Te Riele A, James CA et al (2018) Epicardial fat distribution assessed with cardiac CT in arrhythmogenic right ventricular dysplasia/cardiomyopathy. Radiology 289:641–648

    Article  Google Scholar 

  16. Levy D, Garrison RJ, Savage DD, Kannel WB, Castelli WP (1990) Prognostic implications of echocardiographically determined left ventricular mass in the Framingham Heart Study. N Engl J Med 322:1561–1566

    Article  CAS  Google Scholar 

  17. Morricone L, Malavazos AE, Coman C, Donati C, Hassan T, Caviezel F (2002) Echocardiographic abnormalities in normotensive obese patients: relationship with visceral fat. Obes Res 10:489–498

    Article  Google Scholar 

  18. Erickson BJ, Korfiatis P, Akkus Z, Kline TL (2017) Machine learning for medical imaging(1). Radiographics 37:505–515

    Article  Google Scholar 

  19. Oktay O, Schlemper J, Folgoc LL et al (2018) Attention U-Net: learning where to look for the pancreas. arXiv preprint arXiv:180403999

  20. Mishra D, Chaudhury S, Sarkar M, Soin AS (2019) Ultrasound image segmentation: a deeply supervised network with attention to boundaries. IEEE Trans Biomed Eng 66:1637–1648

    Article  Google Scholar 

  21. Milletari F, Navab N, Ahmadi S (2016) V-Net: fully convolutional neural networks for volumetric medical image segmentation2016 Fourth International Conference on 3D Vision (3DV), pp 565–571

  22. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention, Pt Iii 9351:234–241

  23. Lei Y, Tian S, He X et al (2019) Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net. Med Phys 46:3194–3206

    Article  Google Scholar 

  24. Jetley S, Lord NA, Lee N, Torr PH (2018) Learn to pay attention. arXiv preprint arXiv:180402391

  25. Wolz R, Chu C, Misawa K, Fujiwara M, Mori K, Rueckert D (2013) Automated abdominal multi-organ segmentation with subject-specific atlas generation. IEEE Trans Med Imaging 32:1723–1730

    Article  Google Scholar 

  26. Dong X, Lei Y, Tian S et al (2019) Synthetic MRI-aided multi-organ segmentation on male pelvic CT using cycle consistent deep attention network. Radiother Oncol 141:192–199

    Article  Google Scholar 

  27. Schlemper J, Oktay O, Schaap M et al (2019) Attention gated networks: learning to leverage salient regions in medical images. Med Image Anal 53:197–207

    Article  Google Scholar 

  28. Wang B, Lei Y, Wang TH et al (2019) Automated prostate segmentation of volumetric CT images using 3D deeply supervised dilated FCN. Medical Imaging 2019: Image Processing 10949

  29. Altman DG, Bland JM (1983) Measurement in medicine - the analysis of method comparison studies. J R Stat Soc Ser D Stat 32:307–317

    Google Scholar 

  30. Breslow N (1970) A generalized Kruskal-Wallis test for comparing K samples subject to unequal patterns of censorship. Biometrika 57:579–594

    Article  Google Scholar 

  31. Mihl C, Loeffen D, Versteylen MO et al (2014) Automated quantification of epicardial adipose tissue (EAT) in coronary CT angiography; comparison with manual assessment and correlation with coronary artery disease. J Cardiovasc Comput Tomogr 8:215–221

    Article  Google Scholar 

  32. Commandeur F, Goeller M, Razipour A et al (2019) Fully automated ct quantification of epicardial adipose tissue by deep learning: a multicenter study. Radiology Artificial Intelligence 1:e190045

    Article  Google Scholar 

  33. Bruns S, Wolterink JM, van Hamersvelt RW, Zreik M, Leiner T, Išgum I (2019) Improving myocardium segmentation in cardiac CT angiography using spectral informationMedical Imaging 2019: Image Processing. International Society for Optics and Photonics, pp 109492 M

  34. Mortazi A, Burt J, Bagci U (2017) Multi-planar deep segmentation networks for cardiac substructures from MRI and CT International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, pp 199–206

  35. Zreik M, Leiner T, De Vos BD, van Hamersvelt RW, Viergever MA, Išgum I (2016) Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). IEEE, pp 40-43

  36. Commandeur F, Goeller M, Betancur J et al (2018) Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT. IEEE Trans Med Imaging 37:1835–1846

    Article  Google Scholar 

Download references

Funding

The authors state that this work has not received any funding.

Author information

Authors and Affiliations

  1. Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA

    Xiuxiu He, Bang Jun Guo, Yang Lei, Tonghe Wang, Walter J. Curran, Tian Liu & Xiaofeng Yang

  2. Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, Nanjing, 210002, China

    Bang Jun Guo & Long Jiang Zhang

Authors
  1. Xiuxiu He
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bang Jun Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yang Lei
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tonghe Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Walter J. Curran
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Tian Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Long Jiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Xiaofeng Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Long Jiang Zhang or Xiaofeng Yang.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Xiaofeng Yang.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors has significant statistical expertise.

Informed consent

Institutional review broad approval was obtained; informed consent was not required for this Health Insurance Portability and Accountability Act (HIPPA)-complaint retrospective analysis.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• cross-sectional study

• multicenter study

Additional information

Publisher’s note

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

Xiuxiu He and Bang Jun Guo are Co-first author

Supplementary Information

ESM 1

(DOCX 4676 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

He, X., Guo, B.J., Lei, Y. et al. Automatic quantification of myocardium and pericardial fat from coronary computed tomography angiography: a multicenter study. Eur Radiol 31, 3826–3836 (2021). https://doi.org/10.1007/s00330-020-07482-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-020-07482-5

Keywords

Search

Navigation