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).
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
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
Min JK, Leipsic J, Pencina MJ et al (2012) Diagnostic accuracy of fractional flow reserve from anatomic CT angiography. JAMA 308:1237–1245
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
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
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
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
Investigators S-H (2018) Coronary CT angiography and 5-year risk of myocardial infarction. N Engl J Med 379:924–933
Motoyama S, Sarai M, Narula J, Ozaki Y (2013) Coronary CT angiography and high-risk plaque morphology. Cardiovasc Interv Ther 28:1–8
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
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
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
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
Sacks HS, Fain JN (2007) Human epicardial adipose tissue: a review. Am Heart J 153:907–917
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
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
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
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
Erickson BJ, Korfiatis P, Akkus Z, Kline TL (2017) Machine learning for medical imaging(1). Radiographics 37:505–515
Oktay O, Schlemper J, Folgoc LL et al (2018) Attention U-Net: learning where to look for the pancreas. arXiv preprint arXiv:180403999
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
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
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
Lei Y, Tian S, He X et al (2019) Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net. Med Phys 46:3194–3206
Jetley S, Lord NA, Lee N, Torr PH (2018) Learn to pay attention. arXiv preprint arXiv:180402391
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
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
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
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
Altman DG, Bland JM (1983) Measurement in medicine - the analysis of method comparison studies. J R Stat Soc Ser D Stat 32:307–317
Breslow N (1970) A generalized Kruskal-Wallis test for comparing K samples subject to unequal patterns of censorship. Biometrika 57:579–594
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
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
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
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
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
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
Funding
The authors state that this work has not received any funding.
Author information
Authors and Affiliations
Corresponding authors
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
About this article
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
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-020-07482-5