Epicardial fat Tissue Volumetry: Comparison of Semi-Automatic Measurement and the Machine Learning Algorithm

Aim        To compare assessments of epicardial adipose tissue (EAT) volumes obtained with a semi-automatic, physician-performed analysis and an automatic analysis using a machine-learning algorithm by data of low-dose (LDCT) and standard computed tomography (CT) of chest organs.

Material and methods        This analytical, retrospective, transversal study randomly included 100 patients from a database of a united radiological informational service (URIS). The patients underwent LDCT as a part of the project “Low-dose chest computed tomography as a screening method for detection of lung cancer and other diseases of chest organs” (n=50) and chest CT according to a standard protocol (n=50) in outpatient clinics of Moscow. Each image was read by two radiologists on a Syngo. via VB20 workstation. In addition, each image was evaluated with a developed machine-learning algorithm, which provides a completely automatic measurement of EAT.

Results   Comparison of EAT volumes obtained with chest LDCT and CT showed highly consistent results both for the expert-performed semi-automatic analyses (correlation coefficient >98 %) and between the expert layout and the machine-learning algorithm (correlation coefficient >95 %). Time of performing segmentation and volumetry on one image with the machine-learning algorithm was not longer than 40 sec, which was 30 times faster than the quantitative analysis performed by an expert and potentially facilitated quantification of the EAT volume in the clinical conditions.

Conclusion            The proposed method of automatic volumetry will expedite the analysis of EAT for predicting the risk of ischemic heart disease.

1. Drapkina O.M., Korneeva O.N., Drapkina Yu.S. Epicardial fat: a striker or a spare? Rational Pharmacotherapy in Cardiology. 2013;9(3):287–91. DOI: 10.20996/1819-6446-2013-9-3-287-291

2. Iacobellis G. Local and systemic effects of the multifaceted epicardial adipose tissue depot. Nature Reviews Endocrinology. 2015;11(6):363–71. DOI: 10.1038/nrendo.2015.58

3. Karmazyn M, Purdham DM, Rajapurohitam V, Zeidan A. Signalling mechanisms underlying the metabolic and other effects of adipokines on the heart. Cardiovascular Research. 2008;79(2):279–86. DOI: 10.1093/cvr/cvn115

4. Patel VB, Shah S, Verma S, Oudit GY. Epicardial adipose tissue as a metabolic transducer: role in heart failure and coronary artery disease. Heart Failure Reviews. 2017;22(6):889–902. DOI: 10.1007/s10741-017-9644-1

5. Ding J, Hsu F-C, Harris TB, Liu Y, Kritchevsky SB, Szklo M et al. The association of pericardial fat with incident coronary heart disease: the Multi-Ethnic Study of Atherosclerosis (MESA). The American Journal of Clinical Nutrition. 2009;90(3):499–504. DOI: 10.3945/ajcn.2008.27358

6. Britton KA, Massaro JM, Murabito JM, Kreger BE, Hoffmann U, Fox CS. Body Fat Distribution, Incident Cardiovascular Disease, Cancer, and All-Cause Mortality. Journal of the American College of Cardiology. 2013;62(10):921–5. DOI: 10.1016/j.jacc.2013.06.027

7. Mahabadi AA, Berg MH, Lehmann N, Kälsch H, Bauer M, Kara K et al. Association of Epicardial Fat With Cardiovascular Risk Factors and Incident Myocardial Infarction in the General Population. Journal of the American College of Cardiology. 2013;61(13):1388–95. DOI: 10.1016/j.jacc.2012.11.062

8. Forouzandeh F, Chang SM, Muhyieddeen K, Zaid RR, Trevino AR, Xu J et al. Does Quantifying Epicardial and Intrathoracic Fat With Noncontrast Computed Tomography Improve Risk Stratification Beyond Calcium Scoring Alone? Circulation: Cardiovascular Imaging. 2013;6(1):58–66. DOI: 10.1161/CIRCIMAGING.112.976316

9. Cheng VY, Dey D, Tamarappoo B, Nakazato R, Gransar H, Miranda-Peats R et al. Pericardial Fat Burden on ECG-Gated Noncontrast CT in Asymptomatic Patients Who Subsequently Experience Adverse Cardiovascular Events. JACC: Cardiovascular Imaging. 2010;3(4):352–60. DOI: 10.1016/j.jcmg.2009.12.013

10. Kim BJ, Kang JG, Lee SH, Lee JY, Sung KC, Kim BS et al. Relationship of Echocardiographic Epicardial Fat Thickness and Epicardial Fat Volume by Computed Tomography with Coronary Artery Calcification: Data from the CAESAR Study. Archives of Medical Research. 2017;48(4):352–9. DOI: 10.1016/j.arcmed.2017.06.010

11. Flüchter S, Haghi D, Dinter D, Heberlein W, Kühl HP, Neff W et al. Volumetric Assessment of Epicardial Adipose Tissue With Cardiovascular Magnetic Resonance Imaging. Obesity. 2007;15(4):870–8. DOI: 10.1038/oby.2007.591

12. Lim C, Ahn M-I, Jung JI, Beck KS. Simple quantification of paracardial and epicardial fat dimensions at low-dose chest CT: correlation with metabolic risk factors and usefulness in predicting metabolic syndrome. Japanese Journal of Radiology. 2018;36(9):528–36. DOI: 10.1007/s11604-018-0752-1

13. Miyazawa I, Ohkubo T, Kadowaki S, Fujiyoshi A, Hisamatsu T, Kadota A et al. Change in Pericardial Fat Volume and Cardiovascular Risk Factors in a General Population of Japanese Men. Circulation Journal. 2018;82(10):2542–8. DOI: 10.1253/circj.CJ-18-0153

14. Commandeur F, Goeller M, Betancur J, Cadet S, Doris M, Chen X et al. Deep Learning for Quantification of Epicardial and Thoracic Adipose Tissue From Non-Contrast CT. IEEE Transactions on Medical Imaging. 2018;37(8):1835–46. DOI: 10.1109/TMI.2018.2804799

15. Chernina V.Yu., Morozov S.P., Nizovtsova L.A., Blokhin I.A., Sitdikov D.I., Gombolevskiy V.A. The Role of Quantitative Assessment of Visceral Adipose Tissue of the Heart as a Predictor for Cardiovascular Events. Journal of radiology and nuclear medicine. 2020;100(6):387–94. DOI: 10.20862/0042-4676-2019-100-6-387-394

16. Morozov S.P., Kuzmina E.S., Vetsheva N.N., Gombolevskiy V.A., Lantukh Z.A., Polishuk N.S. et al. Moscow Screening: Lung Cancer Screening With Low-Dose Computed Tomography. Problems of Social Hygiene Public Health and History of Medicine. 2019;27(S):630–6. DOI: 10.32687/0869-866X-2019-27-si1-630-636

17. Nikolаev А.E., Gombolevskiy V.A., Gonchаr А.P., Shаpiev А.N., Lаypаn А.Sh., Morozov S.P. Incidental findings during lung cancer screening by low-dose computed tomography. Tuberculosis and lung diseases. 2018;96(11):60–7. DOI: 10.21292/2075-1230-2018-96-11-60-67

18. Milletari F, Navab N, Ahmadi S-A. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. 2016 Fourth International Conference on 3D Vision (3DV). P. 565–571. 2016. [DOI: 10.1109/3DV.2016.79]

19. Pisov M, Goncharov M, Kurochkina N, Morozov S, Gombolevskiy V, Chernina V et al. Correction to: Incorporating Task-Specific Structural Knowledge into CNNs for Brain Midline Shift Detection. Series Title: Lecture Notes in Computer Science. [DOI: 10.1007/978-3-030-33850-3_11]. In: Interpretability of Machine Intelligence in Medical Image Computing and Multimodal Learning for Clinical Decision Support ETH Zurich, Suzuki K, Reyes M, Syeda-Mahmood T, Glocker B, Wiest R, et al., editors -Cham: Springer International Publishing;2020.

20. Commandeur F, Goeller M, Razipour A, Cadet S, Hell MM, Kwiecinski J et al. Fully Automated CT Quantification of Epicardial Adipose Tissue by Deep Learning: A Multicenter Study. Radiology: Artificial Intelligence. 2019;1(6):e190045. DOI: 10.1148/ryai.2019190045

21. Deo RC. Machine Learning in Medicine. Circulation. 2015;132(20):1920–30. DOI: 10.1161/CIRCULATIONAHA.115.001593

22. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–44. DOI: 10.1038/nature14539

23. Greenspan H, van Ginneken B, Summers RM. Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique. IEEE Transactions on Medical Imaging. 2016;35(5):1153–9. DOI: 10.1109/TMI.2016.2553401

24. Spearman JV, Renker M, Schoepf UJ, Krazinski AW, Herbert TL, De Cecco CN et al. Prognostic value of epicardial fat volume measurements by computed tomography: a systematic review of the literature. European Radiology. 2015;25(11):3372–81. DOI: 10.1007/s00330-015-3765-5

25. Kauczor H-U, Baird A-M, Blum TG, Bonomo L, Bostantzoglou C, Burghuber O et al. ESR/ERS statement paper on lung cancer screening. European Radiology. 2020;30(6):3277–94. DOI: 10.1007/s00330-020-06727-7

26. Nagayama Y, Nakamura N, Itatani R, Oda S, Kusunoki S, Takahashi H et al. Epicardial fat volume measured on nongated chest CT is a predictor of coronary artery disease. European Radiology. 2019;29(7):3638–46. DOI: 10.1007/s00330-019-06079-x