Rationale and Objectives
To compare the prediction performance of the epicardial adipose tissue (EAT) and pericoronary
adipose tissue (PCAT) radiomics models based on coronary computed tomography angiography
for major adverse cardiovascular events (MACE) within 3 years.
Materials and Methods
Our study included 288 patients (144 with MACE and 144 without MACE within 3 years)
by matching age, gender, body mass index, and medication intake. Patients were randomly
assigned either to the training (n = 201) or validation cohort (n = 87). A total of 184 radiomics features were extracted from EAT and PCAT images.
Spearman's rank correlation coefficient and the gradient boosting decision tree algorithm
were performed for feature selection. Five models were established based on PCAT or
EAT radiomics features and clinical factors, including PCAT, EAT, clinical, PCAT-clinical,
and EAT-clinical model (MPCAT, MEAT, Mclinical, MPCAT-clinical, and MEAT-clinical). Receiver operating characteristic curves, calibration curves, and the decision
curve analysis were plotted to evaluate the model performance.
Results
The MPCAT achieved an area under the curve (AUC) of 0.703 in the validation cohort, which was
better than MEAT with AUC of 0.538. The MPCAT-clinical showed better performance (AUC = 0.781) in predicting MACE than the Mclinical (AUC = 0.748) or MEAT-clinical (AUC = 0.745).
Conclusion
Our results showed that the PCAT was better than the EAT in both single modality and
combined models, and the MPCAT-clinical had the most significant clinical value in predicting the occurrence of MACE within
3 years.
Key Words
Abbreviations:
EAT (epicardial adipose tissue), PCAT (pericoronary adipose tissue), CCTA (coronary computed tomography angiography), MACE (major adverse cardiovascular events), CAD (coronary artery disease), FAI (Fat attenuation index), RCA (right coronary artery), AUC (area under the curve), ROI (region of interest), MPCAT (PCAT model), MEAT (EAT model), Mclinical (clinical model), MPCAT-clinical (PCAT-clinical model), MEAT-clinical (EAT-clinical model)To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Academic RadiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
REFERENCES
- Antiinflammatory therapy with canakinumab for atherosclerotic disease.N Engl J Med. 2017; 377: 1119-1131https://doi.org/10.1056/NEJMoa1707914
- Modulation of the interleukin-6 signalling pathway and incidence rates of atherosclerotic events and all-cause mortality: analyses from the Canakinumab Anti-Inflammatory Thrombosis Outcomes Study (CANTOS).Eur Heart J. 2018; 39: 3499-3507https://doi.org/10.1093/eurheartj/ehy310
- The risk continuum of atherosclerosis and its implications for defining chd by coronary angiography.J Am Coll Cardiol. 2016; 68: 2467-2478https://doi.org/10.1016/j.jacc.2016.08.069
- Multiple coronary lesion instability in patients with acute myocardial infarction as determined by optical coherence tomography.Am J Cardiol. 2010; 105: 318-322https://doi.org/10.1016/j.amjcard.2009.09.032
- Nonculprit plaque characteristics in patients with acute coronary syndrome caused by plaque erosion vs plaque rupture: a 3-vessel optical coherence tomography study (published correction appears in JAMA Cardiol. 2018 Mar;3(3):266).JAMA Cardiol. 2018; 3: 207-214https://doi.org/10.1001/jamacardio.2017.5234
- 18F-fluoride positron emission tomography for identification of ruptured and high-risk coronary atherosclerotic plaques: a prospective clinical trial.Lancet. 2014; 383: 705-713https://doi.org/10.1016/S0140-6736(13)61754-7
- 2019 ESC Guidelines for the diagnosis and management of chronic coronary syndromes (published correction appears in Eur Heart J. 2020 Nov 21;41(44):4242).Eur Heart J. 2020; 41: 407-477https://doi.org/10.1093/eurheartj/ehz425
- Association of epicardial fat with cardiovascular risk factors and incident myocardial infarction in the general population: the Heinz Nixdorf Recall Study.J Am Coll Cardiol. 2013; 61: 1388-1395https://doi.org/10.1016/j.jacc.2012.11.062
- Non-invasive detection of coronary inflammation using computed tomography and prediction of residual cardiovascular risk (the CRISP CT study): a post-hoc analysis of prospective outcome data.Lancet. 2018; 392: 929-939https://doi.org/10.1016/S0140-6736(18)31114-0
- Imaging of coronary inflammation for cardiovascular risk prediction.Lancet. 2018; 392: 894-896https://doi.org/10.1016/S0140-6736(18)31716-1
- Artificial intelligence in medicine: humans need not apply?.N Z Med J. 2016; 129 (Published 2016 May 6): 73-76
- A novel machine learning-derived radiotranscriptomic signature of perivascular fat improves cardiac risk prediction using coronary CT angiography.Eur Heart J. 2019; 40: 3529-3543https://doi.org/10.1093/eurheartj/ehz592
- Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study.Cardiovasc Diabetol. 2021; 20 (Published 2021 Jan 29): 27https://doi.org/10.1186/s12933-021-01220-x
- Detecting human coronary inflammation by imaging perivascular fat.Sci Transl Med. 2017; 9: eaal2658https://doi.org/10.1126/scitranslmed.aal2658
- Standardised quantification of coronary inflammation using cardiac computed tomography: the Fat Attenuation Index Score (FAI-Score).E J Prevent Cardiol. 2021; 28https://doi.org/10.1093/EURJPC/ZWAB061.451
- Relationship between changes in pericoronary adipose tissue attenuation and coronary plaque burden quantified from coronary computed tomography angiography.Eur Heart J Cardiovasc Imaging. 2019; 20: 636-643https://doi.org/10.1093/ehjci/jez013
- Association of biologic therapy with coronary inflammation in patients with psoriasis as assessed by perivascular fat attenuation index.JAMA Cardiol. 2019; 4: 885-891https://doi.org/10.1001/jamacardio.2019.2589
- Myocardial infarction associates with a distinct pericoronary adipose tissue radiomic phenotype: a prospective case-control study.JACC Cardiovasc Imaging. 2020; 13: 2371-2383https://doi.org/10.1016/j.jcmg.2020.06.033
- Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach (published correction appears in Nat Commun. 2014;5:4644.Cavalho Sara Nat Commun. 2014; 5 (Published 2014 Jun 3): 4006https://doi.org/10.1038/ncomms5006
- Radiomics: images are more than pictures, they are data.Radiology. 2016; 278: 563-577https://doi.org/10.1148/radiol.2015151169
- A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme.Sci Rep. 2017; 7 (Published 2017 Sep 4): 10353https://doi.org/10.1038/s41598-017-10649-8
- Prognostic implications of coronary CT angiography-derived quantitative markers for the prediction of major adverse cardiac events.J Cardiovasc Comput Tomogr. 2016; 10: 458-465https://doi.org/10.1016/j.jcct.2016.08.003
- Automatic quantification of epicardial adipose tissue volume.Med Phys. 2021; 48: 4279-4290https://doi.org/10.1002/mp.15012
- 3D Slicer: a platform for subject-specific image analysis, visualization, and clinical support.Springer, New York2014
- Radiomics versus visual and histogram-based assessment to identify atheromatous lesions at coronary ct angiography: an ex vivo study.Radiology. 2019; 293: 89-96https://doi.org/10.1148/radiol.2019190407
- Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach.Biometrics. 1988; 44: 837-845
- A prospective natural-history study of coronary atherosclerosis.N Engl J Med. 2011; 364: 226-235https://doi.org/10.1056/NEJMoa1002358
- C-reactive protein, inflammation and atherosclerosis: do we really understand it yet?.Eur Heart J. 2000; 21: 958-960https://doi.org/10.1053/euhj.2000.2109
- Human epicardial adipose tissue is a source of inflammatory mediators.Circulation. 2003; 108: 2460-2466https://doi.org/10.1161/01.CIR.0000099542.57313.C5
- Subepicardial adipose tissue in human coronary atherosclerosis: another neglected phenomenon.Atherosclerosis. 2001; 154: 237-238https://doi.org/10.1016/s0021-9150(00)00676-6
- Relation of systolic and diastolic epicardial adipose tissue thickness with presence and severity of coronary artery disease (The EAT CAD study).J Family Med Prim Care. 2019; 8: 1470-1475https://doi.org/10.4103/jfmpc.jfmpc_194_19
- Deep learning-based quantification of epicardial adipose tissue volume and attenuation predicts major adverse cardiovascular events in asymptomatic subjects.Circ Cardiovasc Imaging. 2020; 13e009829https://doi.org/10.1161/CIRCIMAGING.119.009829
- Pericardial fat, visceral abdominal fat, cardiovascular disease risk factors, and vascular calcification in a community-based sample: the Framingham Heart Study.Circulation. 2008; 117: 605-613https://doi.org/10.1161/CIRCULATIONAHA.107.743062
- Association of pericardial fat, intrathoracic fat, and visceral abdominal fat with cardiovascular disease burden: the Framingham Heart Study.Eur Heart J. 2009; 30: 850-856https://doi.org/10.1093/eurheartj/ehn573
- Cardiac computed tomography radiomics for the non-invasive assessment of coronary inflammation.Cells. 2021; 10 (Published 2021 Apr 12): 879https://doi.org/10.3390/cells10040879
- Prediction of acute coronary syndrome within 3 years using radiomics signature of pericoronary adipose tissue based on coronary computed tomography angiography.Eur Radiol. 2022; 32: 1256-1266https://doi.org/10.1007/s00330-021-08109-z
- What is the real cardiac anatomy?.Clin Anat. 2019; 32: 288-309https://doi.org/10.1002/ca.23340
- The ominous triad of adipose tissue dysfunction: inflammation, fibrosis, and impaired angiogenesis.J Clin Invest. 2017; 127: 74-82https://doi.org/10.1172/JCI88883
- Cardiac computed tomography radiomics for the non-invasive assessment of coronary inflammation.Cells. 2021; 10 (Published 2021 Apr 12): 879https://doi.org/10.3390/cells10040879
- Efficacy and safety of more intensive lowering of LDL cholesterol: a meta-analysis of data from 170,000 participants in 26 randomised trials.Lancet. 2010; 376: 1670-1681https://doi.org/10.1016/S0140-6736(10)61350-5
- Lipid and non-lipid cardiovascular risk factors in postmenopausal type 2 diabetic women with and without coronary heart disease.J Endocrinol Invest. 2014; 37: 261-268https://doi.org/10.1007/s40618-013-0023-z
- Diabetic dyslipidaemia: from basic research to clinical practice.Diabetologia. 2003; 46: 733-749https://doi.org/10.1007/s00125-003-1111-y
- Quantification of epicardial and peri-coronary fat using cardiac computed tomography; reproducibility and relation with obesity and metabolic syndrome in patients suspected of coronary artery disease.Atherosclerosis. 2008; 197: 896-903https://doi.org/10.1016/j.atherosclerosis.2007.08.016
Article info
Publication history
Published online: April 14, 2022
Accepted:
March 18,
2022
Received in revised form:
March 18,
2022
Received:
November 24,
2021
Identification
Copyright
© 2022 Published by Elsevier Inc. on behalf of The Association of University Radiologists.
