5963Automated quantification of epicardial adipose tissue from non-contrast CT on multi-center and multi-vendor data using deep learning

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
F Commandeur ◽  
M Goeller ◽  
A Razipour ◽  
S Cadet ◽  
M M Hell ◽  
...  
Keyword(s):  
Adipose Tissue ◽  
Deep Learning ◽  
Epicardial Adipose Tissue ◽  
Plaque Burden ◽  
Calcium Scoring ◽  
Manual Measurement ◽  
Significant Bias ◽  
Significant Difference ◽  
Automated Quantification ◽  
Highly Correlated

Abstract Background Epicardial adipose tissue (EAT), a metabolically active visceral fat depot surrounding the coronary arteries, has been shown to promote the development of atherosclerosis in underlying coronary vasculature. Purpose We evaluate the performance of deep learning (DL), a sub-group of machine learning algorithms, for robust and fully automated quantification of EAT on multi-center cardiac CT data. Methods In this study, 850 non-contrast calcium scoring CT scans, from multiple cohorts, scanners and protocols, with manual measurements of EAT from 3 different readers were considered. The DL method was based on a convolutional neural network trained to reproduce the expert measurement. DL global performance was first assessed using all the scans, and then compared to inter-observer variability on a subset of 141 scans. Finally, automated EAT progression was compared to manual measurement using baseline and follow-up serial scans available for 70 subjects. The proposed model was validated using 10-fold cross validation. Results Automated quantification was performed in 1.57±0.49 seconds compared to 15 minutes for manual measurement. DL provided high agreement with expert manual quantification for all scans (R=0.974, p<0.001) with no significant bias (0.53 cm3, p=0.13). EAT volume was higher in patients with hypertension (+18.02 cm3, p<0.001, N=442), with diabetes (+18.33 cm3, p<0.001, N=75) and with hypercholesterolemia (+7.33 cm3, p=0.039, N=508). Manual EAT volumes measured by two experienced readers on 141 scans were highly correlated (R=0.984, p<0.001) but presented a significant difference of 4.35 cm3 (p<0.001). On these 141 scans, DL quantifications were highly correlated to both experts' measurements (R=0.973, p<0.001; R=0.979, p<0.001) with significant and non-significant bias for readers 1 and 2 (5.19 cm3, p<0.001; 0.84 cm3, p=0.26), respectively. In 70 subjects, EAT progression quantified by DL correlated strongly with EAT progression measured by the expert reader (R=0.905, p<0.001) with no significant bias (0.64 cm3, p=0.43), and was related to increased non-calcified plaque burden quantified from coronary CT angiography (5.7% vs 1.8%, p=0.026). Automated vs. manual EAT volume Conclusion Deep learning allows rapid, robust and fully automated quantification of EAT from calcium scoring CT. It performs as an expert reader and can be implemented for routine cardiovascular risk assessment. Acknowledgement/Funding 1R01HL133616/01EX1012B/Adelson Medical Research Foundation

scholarly journals Association of Epicardial Adipose Tissue with Essential Hypertension: A Meta-Analysis

2021 ◽  
Author(s):  
Xinyu Zou ◽  
Yingrui Li ◽  
Qiang She ◽  
Bin Liu
Keyword(s):  
Cardiovascular Disease ◽  
Adipose Tissue ◽  
Essential Hypertension ◽  
Odds Ratio ◽  
Observational Studies ◽  
Epicardial Adipose Tissue ◽  
Meta Analysis ◽  
Hypertensive Patients ◽  
New Information ◽  
Significant Difference

Abstract Background and aims: Increased epicardial adipose tissue (EAT) has been proposed as a risk factor for essential hypertension (EH). The aim of this study was to investigate the association of EAT with EH.Methods and results: PubMed, EMBASE, and Cochrane databases were systematically reviewed to identify relevant studies assessing the association of EAT thickness (EAT-t) and volume (EAT-v) with EH. There were 39 observational studies and 8,983 subjects included in the meta-analysis. The analysis indicated that hypertensive patients had a higher mean of EAT-t (SMD=0.64, 95% CI: 0.44-0.83, p<0.001) and EAT-v (SMD: 0.69, 95% CI:0.34-0.1.05, p<0.001) than normotensive individuals. Accordingly, we calculated pooled odds ratio (OR) and 95% confidence intervals (CI) for the association of EAT with EH, and the results showed that EAT-t (OR: 1.59, 95% CI: 1.09–2.33, P<0.001) and EAT-v (OR: 1.82, 95% CI: 1.33–2.19, P<0.001) were associated with essential hypertension. Additionally, higher mean of EAT-t (SMD=0.85, 95% CI=0.49-0.1.21, p<0.001) and EAT-v (SMD=0.83, 95% CI=0.31-1.34, p=0.002) were found in non-dipper hypertensive patients than those in dipper patients, but we didn’t find significant difference in EAT-t among patients with different grades of hypertension. We also investigated the association of EAT with complications in hypertensive patients, and the results showed that EAT was increased in patients with arteriosclerotic cardiovascular disease (ASCVD) or cardiac hypertrophy and dysfunction than those without. Conclusions: The increase in EAT was associated with the occurrence and complications of EH. The findings provide new information regarding the occurrence and complications of EH.

scholarly journals CT-derived characterization of pericoronary, paracardial and epicardial adipose tissue and its association with myocardial ischemia as assessed by adenosine stress CMR perfusion imaging

2021 ◽  
Vol 22 (Supplement_2) ◽  
Author(s):  
M Goeller ◽  
H Duncker ◽  
D Dey ◽  
M Moshage ◽  
D Bittner ◽  
...  
Keyword(s):  
Adipose Tissue ◽  
Myocardial Ischemia ◽  
Perfusion Imaging ◽  
Epicardial Adipose Tissue ◽  
Adenosine Stress ◽  
Single Centre ◽  
Ct Attenuation ◽  
Significant Difference ◽  
Single Centre Study ◽  
Stress Cmr

Abstract Funding Acknowledgements Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Kaltenbach scholarship of the german heart foundation Background  Increased attenuation of pericoronary adipose tissue (PCAT) around the right coronary artery (RCA) is a new imaging biomarker to detect coronary inflammation derived from routine coronary CT angiography (CTA) and has been shown to be associated with cardiac mortality. Increased volume of epicardial adipose tissue (EAT) has been reported be associated with myocardial ischemia. Purpose  We aimed to investigate for the first time a potential association between CTA-derived PCAT measures and myocardial ischemia as assessed by adenosine stress CMR perfusion imaging.  Methods In this single-centre study 109 stable individuals (mean age of 62 ± 11 years, 77% males) with coronary artery disease underwent CTA followed by adenosine stress CMR perfusion imaging to detect myocardial ischemia. PCAT CT attenuation (HU) and PCAT volume (cm³) was measured around the RCA (10 to 50 mm from RCA ostium), the proximal 40 mm of the left anterior descending artery (LAD) and the circumflex artery (LCX) using semi-automated software. Per patient PCAT CT attenuation was calculated as followed: (PCAT attenuation of RCA + LAD + LCX)/3). Non-contrast CT data sets were used for coronary calcium scoring and the quantification of EAT (located between the myocardial surface and the pericardium) and paracardial adipose tissue (PAT; intrathoracic and outside of the pericardium).  Results  Between patients with evidence of significant myocardial ischemia as assessed by adenosine stress CMR (n = 35) and patients without myocardial ischemia (n = 74) there was no significant difference in the PCAT CT attenuation of RCA (-85.3 vs. -85.7  HU, p = 0.87), LAD (-84.8 vs. -85.7 HU, p = 0.66) and LCX (-82.8 vs. -83.2 HU, p = 0.79) as well as in the per patient PCAT CT attenuation (-84.2 vs. -84.9 HU, p = 0.76). Neither did patients with myocardial ischemia within the RCA territory show increased RCA PCAT CT attenuation (-87.7 vs. -85.3 HU, p = 0.40); nor was such a relationship found for the territory of the LAD (-80.6 vs.  85.8 HU, p = 0.11) or LCX (-83.1 vs. -83.0 HU, p = 0.99). The CT attenuation of EAT (-77.9 vs. -78.7 HU, p = 0.65) and PAT (-89.9 vs. -90.0 HU, p = 0.93) did not differ significantly between patients with myocardial ischemia compared to patients without myocardial ischemia. Between patients with myocardial ischemia and patients without myocardial ischemia there was no significant difference in the volumes of EAT (118.1 vs. 110.6 cm³, p = 0.55), PAT (279.5 vs. 240.9 cm³, p = 0.20) and the per patient PCAT volume (1021.9 vs. 1015.5 cm³, p = 0.90). In logistic regression analysis the volume and CT attenuation of the different intrathoracic fat compartments PCAT, EAT and PAT were not independently associated with the presence of myocardial ischemia (n.s.).  Conclusions In this single-centre study CTA-derived quantified CT attenuation and volume of PCAT, EAT and PAT were not associated with myocardial ischemia as assessed by adenosine stress CMR perfusion imaging.

scholarly journals Quantification of Epicardial Fat using 3D Cine Dixon MRI

2020 ◽  
Author(s):  
Markus Henningsson ◽  
Martin Brundin ◽  
Tobias Scheffel ◽  
Carl Edin ◽  
Federica Viola ◽  
...  
Keyword(s):  
Adipose Tissue ◽  
Measurement Error ◽  
Single Phase ◽  
Image Quality Assessment ◽  
Epicardial Adipose Tissue ◽  
Interquartile Range ◽  
Epicardial Fat ◽  
Observer Variability ◽  
Inter Observer Variability ◽  
Significant Difference

Abstract Background There is an increased interest in quantifying and characterizing epicardial fat which has been linked to various cardiovascular diseases such as coronary artery disease and atrial fibrillation. Recently, three-dimensional single-phase Dixon techniques has been used to depict the heart and to quantify the surrounding fat. The purpose of this study was to investigate the merits of a new high-resolution cine 3D Dixon technique for quantification of epicardial adipose tissue and compare it to single-phase 3D Dixon in patients with cardiovascular disease.Methods Fifteen patients referred for clinical CMR examination of known or suspected heart disease were scanned on a 1.5T scanner using single-phase Dixon and cine Dixon. Epicardial fat was segmented by three readers and intra- and inter-observer variability was calculated per slice. Cine Dixon segmentation was performed in the same cardiac phase as single-phase Dixon. Subjective image quality assessment of water and fat images were performed by three readers using a 4-point Likert scale (1 = severe; 2 = significant; 3 = mild; 4 = no blurring of cardiac structures).Results Intra-observer variability was excellent for cine Dixon images (ICC = 0.96), and higher than single-phase Dixon (ICC = 0.92). Inter-observer variability was good for cine Dixon (ICC = 0.76) and moderate for single-phase Dixon (ICC = 0.63). The intra-observer measurement error (mean ± standard deviation) per slice for cine was − 0.02 ± 0.51 ml (-0.08 ± 0.4%), and for single-phase 0.39 ± 0.72 ml (0.18 ± 0.41%). Inter-observer measurement error for cine was 0.46 ± 0.98 ml (0.11 ± 0.46%) and for single-phase 0.42 ± 1.53 ml (0.17 ± 0.47%). Visual scoring of the water image yielded median of 2 (interquartile range = [Q3-Q1] 2–2) for cine and median of 3 (interquartile range = 3 − 2) for single-phase (P < 0.05) while no significant difference was found for the fat images, both techniques yielding a median of 3 and interquartile range of 3 − 2.Conclusion Cine Dixon can be used to quantify epicardial fat with lower intra- and inter-observer variability compared to standard single-phase Dixon. The time-resolved information provided by the cine acquisition appears to support the delineation of the epicardial adipose tissue depot.

scholarly journals Quantification of epicardial fat using 3D cine Dixon MRI

2020 ◽  
Author(s):  
Markus Henningsson ◽  
Martin Brundin ◽  
Tobias Scheffel ◽  
Carl Edin ◽  
Federica Viola ◽  
...  
Keyword(s):  
Adipose Tissue ◽  
Measurement Error ◽  
Single Phase ◽  
Image Quality Assessment ◽  
Epicardial Adipose Tissue ◽  
Interquartile Range ◽  
Epicardial Fat ◽  
Observer Variability ◽  
Inter Observer Variability ◽  
Significant Difference

Abstract Background: There is an increased interest in quantifying and characterizing epicardial fat which has been linked to various cardiovascular diseases such as coronary artery disease and atrial fibrillation. Recently, three-dimensional single-phase Dixon techniques have been used to depict the heart and to quantify the surrounding fat. The purpose of this study was to investigate the merits of a new high-resolution cine 3D Dixon technique for quantification of epicardial adipose tissue and compare it to single-phase 3D Dixon in patients with cardiovascular disease. Methods: Fifteen patients referred for clinical CMR examination of known or suspected heart disease were scanned on a 1.5T scanner using single-phase Dixon and cine Dixon. Epicardial fat was segmented by three readers and intra- and inter-observer variability was calculated per slice. Cine Dixon segmentation was performed in the same cardiac phase as single-phase Dixon. Subjective image quality assessment of water and fat images were performed by three readers using a 4-point Likert scale (1=severe; 2=significant; 3=mild; 4=no blurring of cardiac structures).Results: Intra-observer variability was excellent for cine Dixon images (ICC=0.96), and higher than single-phase Dixon (ICC=0.92). Inter-observer variability was good for cine Dixon (ICC=0.76) and moderate for single-phase Dixon (ICC=0.63). The intra-observer measurement error (mean ± standard deviation) per slice for cine was -0.02±0.51 ml (-0.08±0.4%), and for single-phase 0.39±0.72 ml (0.18±0.41%). Inter-observer measurement error for cine was 0.46±0.98 ml (0.11±0.46%) and for single-phase 0.42±1.53 ml (0.17±0.47%). Visual scoring of the water image yielded median of 2 (interquartile range = [Q3-Q1] 2-2) for cine and median of 3 (interquartile range = 3-2) for single-phase (P < 0.05) while no significant difference was found for the fat images, both techniques yielding a median of 3 and interquartile range of 3-2. Conclusion: Cine Dixon can be used to quantify epicardial fat with lower intra- and inter-observer variability compared to standard single-phase Dixon. The time-resolved information provided by the cine acquisition appears to support the delineation of the epicardial adipose tissue depot.

Abstract 12678: Clinical Utility of Echocardiographic Epicardial Adipose Tissue Thickness Measured Using a High-frequency Linear Probe in Patients With Coronary Artery Disease

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Yukia Hirata ◽  
Hirotsugu Yamada ◽  
Kenya Kusunose ◽  
Susumu Nishio ◽  
Mika Bando ◽  
...  
Keyword(s):  
Risk Factors ◽  
Coronary Artery Disease ◽  
Adipose Tissue ◽  
Coronary Artery ◽  
Coronary Angiography ◽  
High Frequency ◽  
Epicardial Adipose Tissue ◽  
Linear Probe ◽  
Significant Difference ◽  
Artery Disease

Introduction: Epicardial adipose tissue(EAT), which is thought to be an ectopic adipose tissue, has been paid attention in association with coronary artery disease (CAD). Hypothesis: We hypothesized that EAT in anterior interventricular groove (AIG) obtained by echocardiography can be an additional marker over classical risk factors for prediction of CAD. Methods: We enrolled 311 patients (mean age 67±11 yrs, 208 men) who underwent coronary angiography between December 2011 and December 2013 at our hospital. We measured EAT thickness on the AIG and right ventricular free wall (EAT-RV) using high-frequency linear probe. Subjects were divided into 2 groups with and without significant coronary stenosis (≧75%) from coronary angiography. The performance of clinical risk factors (including age, male gender, body mass index (BMI), diabetes mellitus, hypertension, dyslipidemia, and smoking) plus various combinations of EAT thickness measurements for predicting CAD was assessed using the area under the curve (AUC) in ROC analysis. Results: The EAT-AIG thickness was significantly greater in the CAD group than that in the non-CAD group (8.3±3.0 vs. 6.3±2.5 mm, p<0.001), and there as also significant difference in the EAT-RV between the two groups (5.0±2.1 vs. 4.4±2.3 mm, p=0.009). Adding the EAT-AIG thickness over classical risk factors improved prediction of presence CAD (AUC 0.692 vs. 0.788, p<0.001), while the EAT-RV did not (AUC 0.692 vs. 0.704, p=0.343). Conclusions: Echocardiographic EAT-AIG thickness was greater in the CAD group than the non-CAD group. This non-invasive index may have clinical potential as a maker for predicting coronary atherosclerosis.

scholarly journals Association of Epicardial Adipose Tissue Volume and Total Coronary Plaque Burden in Patients with Coronary Artery Disease

2018 ◽  
Vol 59 (6) ◽  
pp. 1219-1226 ◽  
Author(s):  
Kennosuke Yamashita ◽  
Myong Hwa Yamamoto ◽  
Wataru Igawa ◽  
Morio Ono ◽  
Takehiko Kido ◽  
...  
Keyword(s):  
Coronary Artery Disease ◽  
Adipose Tissue ◽  
Coronary Artery ◽  
Epicardial Adipose Tissue ◽  
Coronary Plaque ◽  
Plaque Burden ◽  
Tissue Volume ◽  
Adipose Tissue Volume ◽  
Artery Disease
Sign in / Sign up

Export Citation Format

Share Document