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

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

29Prognostic safety of automatic cancellation of rest myocardial perfusion scan by machine learning: a report from multicenter REFINE SPECT registry of new generation SPECT

Background

We aimed to develop a machine learning (ML) computer score derived from stress imaging and clinical data, which indicates if the rest scan could be automatically and safely canceled in the routine stress/rest myocardial perfusion SPECT (MPS).

Methods

A total of 20414 stress/rest cases from the REFINE SPECT registry collected from 5 sites in 3 countries with Tc-99m-based MPS images, clinical data, and clinical follow-up were included in the study. All images were automatically processed at our Medical Center. The automatically generated myocardial contours were checked by experienced technologists. In total, 93 variables (26 clinical, 17 stress-test, and 50 stress-imaging variables) were used to build a LogitBoost model for prediction of adverse events (AE), including coronary revascularization, death, myocardial infarction, and unstable angina. 10-fold cross-validation was performed to separate test from validation data for the assessment of ML. The overall ML predictive performance was compared to quantitative (stress total perfusion deficit [TPD]) by the area under the receiver operating characteristic curves (AUC). ML cut-off (ML1) to simulate the decision of cancellation of the rest scan was set to result in the same % of normal scans as these determined by the normal clinical reader diagnosis on a 4-point scale in the whole population, or the same % of scans with visual summed stress scores (SSS) = 0 in the subpopulation with available SSS. A second ML cutoff (ML2) was established to achieve a 1% annual risk of AE. The annual risk of AE of the normal ML score was compared with normal clinical diagnosis and with the finding of SSS = 0.

Results

The mean follow-up interval was 4.7±1.5 years. Overall, 3542 AE were observed (3.7% annual risk). The AUC for AE was higher for ML (0.780±0.005) than for stress TPD (0.698±0.006) (p<0.001). Normal clinical diagnosis was reported in 60% cases. In 70% (14242 scans) with available segmental scores, 53% had SSS=0. ML1 and ML2 thresholds were compared with normal visual diagnosis and with SSS = 0 for AE (Figure). ML1 achieved a lower annual risk (1.5%) than normal clinical diagnosis (2.1%) or SSS = 0 (1.6% versus 2.3%) (p<0.001). The more conservative ML2 threshold with a 1% annual risk of AE resulted in a 40% canceling rate.

Figure 1

Conclusion

ML could be used to automatically cancel the rest MPS scan with the same proportion as using normal visual MPS reading, but with significantly lower AE rate in stress-only scans.

Acknowledgement/Funding

R01HL089765 from the National Heart, Lung, and Blood Institute/National Institutes of Health (NHLBI/NIH)

P6151Fully automated epicardial adipose tissue volume and density measured from non-contrast CT predict major adverse cardiovascular events in asymptomatic subjects

Background

Epicardial adipose tissue (EAT) volume and density has shown to correlate with standard markers of coronary artery disease (CAD) and may predict major adverse cardiovascular events (MACE).

Purpose

We aimed to evaluate the prognostic value of EAT volume and density measured by fully automated deep-learning software from non-contrast cardiac computed tomography (CT).

Methods

We assessed 2071 consecutive asymptomatic subjects (age 56±9 years, 59% male) from the EISNER (Early Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) trial with long-term follow-up after coronary artery calcium (CAC) measurement. EAT volume and mean density were quantified using automated deep-learning software from non-contrast cardiac CT. MACE was defined as myocardial infarction (MI), cardiac death, late (>90 days) revascularization and acute coronary syndrome (ACS). EAT volume and density were systematically compared to CAC score and atherosclerotic cardiovascular disease (ASCVD) risk score using Cox proportional hazards regression for MACE prediction.

Results

At 14±3 years, 217 subjects suffered MACE. In age-and-gender-adjusted multivariate analysis, ASCVD risk score, CAC (two-fold increase) and EAT volume (two-fold increase) were associated with increased risk of suffering MACE [Hazard Ratio (HR) (95% CI): 1.03 (1.01–1.04); 1.25 (1.19–1.30); and 1.36 (1.08–1.70) respectively, p<0.01 for all] (Figure); the corresponding Harrell's C-statistic was 0.76. The area-under-the curve from receiver-operator characteristic analysis for MACE prediction increased significantly from 0.69 to 0.77 (p<0.0001) when EAT volume and CAC were added to the current clinical standard (ASCVD, family history and obesity measures BMI and BSA). Both in men and women, increase in EAT volume was associated with increased risk of MACE, with HR 1.14 (1.06–1.22), p<0.001 in men vs. 1.15 (1.01–1.31), p=0.03 in women, for each 20 cubic centimeter increase in volume. EAT density (HU) was independently inversely associated with MACE [HR: 0.96 (0.93–0.99), p=0.01].

MACE Prediction

Conclusions

EAT volume and density measurements improve prediction of MACE in asymptomatic populations over the current clinical standard. Fully automated EAT volume and density quantification by deep-learning from non-contrast cardiac CT can provide additional prognostic value for the asymptomatic patient.

Acknowledgement/Funding

1R01HL133616, Forschungsstiftung Medizin Universitätsklinikum Erlangen, grant from Dr Miriam and Sheldon G. Adelson Medical Research Foundation