Background Advances in three-dimensional reconstruction techniques and computational fluid dynamics of coronary CT angiography (CCTA) data sets make feasible evaluation of endothelial shear stress (ESS) in the vessel wall. Purpose To investigate the relationship between CCTA-derived computational fluid dynamics metrics, anatomic and morphologic characteristics of coronary lesions, and their comparative performance in predicting impaired coronary vasodilating capability assessed by using PET myocardial perfusion imaging (MPI). Materials and Methods In this retrospective study, conducted between October 2019 and September 2020, coronary vessels in patients with stable chest pain and with intermediate probability of coronary artery disease who underwent both CCTA and PET MPI with oxygen 15-labeled water or nitrogen 13 ammonia and quantification of myocardial blood flow were analyzed. CCTA images were used in assessing stenosis severity, lesion-specific total plaque volume (PV), noncalcified PV, calcified PV, and plaque phenotype. PET MPI was used in assessing significant coronary stenosis. The predictive performance of the CCTA-derived parameters was evaluated by using area under the receiver operating characteristic curve (AUC) analysis. Results There were 92 coronary vessels evaluated in 53 patients (mean age, 65 years ± 7; 31 men). ESS was higher in lesions with greater than 50% stenosis versus those without significant stenosis (mean, 15.1 Pa ± 30 vs 4.6 Pa ± 4 vs 3.3 Pa ± 3; P = .004). ESS was higher in functionally significant versus nonsignificant lesions (median, 7 Pa [interquartile range, 5-23 Pa] vs 2.6 Pa [interquartile range, 1.8-5 Pa], respectively; P .001). Adding ESS to stenosis severity improved prediction (change in AUC, 0.10; 95% CI: 0.04, 0.17; P = .002) for functionally significant lesions. Conclusion The combination of endothelial shear stress with coronary CT angiography (CCTA) stenosis severity improved prediction of an abnormal PET myocardial perfusion imaging result versus CCTA stenosis severity alone. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Kusmirek and Wieben in this issue.

Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): This work was supported in part from European Regional Development Fund, Operational Programme “Competitiveness, Entrepreneurship and Innovation 2014-2020 (EPAnEK)”, titled: The Greek Research Infrastructure for Personalized Medicine (pMED-GR) , no. GR 5002802 ,and by Greece and the European Union (European Social Fund-ESF) through the Operational Programme «Human Resources Development, Education and Lifelong Learning 2014-2020» in the context of the project “Assessment of coronary atherosclerosis: a new complete, anatomo-functional, morphological and biomechanical approach”, Project no. 504776 Background Computed Tomography Coronary Angiography (CTCA) is a non-invasive imaging modality, used effectively for anatomo-functional assessment of coronary artery disease (CAD). Machine learning (ML) processes can effectively allow the extraction of useful information from multidimensional feature spaces for evaluation of coronary lesions. Purpose To investigate the ability of ML for predicting impaired myocardial blood flow (MBF) by combining computational fluid dynamics (CFD) derived parameters with quantitative plaque burden, plaque morphology and anatomical characteristics obtained from CTCA. Methods 53 patients (31 male, mean age 64.7 ± 7.1 years) with intermediate pre-test likelihood of CAD who underwent CTCA and PET-MPI were included. PET was considered positive when > 1 contiguous segment demonstrated MBF ≤ 2.3 mL/g/min for 15O-water or ≤ 1.79 for 13N-ammonia respectively. CFD derived parameters such as a previously validated, virtual functional assessment index (vFAI), segmental endothelial shear stress (ESS), as well as anatomical and plaque characteristics were assessed. Seven classifiers were implemented and internally validated using 5-fold cross validation, repeated 1000 times. Using sequential forward selection (SFS), the highest rank features combination, based on appearances in the highest mean area under curve (AUC) classification scheme, was selected and features performance was evaluated following exhaustive search (ES). Results 92 coronary segments were analyzed and 34 features derived from CTCA were extracted. Classifiers performance are depicted in Figure A. k-NN was the best classifier with AUCmean = 0.791 (SENSmean= 0.622, SPECmean = 0.840, p < 0.05). Clusters of features and number of appearances are presented in Figure B. The combination of vFAI, stenosis severity and lumen area demonstrated the highest AUC (1473 times). ES results are depicted in Figure C. The combination of vFAI and lumen area was the best predictor among all the combinations (AUCmean = 0.830, SENSmean =0.61, SPECmean =0.83, p < 0.05) followed by vFAI and stenosis severity (AUCmean = 0.81, SENSmean =0.72, SPECmean = 0.87, p < 0.05) and vFAI alone (AUCmean = 0.806, SENSmean =0.61, SPECmean =0.87, p < 0.05). Conclusion ML analysis is feasible for predicting with reasonable specificity abnormal MBF by PET, using a combination of CFD derived parameters and anatomical features. vFAI as a single characteristic was a specific predictor of impaired MBF, whilst in combination with stenosis severity, maintained almost the same AUC and specificity values and resulted in improved sensitivity. On the other hand, addition of lumen area to vFAI, increases the AUC and provides a relatively good specificity but low  sensitivity. Abstract Figure 1

Background Computed Tomography Coronary Angiography (CTCA) is an effective non-invasive imaging modality for anatomo-functional assessment of coronary artery disease (CAD). Radiomics features have been used for diagnosis or outcome prediction, however, their potential value for characterizing flow limiting coronary lesions has not been explored. Purpose To assess whether application of novel radiomics and machine learning (ML) techniques on CTCA derived datasets improves characterization of functionally significant coronary lesions. Methods Consecutive patients with stable chest pain and intermediate pre-test likelihood for CAD, who underwent CTCA and PET-or SPECT-Myocardial Perfusion Imaging (MPI) respectively, were prospectively evaluated and included in the analysis. PET-MPI was considered abnormal when >1 contiguous segments showed both stress Myocardial Blood Flow ≤2.3mL/g/min and Myocardial Flow Reserve (MFR) ≤2.5 for 15O-water or <1.79 mL/g/min and ≤2.0 for 13N-ammonia respectively. Defect reversibility (DR) was defined as a summed difference score (SDS) between stress and rest images ≥2. CTCA and functional images were fused to assign each myocardial segment to the pertinent coronary territory. Stenosis severity, plaque characteristics and radiomic plaque features were assessed in the total length of the 3 main coronary vessels. In total, 1765 features were extracted from each vessel and a feature reduction and model creation pipeline was constructed [Figure 1]. Two separate datasets: a) coronary stenosis (≥50%) + plaque characteristics and b) coronary stenosis (≥50%) + plaque characteristics + radiomics were formulated and compared in terms of AUCs accordingly. Results A total of 292 coronary vessels (140 with corresponding PET-MPI data and 152 with SPECT MPI data) were analysed. Plaque burden and stenosis severity were the only independent predictors of impaired myocardial perfusion on PET-MPI, with an AUC = 0.749, (95% CI: 0.658–0.826). Stenosis severity, kurtosis, contrast, interquartile range and entropy were predictors of an abnormal PET-MPI result and their combination resulted in an AUC = 0.854, (95% CI: 0.775–0.914). The difference between the 2 models was statistically significant (p-diff: 0.02, 95% CI: 0.0165–0.194). Stenosis severity was the only predictor of a DR on SPECT-MPI, AUC = 0.624 (95% CI: 0.542–0.702). Small Dependence High Gray Level Emphasis, Cluster Prominence, Region Length, wavelet Median and square Median were predictors of a positive SPECT result, with AUC = 0.816, (95% CI: 0.745–0.875). The difference between the two models was statistically significant (p-diff: 0.006, 95% CI: 0.152–0.329) Conclusion Radiomic futures can be combined with anatomical and morphological characteristics of coronary lesions in CTCA imaging and provide valuable complementary information for characterizing functionally significant coronary lesions. Funding Acknowledgement Type of funding sources: Public grant(s) – EU funding. Main funding source(s): This work was supported from European Regional Development Fund, Operational Programme “Competitiveness, Entrepreneurship and Innovation 2014-2022 (EPAnEK)”, titled: The Greek Research Infrastructure for Personalized Medicine (pMED-GR)

Background Advances in CTCA imaging enable assessment of coronary plaque burden, a predictor of myocardial perfusion abnormalities and more recently, with the use of computational fluid dynamics (CFD) of endothelial shear stress (ESS), an established contributor to atherosclerotic plaque development and progression. Purpose To investigate the relationship of local endothelial shear stress (ESS) and plaque burden (PB) between them and with stenosis severity as well as their comparative performance in predicting impaired coronary vasodilating capability assessed by PET myocardial perfusion imaging (MPI). Methods 49 patients (29 males, mean age 65.3±6.3 years, intermediate pre-test likelihood of coronary artery disease, CAD), who underwent PET-MPI with 15O-water or 13N-ammonia and CTCA were included. PET was considered abnormal when >1 contiguous segment showed both stress Myocardial Blood Flow ≤2.3 mL/g/min and Myocardial Flow Reserve ≤2.5 for 15O-water or <1.79 mL/g/min and ≤2.0 for 13N-ammonia respectively. On CTCA, stenosis (sten) severity was classified as: <30%, 31–50%, 51–70% and 71–90%. CFD were applied to every vessel, assuming a mean pressure of 100 mmHg as the inlet boundary condition and a coronary velocity profile of 1 ml/sec as the outlet. ESS was calculated for the full length of a stenosis (total), as well as in the proximal (prox), minimum lumen area (MLA) and distal (dist) stenotic segments. Atherosclerotic PB was defined as lesion plaque volume/lesion vessel volume ×100. Results 85 coronary vessels were evaluated. There was a positive correlation between ESS and PB (r(total)=0.544, r(prox)=0.528, r(MLA)=0.529, r(dist)=0.474, p<0.001 for all). All ESS indices and PB increased progressively with stenosis severity compared to segments with a <30% stenosis (p≤0.004 for all comparisons). ESS indices and PB were also higher in lesions demonstrating impaired vasodilating capacity compared to those without (p≤0.02 for all comparisons, figure 1). All ESS indices performed equally with PB and sten >50% in predicting an abnormal PET MPI, (AUC: from 0.682 to 0.780, p-diff >0.5 for all comparisons). The pairwise combination of sten >50% with the ESS segments, except the distal one, increased the predictive ability of the model over stenosis alone (AUC (sten >50% + ESS(total)) = 0.80, AUC (sten >50% + ESS(prox)) = 0.797, AUC (sten >50% + ESS(MLA)) = 0.822, p-diff ≤0.01 for all comparisons, AUC (sten >50% + ESS(dist)) = 0.768, p-diff=0.07). Conclusion There is a low to moderate positive association between lesion plaque burden and ESS indices. Like PB, ESS increases progressively with stenosis severity and is higher in lesions paired with abnormal PET results. ESS is a moderate predictor of impaired vasodilating capability, performing equally with PB and stenosis severity. The addition of ESS to stenosis severity can improve prediction of an abnormal PET result. Figure 1 Funding Acknowledgement Type of funding source: Public grant(s) – EU funding. Main funding source(s): This study is co-financed by Greece and the European Union (European Social Fund-ESF) through the Operational Programme “Human Resources Development, Education and Lifelong Learning 2014-2020” in the context of the project “Assessment of coronary atherosclerosis: a new complete, anatomo-functional, morphological and biomechanical approach” and from p-Med GR 5002802

Funding Acknowledgements Type of funding sources: Public grant(s) – EU funding. Main funding source(s): This work was supported in part from European Regional Development Fund, Operational Programme “Competitiveness, Entrepreneurship and Innovation 2014-2020 (EPAnEK)”, titled: The Greek Research Infrastructure for Personalized Medicine (pMED-GR) , no. GR 5002802 ,and by Greece and the European Union (European Social Fund-ESF) through the Operational Programme «Human Resources Development, Education and Lifelong Learning 2014-2020» in the context of the project “Assessment of coronary atherosclerosis: a new complete, anatomo-functional, morphological and biomechanical approach”, Project no. 504776 onbehalf EVINCI-SMARTOOL Background/Objectives: The relationship between biomechanical characteristics of a coronary lesion with myocardial blood flow has not been studied. We investigated the relationship between local endothelial shear stress (ESS) and computed tomography coronary angiography (CTCA)-derived anatomical and plaque characteristics data with impaired vasodilating capability assessed by positron emission tomography myocardial perfusion imaging (PET-MPI). Methods A total of 92 coronary vessels of 53 patients who have undergone both CTCA and PET-MPI with 15O-water or 13N-ammonia were analysed. PET was considered abnormal when > 1 contiguous segments showed both stress Myocardial Blood Flow (MBF) ≤2.3mL/g/min and Myocardial Flow Reserve (MFR) ≤2.5 for 15O-water or <1.79 mL/g/min and ≤2.0 for 13N-ammonia respectively.  CTCA images were used to assess stenosis severity, lesion specific total plaque volume (PV), non-calcified PV and calcified PV as well as plaque phenotype. ESS was calculated for the full length of a lesion (total), as well as in the proximal, minimum lumen area and distal lesion segments. Results ESS was weakly correlated with total PV (rho = 0.273, p = 0.008), non-calcified PV (rho = 0.247, p = 0.017) and the volume of necrotic core (rho = 0.242, p = 0.02). ESS increased progressively with stenosis severity (p ≤ 0.001). ΕSS was also higher in functionally significant vs. non-significant lesions (10.4 [8.04-54.4] Pa vs. 3.9 [2.32-7.29] Pa, p ≤0.001). Addition of ESS to stenosis severity improved prediction (Δ[AUC]:0.113, 95% CI: 0.055 to 0.171, p = 0.0001) of functionally significant lesions. Conclusion There is a weak positive association between lesion-specific ESS and plaque volume. ESS increases progressively with stenosis severity and is higher in functionally significant lesions by PET-MPI. The addition of ESS to CTCA-anatomical information improves prediction of an abnormal PET-MPI result.