Comparison of Machine Learning Computed Tomography-Based Fractional Flow Reserve and Coronary CT Angiography-Derived Plaque Characteristics with Invasive Resting Full-Cycle Ratio

Imaging biomarkers in cardiac CT: moving beyond simple coronary anatomical assessment

Cardiac computed tomography angiography (CCTA) is considered the standard non-invasive tool to rule-out obstructive coronary artery disease (CAD). Moreover, several imaging biomarkers have been developed on cardiac-CT imaging to assess global CAD severity and atherosclerotic burden, including coronary calcium scoring, the segment involvement score, segment stenosis score and the Leaman-score. Myocardial perfusion imaging enables the diagnosis of myocardial ischemia and microvascular damage, and the CT-based fractional flow reserve quantification allows to evaluate non-invasively hemodynamic impact of the coronary stenosis. The texture and density of the epicardial and perivascular adipose tissue, the hypodense plaque burden, the radiomic phenotyping of coronary plaques or the fat radiomic profile are novel CT imaging features emerging as biomarkers of inflammation and plaque instability, which may implement the risk stratification strategies. The ability to perform myocardial tissue characterization by extracellular volume fraction and radiomic features appears promising in predicting arrhythmogenic risk and cardiovascular events. New imaging biomarkers are expanding the potential of cardiac CT for phenotyping the individual profile of CAD involvement and opening new frontiers for the practice of more personalized medicine.

Feasibility and Comparison of Resting Full-Cycle Ratio and Computed Tomography Fractional Flow Reserve in Patients with Severe Aortic Valve Stenosis

Background: Computed tomography derived Fractional Flow Reserve (CT-FFR) has been shown to decrease the referral rate for invasive coronary angiography (ICA). The purpose of the study was to evaluate the diagnostic performance of CT-FFR compared to hyperemia-free index Resting Full-cycle Ratio (RFR) in patients with relevant aortic stenosis (AS) and intermediate coronary stenosis. Methods: 41 patients with 46 coronary lesions underwent ICA with quantitative coronary angiography (QCA), pressure wire assessment and routine pre-transcatheter aortic valve replacement (TAVR) computed tomography (CT). CT-FFR analysis was performed using prototype on-site software. Results: RFR showed a significant correlation with CT-FFR (Pearson’s correlation, r = 0.632, p < 0.001). On a per-lesion basis, diagnostic accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of CT-FFR were 82.6% (95% CI 68.6−92.2), 69.6% (95% CI 47.1−86.8), 95.7% (95% CI  78.1−99.9), 94.1% (95% CI 69.8−99.1), and 75.9% (95% CI 62.7−85.4), respectively. The optimal cutoff value of the CT-FFR for RFR ≤ 0.89 prediction was 0.815. The area under the receiver curve showed a larger area under the curve for CT-FFR (0.87; 95% CI 0.75−0.98) compared with CTA stenosis of ≥50% (0.54, 95% CI 0.38−0.71), CTA ≥ 70% (0.72, 95% CI 0.57−0.87) and QCA ≥ 50% (0.67, 95% CI 0.52−0.83). Conclusions: CT-FFR assessed by routine pre-TAVR CT is safe and feasible and shows a significant correlation with RFR in patients with AS. CT-FFR is superior to QCA ≥ 50%, CT ≥ 50% and CT ≥ 70% in assessing the hemodynamic relevance of intermediate coronary lesions. Thus, CT-FFR has the potential to guide revascularization in patients with AS.

Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review

The risk of coronary heart disease (CHD) clinical manifestations and patient management is estimated according to risk scores accounting multifactorial risk factors, thus failing to cover the individual cardiovascular risk. Technological improvements in the field of medical imaging, in particular, in cardiac computed tomography angiography and cardiac magnetic resonance protocols, laid the development of radiogenomics. Radiogenomics aims to integrate a huge number of imaging features and molecular profiles to identify optimal radiomic/biomarker signatures. In addition, supervised and unsupervised artificial intelligence algorithms have the potential to combine different layers of data (imaging parameters and features, clinical variables and biomarkers) and elaborate complex and specific CHD risk models allowing more accurate diagnosis and reliable prognosis prediction. Literature from the past 5 years was systematically collected from PubMed and Scopus databases, and 60 studies were selected. We speculated the applicability of radiogenomics and artificial intelligence through the application of machine learning algorithms to identify CHD and characterize atherosclerotic lesions and myocardial abnormalities. Radiomic features extracted by cardiac computed tomography angiography and cardiac magnetic resonance showed good diagnostic accuracy for the identification of coronary plaques and myocardium structure; on the other hand, few studies exploited radiogenomics integration, thus suggesting further research efforts in this field. Cardiac computed tomography angiography resulted the most used noninvasive imaging modality for artificial intelligence applications. Several studies provided high performance for CHD diagnosis, classification, and prognostic assessment even though several efforts are still needed to validate and standardize algorithms for CHD patient routine according to good medical practice.

CT-FFR vs a model of combined plaque characteristics for identifying ischemia: Results from CT-FFR CHINA trial

OBJECTIVES

To evaluate the diagnostic performance of fractional flow reserve (FFR) derived from coronary computed tomography angiography (CCTA; CT-FFR) and combined plaque characteristics for ischemia in different CCTA stenosis levels.

METHODS

This clinical trial analyzed 317 patients with 30 %-90 % coronary stenosis in 366 vessels from 5 centers undergoing CCTA and invasive FFR. 366 vessels were assigned into < 50 % (nonobstructive) and ≥ 50 % (obstructive) stenosis groups. Lesion length (LL), plaque burden (PB), diameter stenosis (DS), volume ratio of plaque subcomponents < 30 HU (VR < 30HU), and high-risk features were analyzed. Logistic regression models were used to identify plaque characteristic predictors for lesion-specific ischemia in different stenosis grades. The area under receiver operating characteristics curve (AUC) of integrated plaque characteristics and CT-FFR were calculated and compared.

RESULTS

In < 50 % stenosis lesions, PB (OR: 1.296, p = 0.002), LL (OR:1.075, p = 0.020), and DS (OR:1.085, p = 0.031) were independent predictors of ischemia. In ≥ 50 % stenosis lesions, VR < 30HU (OR:1.031, p = 0.005) and DS (OR: 1.020, p =  0.044) were independent predictors for ischemia. AUC of plaque characteristic (VR < 30HU plus DS) for ischemia was 0.67 (95 % CI: 0.61-0.72) in ≥ 50 % stenosis level, which was significantly lower than CT-FFR (AUC=0.90; 95 % CI: 0.86-0.93) (p <  0.001). For lesions causing < 50 % stenosis, AUC of combined plaque model (VR < 30HU plus DS) was 0.88 (95 % CI: 0.80-0.95), equivalent to AUC of CT-FFR (AUC = 0.88; 95 % CI: 0.80-0.96; p =  0.957).

CONCLUSION

CT-FFR is a powerful functional assessment tool for both obstructive and nonobstructive diseases. However, for nonobstructive CAD confirmed by CCTA, a model of a combination of plaque characteristics could be a valuable alternative to CT-FFR.