Circulation: Cardiovascular Imaging最新文献

Background: Current atherosclerotic cardiovascular disease risk prediction tools based on traditional risk factors and the coronary artery calcium score have limitations.

Methods: The CREATION study includes patients with suspected coronary artery disease who underwent coronary computed tomography angiography (CCTA) at Fuwai Hospital between 2016 and 2019. The primary outcome was major adverse cardiac events defined as a composite end point of all-cause death, acute myocardial infarction, coronary revascularization, or stroke. Six machine learning survival models were used to create an atherosclerotic cardiovascular disease prediction model.

Results: Overall, 8431 participants with analyzable CCTA data were included with a median follow-up of 3.68 years, and 319 major adverse cardiac events (3.8%) occurred (mean age: 54.73±10.21 years, 48.2% were male, 50.9% with symptomatic chest pain). Among 6 machine learning models trained with 48 CCTA parameters, XGBoost showed the best performance and was selected for model development. In the training cohort (n=5901, 70%), the XGBoost model significantly outperformed the clinical risk factors and coronary artery calcium score model (area under the curve, 0.903 versus 0.830; P<0.001). Testing cohort showed similar performance (area under the curve, 0.899 versus 0.753; P<0.001). The CCTA model demonstrates consistent predictive performance across sex (female or male), onset-age (early onset or late-onset), and symptom (asymptomatic or symptomatic) subgroup analysis. The final CCTA model included diameter stenosis, lipid plaque burden and volume, total plaque volume, high-risk plaque, and vessel volume as the most important features. Lipid plaque burden was most strongly associated with major adverse cardiac event (adjusted hazard ratio per 5% increase: 2.524 [95% CI, 2.157-2.996]; P<0.001). The incremental value of machine learning CCTA features was consistent across different time points throughout the 1- to 5-year follow-up period. The findings remained unchanged when restricted to a secondary composite end point (death, myocardial infarction, or stroke).

Conclusions: The machine learning model incorporating CCTA plaque quantification, characterization, and stenosis assessment significantly enhanced the predictive capacity for major adverse cardiac events. It provides direct visualization of coronary atherosclerosis and outperforms the traditional risk factors and the coronary artery calcium score model recommended in clinical practice.

Background: Entropy, a novel measure of myocardial tissue heterogeneity by cardiovascular magnetic resonance imaging, may have clinical value in patients with hypertrophic cardiomyopathy (HCM). We aimed to investigate the associations of entropy with risk predictors in HCM, using the National Heart, Lung, and Blood Institute HCM Registry.

Methods: Entropy values were calculated using the probability distribution of pixel signal intensities of the left ventricular (LV) myocardium on the late gadolinium enhancement (LGE) short-axis stack images. Entropy values were correlated with demographic, genetic, imaging, and serum biomarkers as well as ambulatory Holter recordings and the European Society of Cardiology risk score of sudden cardiac death at 5 years.

Results: Among 1736 patients with HCM, LV entropy demonstrated significant associations with sarcomere mutations, history of ventricular tachycardia, atrial fibrillation, and elevation of cTnT (cardiac troponin T) and NT-proBNP (N-terminal pro-B-type natriuretic peptide) levels (P<0.001). Furthermore, LV entropy demonstrated an association with increased maximal LV wall thickness, LGE presence and extent, higher extracellular volume, left atrial area and function, myocardial strain (P<0.001), and was positively correlated with higher values of the European Society of Cardiology risk score (P<0.001). In the subgroup of patients without LGE (n=858), entropy values remained significantly associated with a history of ventricular tachycardia, increased maximal wall thickness, decreased myocardial strain, and the European Society of Cardiology risk score (P<0.05 for all). In both the whole cohort and in patients without LGE, LV entropy was the strongest predictor of ventricular tachycardia on Holter (odds ratio [95% CI] 1.59 [1.33-1.90]; 1.87 [1.28-2.74] respectively, P<0.001 for both).

Conclusions: In patients with HCM, LV entropy demonstrated associations with clinical, imaging, and biological predictors of adverse outcomes independent of LGE presence and was the strongest predictor of ventricular tachycardia on Holter.

Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT01915615.

Background: Intracoronary optical coherence tomography (OCT) can identify changes following drug/device treatment and high-risk plaques, but analysis requires expert clinician or core laboratory interpretation, while artifacts and limited sampling markedly impair reproducibility. Assistive technologies such as artificial intelligence-based analysis may therefore aid both detailed OCT interpretation and patient management. We determined if artificial intelligence-based OCT analysis (AutoOCT) can rapidly process, optimize, and analyze OCT images, and identify plaque composition changes that predict drug success/failure and high-risk plaques.

Methods: AutoOCT deep learning artificial intelligence modules were designed to correct segmentation errors from poor-quality or artifact-containing OCT images, identify tissue/plaque composition, classify plaque types, measure multiple parameters including lumen area, lipid and calcium arcs, and fibrous cap thickness, and output segmented images and clinically useful parameters. Model development used 36 212 frames (127 whole pullbacks, 106 patients). Internal validation of tissue and plaque classification and measurements used ex vivo OCT pullbacks from autopsy arteries, while external validation for plaque stabilization and identifying high-risk plaques used core laboratory analysis of IBIS-4 (Integrated Biomarkers and Imaging Study-4) high-intensity statin (83 patients) and CLIMA (Relationship Between Coronary Plaque Morphology of Left Anterior Descending Artery and Long-Term Clinical Outcome Study; 62 patients) studies, respectively.

Results: AutoOCT recovered images containing common artifacts with measurements and tissue and plaque classification accuracy of 83% versus histology, equivalent to expert clinician readers. AutoOCT replicated core laboratory plaque composition changes after high-intensity statin, including reduced lesion lipid arc (13.3° versus 12.5°) and increased minimum fibrous cap thickness (18.9 µm versus 24.4 µm). AutoOCT also identified high-risk plaque features leading to patient events including minimal lumen area <3.5 mm², Lipid arc >180°, and fibrous cap thickness <75 µm, similar to the CLIMA core laboratory.

Conclusions: AutoOCT-based analysis of whole coronary artery OCT identifies tissue and plaque types and measures features correlating with plaque stabilization and high-risk plaques. Artificial intelligence-based OCT analysis may augment clinician or core laboratory analysis of intracoronary OCT images for trials of drug/device efficacy and identifying high-risk lesions.