Radiomics Analysis of Pericoronary Adipose Tissue From Baseline Coronary Computed Tomography Angiography Enables Prediction of Coronary Plaque Progression.

PURPOSE: The relationship between plaque progression and pericoronary adipose tissue (PCAT) radiomics has not been comprehensively evaluated. We aim to predict plaque progression with PCAT radiomics features and evaluate their incremental value over quantitative plaque characteristics. PATIENTS AND METHODS: Between January 2009 and December 2020, 500 patients with suspected or known coronary artery disease who underwent serial coronary computed tomography angiography (CCTA) ≥2 years apart were retrospectively analyzed and randomly stratified into a training and testing data set with a ratio of 7:3. Plaque progression was defined with annual change in plaque burden exceeding the median value in the entire cohort. Quantitative plaque characteristics and PCAT radiomics features were extracted from baseline CCTA. Then we built 3 models including quantitative plaque characteristics (model 1), PCAT radiomics features (model 2), and the combined model (model 3) to compare the prediction performance evaluated by area under the curve. RESULTS: The quantitative plaque characteristics of the training set showed the values of noncalcified plaque volume (NCPV), fibrous plaque volume, lesion length, and PCAT attenuation were larger in the plaque progression group than in the nonprogression group ( P < 0.05 for all). In multivariable logistic analysis, NCPV and PCAT attenuation were independent predictors of coronary plaque progression. PCAT radiomics exhibited significantly superior prediction over quantitative plaque characteristics both in the training (area under the curve: 0.814 vs 0.615, P < 0.001) and testing (0.736 vs 0.594, P = 0.007) data sets. CONCLUSIONS: NCPV and PCAT attenuation were independent predictors of coronary plaque progression. PCAT radiomics derived from baseline CCTA achieved significantly better prediction than quantitative plaque characteristics.

Predicting coronary plaque progression with conventional plaque parameters and radiomics features derived from coronary CT angiography.

OBJECTIVES: To determine the value of combining conventional plaque parameters and radiomics features derived from coronary computed tomography angiography (CCTA) for predicting coronary plaque progression. MATERIALS AND METHODS: Clinical data and CCTA images of 400 patients who underwent at least two CCTA examinations between January 2009 and August 2020 were analyzed retrospectively. Diameter stenosis, total plaque volume and burden, calcified plaque volume and burden, noncalcified plaque volume and burden (NCPB), pericoronary fat attenuation index (FAI), and other conventional plaque parameters were recorded. The patients were assigned to a training cohort (n = 280) and a validation cohort (n = 120) in a 7:3 ratio using a stratified random splitting method. The area under the receiver operating characteristics curve (AUC) was used to evaluate the predictive abilities of conventional parameters (model 1), radiomics features (model 2), and their combination (model 3). RESULTS: FAI and NCPB were identified as independent risk factors for coronary plaque progression in the training cohort. Both model 2 (training cohort AUC: 0.814, p < 0.001; validation cohort AUC: 0.729, p = 0.288) and model 3 (training cohort AUC: 0.824, p < 0.001; validation cohort AUC: 0.758, p = 0.042) had better diagnostic performances in predicting plaque progression than model 1 (training cohort AUC: 0.646; validation cohort AUC: 0.654). Moreover, model 3 was slightly higher than model 2, although not statistically significant. CONCLUSIONS: The combination of conventional coronary plaque parameters and CCTA-derived radiomics features had a better ability to predict plaque progression than conventional parameters alone. CLINICAL RELEVANCE STATEMENT: The conventional coronary plaque characteristics such as noncalcified plaque burden, pericoronary fat attenuation index, and radiomics features derived from CCTA can identify plaques prone to progression, which is helpful for further clinical decision-making of coronary artery disease. KEY POINTS: • FAI and NCPB were identified as independent risk factors for predicting plaque progression. • Coronary plaque radiomics features were more advantageous than conventional parameters in predicting plaque progression. • The combination of conventional coronary plaque parameters and radiomics features could significantly improve the predictive ability of plaque progression over conventional parameters alone.

The incremental value of CCTA-derived myocardial radiomics signature for ischemia diagnosis with reference to CT myocardial perfusion imaging.

OBJECTIVES: To explore the incremental value of myocardial radiomics signature derived from static coronary computed tomography angiography (CCTA) for identifying myocardial ischemia based on stress dynamic CT myocardial perfusion imaging (CT-MPI). METHODS: Patients who underwent CT-MPI and CCTA were retrospectively enrolled from two independent institutions, one used as training and the other as testing. Based on CT-MPI, coronary artery supplying area with relative myocardial blood flow (rMBF) value <0.8 was considered ischemia. Conventional imaging features of target plaques which caused the most severe narrowing of the vessel included area stenosis, lesion length (LL), total plaque burden, calcification burden, non-calcification burden, high-risk plaque (HRP) score, and CT fractional flow reserve (CT-FFR). Myocardial radiomics features were extracted at three vascular supply areas from CCTA images. The optimized radiomics signature was added to the conventional CCTA features to build the combined model (radiomics + conventional). RESULTS: There were 168 vessels from 56 patients enrolled in the training set, and the testing set consisted of 135 vessels from 45 patients. From either cohort, HRP score, LL, stenosis ≥50% and CT-FFR ≤0.80 were associated with ischemia. The optimal myocardial radiomics signature consisted of nine features. The detection of ischemia using the combined model was significantly improved compared with conventional model in both training and testing set (AUC 0.789 vs 0.608, p < 0.001; 0.726 vs 0.637, p = 0.045). CONCLUSIONS: Myocardial radiomics signature extracted from static CCTA combining with conventional features could provide incremental value to diagnose specific ischemia. ADVANCES IN KNOWLEDGE: Myocardial radiomics signature extracted from CCTA may capture myocardial characteristics and provide incremental value to detect specific ischemia when combined with conventional features.