Diagnostic Performance of Machine Learning-Derived Radiomics Signature of Pericoronary Adipose Tissue in Coronary Computed Tomography Angiography for Coronary Artery In-Stent Restenosis

Coronary inflammation can alter the perivascular fat phenotype. Hence, we aimed to assess the diagnostic performance of radiomics features of pericoronary adipose tissue (PCAT) in coronary computed tomography angiography (CCTA) for in-stent restenosis (ISR) after percutaneous coronary intervention.In this study, 165 patients with 214 eligible vessels were included, and ISR was found in 79 vessels. After evaluating clinical and stent characteristics, peri-stent fat attenuation index, and PCAT volume, 1688 radiomics features were extracted from each peri-stent PCAT segmentation. The eligible vessels were randomly categorized into training and validation groups in a ratio of 7:3. After performing feature selection using Pearson's correlation, F test, and least absolute shrinkage and selection operator analysis, radiomics models and integrated models that combined selected clinical features and Radscore were established using five different machine learning algorithms (logistic regression, support vector machine, random forest, stochastic gradient descent, and XGBoost). Subgroup analysis was performed using the same method for patients with stent diameters of ≤ 3 mm.Nine significant radiomics features were selected, and the areas under the curves (AUCs) for the radiomics model and the integrated model were 0.69 and 0.79, respectively, for the validation group. The AUCs of the subgroup radiomics model based on 15 selected radiomics features and the subgroup integrated model were 0.82 and 0.85, respectively, for the validation group, which showed better diagnostic performance.CCTA-based radiomics signature of PCAT has the potential to identify coronary artery ISR without additional costs or radiation exposure.