Search

Objectives: To explore whether radiomics-based machine learning (ML) models could outperform conventional diagnostic methods at identifying vulnerable lesions on coronary computed tomographic angiography (CCTA). Methods: In this retrospective study, 36 heart transplant recipients with coronary heart disease (CAD) and end-stage heart failure were included. Pathological cross-section samples of 350 plaques were collected and coregistered to patients' preoperative CCTA images. A total of 1184 radiomic features were extracted from CCTA images. Through feature selection and stratified fivefold cross-validation, we derived eight radiomics-based ML models for lesion vulnerability prediction. An independent set of 196 plaques from another 8 CAD patients who underwent heart transplants was collected to validate radiomics-based ML models' diagnostic accuracy against conventional CCTA feature-based diagnosis (presence of at least 2 high-risk plaque features). The performance of the prediction models was assessed by the area under the receiver operating characteristic curve (AUC) with 95% confidence intervals (CI). Results: The training group used to develop radiomics-based ML models contained 200/350 (57.1%) vulnerable plaques and the external validation group was composed of 67.3% (132/196) vulnerable plaques. The radiomics-based ML model based on eight radiomic features showed excellent cross-validation diagnostic accuracy (AUC: 0.900 ± 0.033). In the validation group, diagnosis based on conventional CCTA features demonstrated moderate performance (AUC: 0.656 [95% CI: 0.593 –0.718]), while the radiomics-based ML model showed higher diagnostic ability (0.782 [95% CI: 0.710 –0.846]). Conclusions: Radiomics-based ML models showed better diagnostic ability than the conventional CCTA features at assessing coronary plaque vulnerability. Key Points: • CCTA has great potential in the diagnosis of vulnerable coronary artery lesions. • Radiomics model built through CCTA could discriminate coronary vulnerable lesions in good diagnostic ability. • Radiomics model could improve the ability of vulnerability diagnosis against traditional CCTA method, sensitivity especially. [ABSTRACT FROM AUTHOR]

There is controversy about whether symptomatic population with coronary artery calcium score (CACS) of zero have coronary artery disease (CAD) and the distribution at different ages. We sought to analyze the prevalence of CAD in symptomatic patients with zero CACS, especially in different age groups. We studied patients suspected of CAD and underwent CACS scan and coronary computed tomography angiography (CTA). We included patients with CACS of zero. Clinical data was collected to achieve information on demographic characteristics and risk factors. The presence of plaque and obstructive CAD were analyzed based on coronary CTA. The association between age and the prevalence of plaque and obstructive CAD was evaluated.Overall 5514 patients (51.1% men; mean age 54.40 years) were analyzed, of whom 4120 (74.72%) with normal coronary artery, 1394 (25.28%) with plaque and 514 (9.32%) with obstructive CAD. The prevalence of plaque and obstructive CAD increased significantly with age (p < 0.001). Age was significantly associated with the risk of developing plaque and obstructive CAD in the unadjusted model and multivariate model. Taking age less than 40 as a reference, risk ratios (RRs) of prevalence of plaque increased with age in the multivariate model (RR = 2.353 for 40–50, RR = 6.489 for > 70). RRs of prevalence of obstructive CAD also increased with age in the multivariate model (RR = 2.075 for 40–50, RR = 4.102 for > 70). Quite a few CAD could occur in symptomatic patients with CACS of zero, especially in old patients. Coronary CTA was required to exclude CAD in this cohort. [ABSTRACT FROM AUTHOR]