Chest-CT-based radiomics feature of epicardial adipose tissue for screening coronary atherosclerosis

Abstract

Background and aims: This study aims to investigate the diagnostic value of chest-CT epicardial adipose tissue (EAT) radiomics feature in coronary atherosclerotic stenosis.

Methods: Clinical data from 215 individuals who underwent coronary angiography and chest-CT scan from January to July 2022 at our institution were retrospectively analyzed. Based on the coronary angiography results, the total population, men, and women were divided into the CAD group and non-CAD group. radiomics feature of EAT at the level of the bifurcation of the left-main coronary artery on the transverse level of chest CT were measured. The features contain both first-order feature and shape-order feature.The differences between groups were analyzed using the t test or Chi-square test. The diagnostic efficacy of each parameter in diagnosing atherosclerotic stenosis of coronary arteries was assessed by plotting the receiver operating characteristic (ROC) curve.

Results: First-order features: Mean, IntDen, Median, and RawIntDen; shape-order features: Area, Perim, Round, and BSA index; and clinical index: HbA1c showed statistical significance between the CAD group and the non-CAD group. The ROC curve analysis demonstrated high diagnostic efficacy, with the best for diagnostic efficacy being Median for the first-order feature parameter (AUC, 0.753; 95% confidence interval [CI], 0.689-0.817; t = 4.785, p < 0.001), Round for the shape-order feature (AUC, 0.775; 95% CI, 0.714-0.836; t = 7.842, p < 0.001), and HbA1c for the clinical index (AUC, 0.797; 95% CI, 0.783-0.856; t = 6.406, p < 0.001). After dividing the participants into male and female subgroups, the best diagnostic efficacy was observed with the BSA index for men (AUC, 0.743; 95% CI, 0.656-0.829; t = 5.128, p < 0.001) and Round for women (AUC, 0.871; 95% CI, 0.793-0.949; t = 7.247, p < 0.001).

Conclusions: Median, Round in radiomics feature of EAT on chest CT may play a role in the assessment of coronary atherosclerotic stenosis.

Keywords: Coronary atherosclerosis stenosis; Epicardial adipose tissue; Radiomics feature; Subject operating characteristic curves.

Fig. 1

EAT left coronary bifurcation level outlining ROI. A Sixty-four -year-old male, LCX stenosis 60%; a EAT left-main coronary bifurcation level. B:Yellow line represents manually outlined EAT, red within yellow line is EAT area

Fig. 2

Gray-scale histogram of the EAT ROI. A Sixty-four -year-old male with 60% LCX stenosis.Gray-scale histogram waveform peaks to the left. B Fifty-nine-year-old male coronary artery without stenosis, gray-scale histogram waveform peaks to the right (Threshold range of less than Min-250 is due to software value interval)

Fig. 3

Parameter ROC curve for total population stenosis group and control group. The highest AUC values in the stenosis and control groups were obtained for the parameter “Round”

Fig. 4

Statistically significant parametric ROC curve for the male group (BAS index). In the male group, the highest AUC values were obtained for the parameter “BSA index”

Fig. 5

Statistically significant parameter ROC curve for the female group (Round). In the female group, the highest AUC values were obtained for the parameter “Round”

Fig. 6

Graphs showing the results of BSA index, Median, Perim, Round. Comparison of four parameters “BSA index, Median, Perim, Round” in the stenosis group and the control group