Ultrasound Radiomics Nomogram Integrating Three-Dimensional Features Based on Carotid Plaques to Evaluate Coronary Artery Disease

Abstract

This study aimed to explore the feasibility of ultrasound radiomics analysis before invasive coronary angiography (ICA) for evaluating the severity of coronary artery disease (CAD) quantified by the SYNTAX score (SS). This study included 105 carotid plaques from 105 patients (64 low-SS patients, 41 intermediate-high-SS patients). The clinical characteristics and three-dimensional ultrasound (3D-US) features before ICA were assessed. Ultrasound images of carotid plaques were used for radiomics analysis. Least absolute shrinkage and selection operator (LASSO) regression, which generated several nonzero coefficients, was used to select features that could predict intermediate-high SS. Based on those coefficients, the radiomics score (Rad-score) was calculated. The selected clinical characteristics, 3D-US features, and Rad-score were finally integrated into a radiomics nomogram. Among the clinical characteristics and 3D-US features, high-density lipoprotein (HDL), apolipoprotein B (Apo B), and plaque volume were identified as predictors for distinguishing between low SS and intermediate-high SS. During the radiomics process, 8 optimal radiomics features most capable of identifying intermediate-high SS were selected from 851 candidate radiomics features. The differences in Rad-score between the training and the validation set were significant (p = 0.016 and 0.006). The radiomics nomogram integrating HDL, Apo B, plaque volume, and Rad-score showed excellent results in the training set (AUC, 0.741 (95% confidence interval (CI): 0.646-0.835)) and validation set (AUC, 0.939 (95% CI: 0.860-1.000)), with good calibration (mean absolute errors of 0.028 and 0.059 in training and validation sets, respectively). Decision curve analysis showed that the radiomics nomogram could identify patients who could obtain the most benefit. We concluded that the radiomics nomogram based on carotid plaque ultrasound has favorable value for the noninvasive prediction of intermediate-high SS. This radiomics nomogram has potential value for the risk stratification of CAD before ICA and provides clinicians with a noninvasive diagnostic tool.

Keywords: SYNTAX; carotid plaques; radiomics; three-dimensional ultrasound; ultrasound image.

Figure 1

Flow chart of patient enrollment. CAD, coronary artery disease; ICA, invasive coronary angiography; 2D-US, two-dimensional ultrasound; 3D-US, three-dimensional ultrasound; SS, SYNTAX score.

Figure 2

Workflow of the radiomics analysis to distinguish between low and intermediate-high SYNTAX scores.

Figure 3

Feature selection process of radiomics in predicting intermediate-high SS. (A,B) An optimal tuning parameter (λ) value of 0.0914, with log(λ) = −2.3925 was determined by ten-fold cross-validation via minimum mean cross-validated error in LASSO model. Eight features that were most capable of predicting intermediate-high risk of coronary atherosclerosis were selected from 851 features. (C) The coefficients of the 8 features.

Figure 4

Receiver operating characteristic (ROC) curves in both the training and the validation set. Method A, Method B, and Method C represented the modeling methods of clinical features (HDL + Apo B), ultrasound features (plaque volume + Rad-score), and the combined model (HDL + Apo B + plaque volume + Rad-score). (A) Training set: the AUCs in Model A, Model B, and Model C were 0.648 (95% CI, 0.543–0.753), 0.723 (95% CI, 0.627–0.818) and 0.741 (95% CI, 0.646–0.835), respectively. (B) Validation set: the AUCs in Model A, Model B, and Model C were 0.667 (95% CI, 0.485–0.848), 0.922 (95% CI, 0.833–1.000) and 0.939 (95% CI, 0.860–1.000), respectively.

Figure 5

Decision curve analysis (DCA) of the three models in predicting intermediate-high SS. (A) Training set. (B) Validation set.

Figure 6

Nomogram combining HDL, Apo B, plaque volume, and Rad-score. (A) Nomogram plot. (B) Calibration graph for the training set. (C) Calibration graph for the validation set. HDL, high-density lipoprotein; ApoB, apolipoprotein B; PV, plaque volume; SS, SYNTAX scores. Result = 1: The SS was intermediate-high.