The diagnostic value of a non-contrast computed tomography scan-based radiomics model for acute aortic dissection

Abstract

To investigate the diagnostic value of a computed tomography (CT) scan-based radiomics model for acute aortic dissection.For the dissection group, we retrospectively selected 50 patients clinically diagnosed with acute aortic dissection between October 2018 and November 2019, for whom non-contrast CT and CT angiography images were available. Fifty individuals with available non-contrast CT and CT angiography images for other causes were selected for inclusion in the non-dissection group. Based on the aortic dissection locations on the CT angiography images, we marked the corresponding regions-of-interest on the non-contrast CT images of both groups. We collected 1203 characteristic parameters from these regions by extracting radiomics features. Subsequently, we used a random number table to include 70 individuals in the training group and 30 in the validation group. Finally, we used the Lasso regression for dimension reduction and predictive model construction. The diagnostic performance of the model was evaluated by a receiver operating characteristic (ROC) curve.Fourteen characteristic parameters with non-zero coefficients were selected after dimension reduction. The accuracy, sensitivity, specificity, and area under the ROC curve of the prediction model for the training group were 94.3% (66/70), 91.2% (31/34), 97.2% (35/36), and 0.988 (95% confidence interval [CI]: 0.970-0.998), respectively. The respective values for the validation group were 90.0% (27/30), 94.1% (16/17), 84.6% (11/13), and 0.952 (95% CI: 0.883-0.986).Our non-contrast CT scan-based radiomics model accurately facilitated acute aortic dissection diagnosis.

Figure 1

A 31-year-old male patient. The true and false lumens are revealed in these contrast-enhanced CT angiography images. CT = computed tomography.

Figure 2

No apparent abnormality is observed at the corresponding layer in the non-enhanced CT image of the same patient as in Fig. 1. CT = computed tomography.

Figure 3

A schematic of the region-of-interest (ROI) depicted in this layer.

Figure 4

A schematic showing radiomic features extraction by the PyRadiomics platform.

Figure 5

A flow chart showing the study design.

Figure 6

Leave-one-out cross-validation in Lasso regression yielded the binomial deviation of the model and its relationship with the regularization parameter log(λ). The dotted line on the left represents the radiomics model when using an optimum λ of 0.030718. The dotted line on the right represents the radiomics model using the smallest coefficient and λ within one standard deviation from its optimum value (the corresponding value of λ is 0.077883).

Figure 7

The relationship between the feature coefficient and log(λ) in Lasso regression. This figure describes the converging process of the feature coefficients. We obtained 14 characteristic features with non-zero coefficients when λ = 0.077883.

Figure 8

The area under the receiver operating characteristic (ROC) curve (AUC) of the non-contrast CT scan-based radiomics model for the training group was 0.988. CT = computed tomography.

Figure 9

The area under the receiver operating characteristic (ROC) curve (AUC) of the non-contrast CT scan-based radiomics model for the validation group was 0.952. CT = computed tomography.