Contrast-enhanced ultrasound-based ultrasomics score: a potential biomarker for predicting early recurrence of hepatocellular carcinoma after resection or ablation

Abstract

Objectives: This study aimed to construct a prediction model based on contrast-enhanced ultrasound (CEUS) ultrasomics features and investigate its efficacy in predicting early recurrence (ER) of primary hepatocellular carcinoma (HCC) after resection or ablation.

Methods: This study retrospectively included 215 patients with primary HCC, who were divided into a developmental cohort (n = 139) and a test cohort (n = 76). Four representative images-grayscale ultrasound, arterial phase, portal venous phase and delayed phase-were extracted from each CEUS video. Ultrasomics features were extracted from tumoral and peritumoral area inside the region of interest. Logistic regression was used to establish models, including a tumoral model, a peritumoral model and a combined model with additional clinical risk factors. The performance of the three models in predicting recurrence within 2 years was verified.

Results: The combined model performed best in predicting recurrence within 2 years, with an area under the curve (AUC) of 0.845, while the tumoral model had an AUC of 0.810 and the peritumoral model one of 0.808. For prediction of recurrence-free survival, the 2-year cumulative recurrence rate was significant higher in the high-risk group (76.5%) than in the low-risk group (9.5%; p < 0.0001).

Conclusion: These CEUS ultrasomics models, especially the combined model, had good efficacy in predicting early recurrence of HCC. The combined model has potential for individual survival assessment for HCC patients undergoing resection or ablation.

Advances in knowledge: CEUS ultrasomics had high sensitivity, specificity and PPV in diagnosing early recurrence of HCC, and high efficacy in predicting early recurrence of HCC (AUC > 0.8). The combined model performed better than the tumoral ultrasomics model and peritumoral ultrasomics model in predicting recurrence within 2 years. Recurrence was more likely to occur in the high-risk group than in the low-risk group, with 2-year cumulative recurrence rates, respectively, 76.5% and 9.5% (p < 0.0001).

Figure 1.

Flowchart of the patient selection process (HCC, hepatocellular carcinoma; CEUS, contrast-enhanced ultrasound)

Figure 2.

Drawing of the region of interest (ROI). A 62-year-old male with histopathologically confirmed HCC segment eight and tumor size of 2.2× 2.0 cm. (a–d) The ROI was drawn with the edge of the lesion as the boundary for the tumor model in the grayscale ultrasound, arterial phase, portal venous phase and delayed phase. (e–h) The ROI for the peritumoral model was expanded 2 cm from the lesion in the grayscale ultrasound, arterial phase, portal venous phase and delayed phase

Figure 3.

Correlation coefficient heatmap of ultrasomics features. The ruler shows the absolute correlation coefficient between features; 0 (light yellow) indicates a very low correlation and 1 (dark blue) a very high correlation. The results suggested complex feature correlations among and within the phases of CEUS, and further screening was needed to reduce the risk of overfitting of the model

Figure 4.

The ROC curves of (A) the development cohort and (B) the test cohort. The curves show that the combined model (red curve) had better performance and a higher AUC

Figure 5.

The calibration plots of (a) the tumoral model, (b) peritumoral model and (c) combined model performed in the test cohort. The calibration plots of the test cohort suggest that the peritumoral model was reliable

Figure 6.

The recurrence curve of the test cohort was divided by the combined model, as were the high-risk and low-risk groups. Orange indicates the low-risk group; blue, the high-risk group. The results showed a significant difference in recurrence between the two groups (p < 0.0001)