Predictive Value of Spectral Computed Tomography Parameters in Esophageal Variceal Rupture and Bleeding in Cirrhosis

Abstract

Background: To evaluate the value of the spectral CT parameters in predicting the risk of esophageal variceal bleeding in cirrhosis with portal hypertension and to provide a reference for clinical diagnosis and treatment.

Methods: Seventy-eight patients were divided into an esophageal variceal bleeding group and a non- esophageal variceal bleeding group. A comparison of variables including age, gender, platelet count, Child-Pugh classification, and spectral parameters between the 2 groups was done. Baseline model and spectral model were constructed with conventional parameters and conventional parameters coupled with spectral parameters, respectively. The 2 models were analyzed by the Receiver Operating Characteristic (ROC) curve.

Results: The baseline model was established based on 4 conventional parameters and evaluated by ROC curve analysis. The spectral model was constructed based on the variables in the baseline combined with normalized iodine density in the liver parenchyma for the arterial phase, normalized iodine density in the liver parenchyma for the portal phase, normalized iodine density in the splenic parenchyma for the portal phase, diameter of the main portal vein, diameter of the splenic vein, and normalized iodine density of the left gastric vein. Normalized iodine density of the left gastric vein, normalized iodine density in the liver parenchyma for the portal phase, and Child-Pugh classification were the influencing factors of esophageal variceal bleeding in cirrhosis patients. The Area Under Curve (AUC) for the baseline and spectral models were compared (0.664 vs. 0.860) and the difference was found to be statistically significant (P < .001).

Conclusions: The use of spectral CT parameters in consort with the conventional parameters can improve the diagnostic effectiveness of esophageal variceal bleeding in cirrhosis cases and screen for high-risk esophageal variceal bleeding patients. It may also provide an objective basis for the clinical prevention and treatment of esophageal variceal bleeding.

Figure 1.

Spectral CT images (A) Axial ROI in hepatic artery phase (L1, L2, L3, L4, L5, and L6 represent iodine density (mg/mL) in the left lateral lobe, left medial lobe, right anterior lobe, right posterior lobe, caudate lobe, and abdominal aorta, respectively, in the hepatic artery phase). (B) Axial ROI in hepatic portal phase (L1, L2, L3, L4, L5, L6, and L7 represent iodine density in the left lateral lobe, left medial lobe, right anterior lobe, right posterior lobe, caudate lobe, main portal vein, and spleen parenchyma, respectively, in the hepatic portal phase). (C) Coronal ROI of the left gastric vein (L7 represent iodine density in the left gastric vein).

Figure 2.

Comparative analysis of ROC curves of the 2 models.