Value of intralesional and perilesional radiomics for predicting the bioactivity of hepatic alveolar echinococcosis

Abstract

Objectives: To investigate the value of intralesional and perilesional radiomics based on computed tomography (CT) in predicting the bioactivity of hepatic alveolar echinococcosis (HAE).

Materials and methods: In this retrospective study, 131 patients who underwent surgical resection and diagnosed HAE in pathology were included (bioactive, n=69; bioinactive, n=62). All patients were randomly assigned to the training cohort (n=78) and validation cohort (n=53) in a 6:4 ratio. The gross lesion volume (GLV), perilesional volume (PLV), and gross combined perilesional volume (GPLV) radiomics features were extracted on CT images of portal vein phase. Feature selection was performed by intra-class correlation coefficient (ICC), univariate analysis, and least absolute shrinkage and selection operator (LASSO). Radiomics models were established by support vector machine (SVM). The Radscore of the best radiomics model and clinical independent predictors were combined to establish a clinical radiomics nomogram. Receiver operating characteristic curve (ROC) and decision curves were used to evaluate the predictive performance of the nomogram model.

Results: In the training cohort, the area under the ROC curve (AUC) of the GLV, PLV, and GPLV radiomic models was 0.774, 0.729, and 0.868, respectively. GPLV radiomic models performed best among the three models in training and validation cohort. Calcification type and fibrinogen were clinical independent predictors (p<0.05). The AUC of the nomogram-model-based clinical and GPLV radiomic signatures was 0.914 in the training cohort and 0.833 in the validation cohort. The decision curve analysis showed that the nomogram had greater benefits compared with the single radiomics model or clinical model.

Conclusion: The nomogram model based on clinical and GPLV radiomic signatures shows the best performance in prediction of the bioactivity of HAE. Radiomics including perilesional tissue can significantly improve the prediction efficacy of HAE bioactivity.

Keywords: computed tomography; hepatic alveolar echinococcosis; nomogram; perilesional; radiomics.

Figure 1

(A) Flow chart of patient enrollment; (B) the radiomics workflow.

Figure 2

(A) The selected features of GLV model, (B) the selected features of PLV model, (C) the selected features of GPLV model.

Figure 3

An individualized nomogram on Radscore and clinical features. The variables fibrinogen, calcification type, and Radscore have their own independent scale as shown in the figure, representing their respective value ranges. Each variable has a corresponding single item score at different values. The total score, summing each value of the variable, corresponds to the risk of bioactivity.

Figure 4

(A) The ROC curve for the three models in the training cohort, (B) the ROC curve for the three models in the validation cohort, (C) the DCA curve for the three models in the training cohort, (D) the DCA curve for the three models in the validation cohort.