Radiomics-Based Prediction of Future Portal Vein Tumor Infiltration in Patients with HCC—A Proof-of-Concept Study

SIMPLE SUMMARY: Portal vein infiltration (PVI) is a complication of HCC with critical impact on further patient management as systemic therapies are recommended once PVI is diagnosed. In our study, we matched 44 patients with HCC who developed PVI in the course of disease with no CT-detectable PVI at initial diagnosis to the same number of patients who never developed PVI during follow-up, but showed the same conventional tumor traits (size and number of lesions, growth type, contrast enhancement pattern, etc.). Using LASSO regression, radiomics feature analysis showed a sensitivity and specificity of 0.78 to detect the occurrence of PVI in the validation set. Therefore, an additional radiomics evaluation at initial diagnosis could help to identify patients benefiting from a closer surveillance. ABSTRACT: Portal vein infiltration (PVI) is a typical complication of HCC. Once diagnosed, it leads to classification as BCLC C with an enormous impact on patient management, as systemic therapies are henceforth recommended. Our aim was to investigate whether radiomics analysis using imaging at initial diagnosis can predict the occurrence of PVI in the course of disease. Between 2008 and 2018, we retrospectively identified 44 patients with HCC and an in-house, multiphase CT scan at initial diagnosis who presented without CT-detectable PVI but developed it in the course of disease. Accounting for size and number of lesions, growth type, arterial enhancement pattern, Child–Pugh stage, AFP levels, and subsequent therapy, we matched 44 patients with HCC who did not develop PVI to those developing PVI in the course of disease (follow-up ended December 2021). After segmentation of the tumor at initial diagnosis and texture analysis, we used LASSO regression to find radiomics features suitable for PVI detection in this matched set. Using an 80:20 split between training and holdout validation dataset, 17 radiomics features remained in the fitted model. Applying the model to the holdout validation dataset, sensitivity to detect occurrence of PVI was 0.78 and specificity was 0.78. Radiomics feature extraction had the ability to detect aggressive HCC morphology likely to result in future PVI. An additional radiomics evaluation at initial diagnosis might be a useful tool to identify patients with HCC at risk for PVI during follow-up benefiting from a closer surveillance.