Multimodal imaging-based prediction of recurrence for unresectable HCC after downstage and resection-cohort study

Abstract

Background: Surgical resection (SR) following transarterial chemoembolization (TACE)-based downstaging is a promising treatment for unresectable hepatocellular carcinoma (uHCC), and identification of patients at high-risk of postoperative recurrence may assist individualized treatment. Purpose: To develop and externally validate preoperative and postoperative prognostic models integrating multimodal CT and digital subtraction angiography features as well as clinico-therapeutic-pathological features for predicting disease-free survival (DFS) after TACE-based downstaging therapy. Materials and methods: From March 2008 to August 2022, 488 consecutive patients with Barcelona Clinic Liver Cancer (BCLC) A/B uHCC receiving TACE-based downstaging therapy and subsequent SR were included from four tertiary-care hospitals. All CT and digital subtraction angiography images were independently evaluated by two blinded radiologists. In the derivation cohort (n=390), the XGBoost algorithm was used for feature selection, and Cox regression analysis for developing nomograms for DFS (time from downstaging to postoperative recurrence or death). In the external testing cohort (n=98), model performances were compared with five major staging systems. Results: The preoperative nomogram included over three tumors [hazard ratio (HR), 1.42; P=0.003], intratumoral artery (HR, 1.38; P=0.006), TACE combined with tyrosine kinase inhibitor (HR, 0.46; P<0.001) and objective response to downstaging therapy (HR, 1.60; P<0.001); while the postoperative nomogram included over three tumors (HR, 1.43; P=0.013), intratumoral artery (HR, 1.38; P=0.020), TACE combined with tyrosine kinase inhibitor (HR, 0.48; P<0.001), objective response to downstaging therapy (HR, 1.69; P<0.001) and microvascular invasion (HR, 2.20; P<0.001). The testing dataset C-indexes of the preoperative (0.651) and postoperative (0.687) nomograms were higher than all five staging systems (0.472–0.542; all P<0.001). Two prognostically distinct risk strata were identified according to these nomograms (all P<0.001). Conclusion: Based on 488 patients receiving TACE-based downstaging therapy and subsequent SR for BCLC A/B uHCCs, the authors developed and externally validated two nomograms for predicting DFS, with superior performances than five major staging systems and effective survival stratification.