MRI-based prediction of very early recurrence within 1 year after resection of HCC: An international cohort study

Background & Aims Very early recurrence (within one year after resection) of hepatocellular carcinoma (HCC) indicates aggressive tumor biology and poor prognosis, yet noninvasive prediction tools remain scarce. This study aimed to develop and validate MRI-based models for very early recurrence prediction and explore their biological underpinnings. Methods This international, multicenter cohort study retrospectively included 1811 consecutive patients who underwent curative-intent resection for single BCLC 0/A HCC and preoperative contrast-enhanced MRI or CT across 14 tertiary-care hospitals in China, South Korea, Singapore, France and the USA, and 40 eligible patients from TCGA-LIHC dataset. To predict 1-year recurrence-free survival (RFS), M RI for Very E arly R ecurrence P rediction (MERP) models were developed using preoperative variables alone (MERP-pre) or combining pre- and postoperative variables (MERP-post) in the derivation cohort ( n =628), externally validated in Eastern ( n =775) and Western ( n =178) test cohorts, and extrapolated to a CT test cohort ( n =230). Biological correlates were investigated using whole-exome and RNA sequencing. Results MERP-pre incorporated alpha-fetoprotein, tumor size, portal venous phase peritumoral hypoenhancement, and blood products in mass, while MERP-post replaced tumor size with microvascular invasion (MVI). Both models outperformed major staging systems and IMbrave050 criteria across all test cohorts (C-indexes, 0.685-0.790 vs. 0.524-0.682; P values, <0.001 to 0.046) and improved risk reclassification (net reclassification improvement [NRI], 0.004-0.372). MERP models consistently stratified patients into high- and low-risk groups with distinct 1-year RFS rates (all P <0.001). MERP-pre further improved MVI-based reclassification (NRI, 0.323) and survival risk stratification. MERP-pre low-risk tumors demonstrated non-proliferative class features, increased lipid catabolism, and an immunoactive microenvironment. Conclusions MERP models may serve as robust, generalizable, and biologically correlated tools for predicting very early HCC recurrence, holding promise for refining risk-stratified management. Impact and implications Very early recurrence (VER) of hepatocellular carcinoma (HCC) within one year after resection denotes aggressive tumor biology and poor prognosis, yet reliable tools for predicting VER remain scarce. In this large, international, multicenter cohort of patients with single Barcelona Clinic Liver Cancer stage 0/A HCC undergoing curative-intent resection, we developed and externally validated two MRI-based models (MERP-pre and MERP-post) that integrate routinely available clinicopathological and imaging variables. The MERP models consistently outperformed currently adopted prognostic systems and effectively stratified patients into high- and low-risk groups with distinct 1-year recurrence-free survival across diverse cohorts. These advances underscore the potential of MERP models to complement existing systems for optimizing risk-stratified management of HCC.