Hepatic Hypertrophy in Normal and Cirrhotic Livers Following Portal Vein Embolization: Comparative Assessment of 2 Different Embolic Regimens in a Large Animal Model.

PURPOSE: To compare the mechanistic effects and hypertrophy outcomes using 2 different portal vein embolization (PVE) regimens in normal and cirrhotic livers in a large animal model. METHODS AND MATERIALS: The Institutional Animal Care and Use Committee approved all experiments conducted in this study. Fourteen female Yorkshire pigs were separated into a cirrhotic group (CG, n = 7) and non-cirrhotic group (NCG, n = 7) and further subgrouped into those using microspheres and coils (MC, n = 3) or n-butyl cyanoacrylate (nBCA, n = 3) and their corresponding controls (each n = 1). A 3:1 ethiodized oil and ethanol mixture was administered intra-arterially in the CG to induce cirrhosis 4 weeks before PVE. Animals underwent baseline computed tomography (CT), PVE including pre-PVE and post-PVE pressure measurements, and CT imaging at 2 and 4 weeks after PVE. Immunofluorescence stainings for CD3, CD16, Ki-67, and caspase 3 were performed to assess immune cell infiltration, hepatocyte proliferation, and apoptosis. Statistical significance was tested using the Student's t test. RESULTS: Four weeks after PVE, the percentage of future liver remnant (FLR%) increased by 18.8% (standard deviation [SD], 3.6%) vs 10.9% (SD, 0.95%; P < .01) in the NCG vs CG. The baseline percentage of standardized future liver remnant (sFLR%) for the controls were 41.6% for CG vs 43.6% for NCG. Based on the embolic agents used, the sFLR% two weeks after PVE was 58.4% (SD, 3.7%) and 52.2% (SD, 0.9%) (P < .01) for MC and 46.0% (SD, 2.2%) and 47.2% (SD, 0.4%) for nBCA in the NCG and CG, respectively. Meanwhile, the sFLR% 4 weeks after PVE was 60.5% (SD, 3.9%) and 54.9% (SD, 0.8%) (P < .01) and 60.4% (SD, 3.5%) and 54.2% (SD, 0.95%) (P < .01), respectively. Ki-67 signal intensity increased in the embolized lobe in both CG and NCG (P < .01). CONCLUSIONS: This preclinical study demonstrated that MC could be the preferred embolic of choice compared to nBCA when a substantial and rapid FLR increase is needed for resection, in both cirrhotic and non-cirrhotic livers.

Machine Learning Models for Prediction of Posttreatment Recurrence in Early-Stage Hepatocellular Carcinoma Using Pretreatment Clinical and MRI Features: A Proof-of-Concept Study.

BACKGROUND. Posttreatment recurrence is an unpredictable complication after liver transplant for hepatocellular carcinoma (HCC) that is associated with poor survival. Biomarkers are needed to estimate recurrence risk before organ allocation. OBJECTIVE. This proof-of-concept study evaluated the use of machine learning (ML) to predict recurrence from pretreatment laboratory, clinical, and MRI data in patients with early-stage HCC initially eligible for liver transplant. METHODS. This retrospective study included 120 patients (88 men, 32 women; median age, 60.0 years) with early-stage HCC diagnosed who were initially eligible for liver transplant and underwent treatment by transplant, resection, or thermal ablation between June 2005 and March 2018. Patients underwent pretreatment MRI and posttreatment imaging surveillance. Imaging features were extracted from postcontrast phases of pretreatment MRI examinations using a pretrained convolutional neural network. Pretreatment clinical characteristics (including laboratory data) and extracted imaging features were integrated to develop three ML models (clinical model, imaging model, combined model) for predicting recurrence within six time frames ranging from 1 through 6 years after treatment. Kaplan-Meier analysis with time to recurrence as the endpoint was used to assess the clinical relevance of model predictions. RESULTS. Tumor recurred in 44 of 120 (36.7%) patients during follow-up. The three models predicted recurrence with AUCs across the six time frames of 0.60-0.78 (clinical model), 0.71-0.85 (imaging model), and 0.62-0.86 (combined model). The mean AUC was higher for the imaging model than the clinical model (0.76 vs 0.68, respectively; p = .03), but the mean AUC was not significantly different between the clinical and combined models or between the imaging and combined models (p > .05). Kaplan-Meier curves were significantly different between patients predicted to be at low risk and those predicted to be at high risk by all three models for the 2-, 3-, 4-, 5-, and 6-year time frames (p < .05). CONCLUSION. The findings suggest that ML-based models can predict recurrence before therapy allocation in patients with early-stage HCC initially eligible for liver transplant. Adding MRI data as model input improved predictive performance over clinical parameters alone. The combined model did not surpass the imaging model's performance. CLINICAL IMPACT. ML-based models applied to currently underutilized imaging features may help design more reliable criteria for organ allocation and liver transplant eligibility.