Prognostic Nomogram for Sorafenib Benefit in Hepatitis B Virus-Related Hepatocellular Carcinoma After Partial Hepatectomy

Noninvasive identification of SOX9 status using radiomics signatures may help construct personalized treatment strategy in hepatocellular carcinoma

OBJECTIVES

To develop and validate a radiomics-based model for predicting SOX9-positive hepatocellular carcinoma (HCC) using preoperative contrast-enhanced computed tomography (CT) images.

METHODS

From January 2013 to April 2017, patients with histologically proven HCC who received systemic sorafenib treatment after curative resection were retrospectively enrolled. Radiomic features were extracted from portal venous phase CT images and selected to build a radiomics score using logistic regression analysis. The factors associated with SOX9 expression were selected and combined by univariate and multivariate analyses to establish clinico-liver imaging (CL) model and clinico-liver imaging-radiomics (CLR) model. Diagnostic performance was measured by area under curve (AUC). Overall survival (OS) and recurrence-free survival (RFS) rates were compared using Kaplan-Meier method.

RESULTS

A total of 108 patients (training cohort: n = 80; validation cohort: n = 28) were enrolled. Multivariate analyses revealed that the albumin-bilirubin grade and tumor size were significant independent factors for predicting SOX9-positive HCCs and were included in the CL model. The CLR model integrating the radiomics score with albumin-bilirubin grade and tumor size showed better discriminative performance than the CL model with AUCs of 0.912 and 0.790 in the training and validation cohorts. Survival curves for RFS and OS showed that SOX9 expression was closely related to the prognosis of HCC patients. RFS and OS rates were significantly lower in patients with SOX9-positive than SOX9-negative (51.02% vs. 75.00% at 1-year RFS rates; 76.92% vs. 94.94% at 2-year OS rates).

CONCLUSION

Radiomics signatures may serve as noninvasive predictors for SOX9 status evaluation in patients with HCC and may aid in constructing individualized treatment strategies.

ACTB may serve as a predictive marker for the efficacy of lenvatinib in patients with HBV-related early-stage hepatocellular carcinoma following partial hepatectomy: a retrospective cohort study

Background

The lack of effective biomarkers for the treatment of postoperative recurrence in hepatocellular carcinoma (HCC) persists despite lenvatinib therapy. This study aims to identify beta-actin (ACTB) as a predictive biomarker for lenvatinib that can facilitate individualized treatment for HCC.

Methods

This retrospective study included a subset of patients with HCC who underwent partial hepatectomy, with some receiving postoperative lenvatinib treatment and others not receiving lenvatinib treatment. A propensity score matching (PSM) analysis of patients who underwent treatment with or without lenvatinib following HCC partial hepatectomy was performed. Immunohistochemistry was employed to determine the levels of ACTB expression in HCC samples obtained from matched patients (n=225) enrolled in this study. The X-Tile was employed to determine the optimal cut-off point of ACTB levels for predicting time to recurrence (TTR). To assess the correlation between ACTB levels and lenvatinib efficacy, a subgroup analysis of TTR was conducted. A Cox regression model with an interaction term was utilized to assess the predictive significance of the model. Subsequently, a nomogram was developed and its discriminative ability and predictive accuracy were assessed using the concordance index (C-index) and calibration curve. For the investigation of the ACTB expression, HCC and para-tumoral normal tissues were employed. The patient-derived xenograft (PDX) model was utilized to validate the correlation between ACTB levels and lenvatinib responsiveness.

Results

After PSM, a total of 76 patients who underwent postoperative lenvatinib treatment were included in the analysis, with a median TTR of 24.35 months. Early-stage HCC patients with lower levels of ACTB exhibited a more favorable response to lenvatinib therapy compared to those with higher levels. The reduced expression of ACTB was indicative of the benefits of lenvatinib, as opposed to higher levels {hazard ratio (HR) =0.243 [95% confidence interval (CI): 0.096-0.619], P<0.001, P value for interaction =0.014}. In approximately 81.8% of cases involving HCC patients, there was an observed increase in the expression of ACTB. Multivariate analysis of the lenvatinib cohort revealed Child-Pugh [HR =5.416 (95% CI: 1.390-21.104), P=0.015], Barcelona Clinic Liver Cancer (BCLC) stage [HR =2.508 (95% CI: 1.116-5.639), P=0.026], and ACTB [HR =5.879 (95% CI: 2.424-14.259), P<0.001] score as independent factors for TTR, and all were included in the nomogram. The survival probability based on the calibration curve showed that the prediction of the nomogram was in good agreement with the actual observation. The C-index of the nomogram for predicting survival was 0.76 (95% CI: 0.71-0.84). Moreover, the PDXs derived from tumors exhibiting low levels of ACTB expression demonstrated a heightened sensitivity to lenvatinib treatment.

Conclusions

In patients with tumors treated with lenvatinib, low ACTB expression can predict a lower risk of recurrence. The validation of this potential biomarker in independent cohorts is necessary prior to its implementation for precision treatment stratification in patients undergoing partial hepatectomy for early-stage HCC.

A Promising Preoperative Prediction Model for Microvascular Invasion in Hepatocellular Carcinoma Based on an Extreme Gradient Boosting Algorithm

Background

The non-invasive preoperative diagnosis of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is vital for precise surgical decision-making and patient prognosis. Herein, we aimed to develop an MVI prediction model with valid performance and clinical interpretability.

Methods

A total of 2160 patients with HCC without macroscopic invasion who underwent hepatectomy for the first time in West China Hospital from January 2015 to June 2019 were retrospectively included, and randomly divided into training and a validation cohort at a ratio of 8:2. Preoperative demographic features, imaging characteristics, and laboratory indexes of the patients were collected. Five machine learning algorithms were used: logistic regression, random forest, support vector machine, extreme gradient boosting (XGBoost), and multilayer perception. Performance was evaluated using the area under the receiver operating characteristic curve (AUC). We also determined the Shapley Additive exPlanation value to explain the influence of each feature on the MVI prediction model.

Results

The top six important preoperative factors associated with MVI were the maximum image diameter, protein induced by vitamin K absence or antagonist-II, α-fetoprotein level, satellite nodules, alanine aminotransferase (AST)/aspartate aminotransferase (ALT) ratio, and AST level, according to the XGBoost model. The XGBoost model for preoperative prediction of MVI exhibited a better AUC (0.8, 95% confidence interval: 0.74–0.83) than the other prediction models. Furthermore, to facilitate use of the model in clinical settings, we developed a user-friendly online calculator for MVI risk prediction based on the XGBoost model.

Conclusions

The XGBoost model achieved outstanding performance for non-invasive preoperative prediction of MVI based on big data. Moreover, the MVI risk calculator would assist clinicians in conveniently determining the optimal therapeutic remedy and ameliorating the prognosis of patients with HCC.