Search

Objective: We present a new artificial intelligence-powered method to predict 3-year hepatocellular carcinoma (HCC) recurrence by analysing the radiomic profile of contrast-enhanced CT (CECT) images that was validated in patient cohorts., Methods: This retrospective cohort study of 224 HCC patients with follow-up for at least 3 years was performed at a single centre from 2012 to 2019. Two groups of radiomic signatures were extracted from the arterial and portal venous phases of pre-operative CECT. Then, the radiological model (RM), deep learning-based radiomics model (DLRM), and clinical & deep learning-based radiomics model (CDLRM) were established and validated in the area under curve (AUC), calibration curve, and clinical decision curve., Results: Comparison of the clinical baseline variables between the non-recurrence ( n = 109) and recurrence group ( n = 115), three clinical independent factors (Barcelona Clinic Liver Cancer staging, microvascular invasion, and α-fetoprotein) were incorporated into DLRM for the CDLRM construction. Among the 30 radiomic features most crucial to the 3 year recurrence rate, the selection from deep learning-based radiomics (DLR) features depends on CECT. through the Gini index. In most cases, CDLRM has shown superior accuracy and distinguished performance than DLRM and RM, with the 0.98 AUC in the training cohorts and 0.83 in the testing., Conclusion: This study proposed that DLR-based CDLRM construction would be allowed for the predictive utility of 3-year recurrence outcomes of HCCs, providing high-risk patients with an effective and non-invasive method to possess extra clinical intervention., Advances in Knowledge: This study has highlighted the predictive value of DLR in the 3-year recurrence rate of HCC.

Hepatocellular carcinoma (HCC) is the most common gastrointestinal tumor with a poor prognosis, which is associated with poor differentiation of tumor cells. However, the potential value of cell differentiation-related molecules in predicting the benefit and prognosis of immune checkpoint inhibitors (ICI) therapy remains unknown. Herein, to investigate the differentiation trajectory of HCC cells and their clinical significance, a differentiation-related gene prognostic index (DRGPI) based on HCC differentiation-related genes (HDRGs) was constructed to elucidate the immune characteristics and therapeutic benefits of ICI in the HCC subgroup defined by DRGPI. Single-cell RNA sequencing (scRNA-seq) and bulk RNA-seq data from four HCC samples were integrated for bioinformatics analysis. Then, PON1, ADH4, SQSTM1, HSP90AA1, and STMN1 were screened out to construct a DRGPI. More intriguingly, RT-qPCR validation of the expression of these genes yielded consistent results with the TCGA database. Next, the risk scoring (RS) constructed based on DRGPI suggested that the overall survival (OS) of the DRGPI-high patients was significantly worse than that of the DRGPI-low patients. A nomogram was constructed based on DRGPI-RS and clinical characteristics, which showed strong predictive performance and high accuracy. The comprehensive results indicated that a low DRGPI score was associated with low TP53 mutation rates, high CD8 T cell infiltration, and more benefit from ICI therapy. Homoplastically, the high DRGPI score reflected the opposite results. Taken together, our study highlights the significance of HCC cell differentiation in predicting prognosis, indicating immune characteristics, and understanding the therapeutic benefits of ICI, and suggests that DRGPI is a valuable prognostic biomarker for HCC.

GTSE1 is well correlated with tumor progression; however, little is known regarding its role in liver cancer prognosis. By analyzing the hepatocellular carcinoma (HCC) datasets in GEO and TCGA databases, we showed that high expression of GTSE1 was correlated with advanced pathologic stage and poor prognosis of HCC patients. To investigate underlying molecular mechanism, we generated GTSE1 knockdown HCC cell line and explored the effects of GTSE1 deficiency in cell growth. Between GTSE1 knockdown and wild-type HCC cells, we identified 979 differentially expressed genes (520 downregulated and 459 upregulated genes) in the analysis of microarray-based gene expression profiling. Functional enrichment analysis of DEGs suggested that S phase was dysregulated without GTSE1 expression, which was further verified from flow cytometry analysis. Moreover, three other DEGs: CDC20, PCNA, and MCM6, were also found contributing to GTSE1-related cell cycle arrest and to be associated with poor overall survival of HCC patients. In conclusion, GTSE1, together with CDC20, PCNA, and MCM6, may synergistically promote adverse prognosis in HCC by activating cell cycle. Genes like GTSE1, CDC20, PCNA, and MCM6 may be promising prognostic molecular biomarkers in liver cancer., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2019 Yongchang Zheng et al.)