Noninvasive Prediction of Vessels Encapsulating Tumor Clusters in HCC

Overview

This study evaluates the predictive performance of pre-treatment contrast-enhanced MRI radiomics and deep learning models for identifying vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC).

Background

Hepatocellular carcinoma (HCC) is a leading cause of cancer-related mortality globally, with a poor prognosis due to high recurrence rates and aggressive behavior. Vessels encapsulating tumor clusters (VETC) represent a distinct and aggressive subtype of HCC that facilitates metastasis and immune evasion. Accurate noninvasive identification of VETC is crucial.

Data Highlights

Key Findings

• The fusion model integrating ITH and DL features achieved AUCs of 0.901 and 0.870 in training and validation cohorts, respectively.
• Significant differential gene expression was found between high-risk and low-risk groups based on transcriptomic analyses.
• Low-risk group was enriched in pathways related to cell cycle, translation, and mitochondrial function.
• Immune profiling indicated a significant reduction in resting dendritic cells in the high-risk group (P < 0.05).

Clinical Implications

The findings suggest that pre-treatment CEMRI-based models can accurately predict VETC, which may inform surgical and therapeutic strategies. Understanding the immune microenvironment associated with VETC could guide future immunotherapeutic approaches.

Conclusion

The study demonstrates that a CEMRI-based fusion model can effectively predict VETC in HCC. Further validation is necessary to confirm these findings in clinical practice.

Related Resources & Content

1. Frontiers in Oncology, 2026 -- Ultrasound - based deep learning radiomics nomogram for noninvasive prediction of p53 mutation status in hepatocellular carcinoma: a variational autoencoder based development and validation study
2. Frontiers in Oncology, 2026 -- CT-based habitat imaging integrated with radiomics and clinicopathology for noninvasive prediction of microvascular invasion in hepatocellular carcinoma
3. EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma - Journal of Hepatology
4. JCI - Vessels encapsulating tumor clusters promote noninvasive metastasis of hepatocellular carcinoma by shaping an immunosuppressive microenvironment
5. European Radiology — Evaluation of Anti-HER2 Treatment Response for Tailoring Therapy in Early HER2-Positive Breast Cancer Utilizing an Innovative Deep Learning Radiomics Approach
6. npj Digital Medicine — Deep learning model for assessing survival benefits in hepatocellular carcinoma patients undergoing intra-arterial therapies based on proliferative subtype
7. EASL Clinical Practice Guidelines on the management of hepatocellular carcinoma - Journal of Hepatology
8. The 2024 LI-RADS treatment response update: practical reporting after non-radiation and radiation locoregional therapies for hepatocellular carcinoma | Insights into Imaging | Springer Nature Link
9. Hepatocellular carcinoma: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up - PubMed
10. JCI - Vessels encapsulating tumor clusters promote noninvasive metastasis of hepatocellular carcinoma by shaping an immunosuppressive microenvironment
11. Immunological and prognostic significance of vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma
12. Vessels encapsulating tumor clusters in hepatocellular carcinoma: a distinct metastatic pathway with diagnostic and therapeutic significance - PMC
13. Effectiveness of Machine Learning in Detecting Vessels Encapsulating Tumor Clusters in Hepatocellular Carcinoma: Systematic Review and Meta-Analysis - PMC
14. The diagnostic accuracy of imaging methods in preoperative prediction of vessels encapsulating tumor clusters in hepatocellular carcinoma in East Asian populations: a systematic review and meta-analysis - PMC
15. Validation of proposed imaging criteria for estimating vessels encapsulating tumor clusters in hepatocellular carcinoma at CT and gadoxetic acid-enhanced MRI - ScienceDirect
16. Deep Learning Radiopathomics Models Based on Contrast-enhanced MRI and Pathologic Imaging for Predicting Vessels Encapsulating Tumor Clusters and Prognosis in Hepatocellular Carcinoma | Radiology: Imaging Cancer