Construction and validation of a prediction model of extrahepatic metastasis for hepatocellular carcinoma based on common clinically available data

Radiomics and machine learning based on preoperative MRI for predicting extrahepatic metastasis in hepatocellular carcinoma patients treated with transarterial chemoembolization

Purpose

To develop and validate a radiomics machine learning (Rad-ML) model based on preoperative MRI to predict extrahepatic metastasis (EHM) in hepatocellular carcinoma (HCC) patients receiving transarterial chemoembolization (TACE) treatment.

Methods

A total of 355 HCC patients who received multiple TACE procedures were split at random into a training set and a test set at a 7:3 ratio. Radiomic features were calculated from tumor and peritumor in arterial phase and portal venous phase, and were identified using intraclass correlation coefficient, maximal relevance and minimum redundancy, and least absolute shrinkage and selection operator techniques. Cox regression analysis was employed to determine the clinical model. The best-performing algorithm among eight machine learning methods was used to construct the Rad-ML model. A nomogram combining clinical and Rad-ML parameters was used to develop a combined model. Model performance was evaluated using C-index, decision curve analysis, calibration plot, and survival analysis.

Results

In clinical model, elevated neutrophil to lymphocyte ratio and alpha-fetoprotein were associated with faster EHM. The XGBoost-based Rad-ML model demonstrated the best predictive performance for EHM. When compared to the clinical model, both the Rad-ML model and the combination model performed better (C-indexes of 0.61, 0.85, and 0.86 in the training set, and 0.62, 0.82, and 0.83 in the test set, respectively). However, the combined model's and the Rad-ML model's prediction performance did not differ significantly. The most influential feature was peritumoral waveletHLL_firstorder_Minimum in AP, which exhibited an inverse relationship with EHM risk.

Conclusions

Our study suggests that the preoperative MRI-based Rad-ML model is a valuable tool to predict EHM in HCC patients treated with TACE.

Hepatocellular carcinoma presenting as an extrahepatic mass: A case report and review of literature

BACKGROUND

Hepatocellular carcinoma (HCC) is a primary liver tumor generally diagnosed based on radiographic findings. Metastatic disease is typically associated with increased tumor diameter, multifocality, and vascular invasion. We report a case of a patient who presented with extrahepatic HCC metastasis to a portocaval lymph node with occult hepatic primary on computed tomography (CT). We review the literature for cases of extrahepatic HCC presentation without known hepatic lesions and discuss strategies to differentiate between metastatic and ectopic HCC.

CASE SUMMARY

A 67-year-old male with remotely treated hepatis C was referred for evaluation of an enlarging portocaval, mixed cystic-solid mass. Serial CT evaluations demonstrated steatosis, but no cirrhosis or liver lesions. Endoscopic ultrasound demonstrated a normal-appearing pancreas, biliary tree, and liver. Fine needle aspiration yielded atypical cells. The differential diagnosis included duodenal or pancreatic cyst, lymphoproliferative cyst, stromal or mesenchymal lesions, nodal involvement from gastrointestinal or hematologic malignancy, or duodenal gastro-intestinal stromal tumor. After review by a multidisciplinary tumor board, the patient underwent open surgical resection of a 5.2 cm × 5.5 cm retroperitoneal mass with pathology consistent with moderately-differentiated HCC. Magnetic resonance imaging (MRI) subsequently demonstrated a 1.2 cm segment VIII hepatic lesion with late arterial enhancement, fatty sparing, and intrinsic T1 hyperintensity. Alpha fetoprotein was 23.3 ng/mL. The patient was diagnosed with HCC with portocaval nodal involvement. Review: We surveyed the literature for HCC presenting as extrahepatic masses without history of concurrent or prior intrahepatic HCC. We identified 18 cases of extrahepatic HCC ultimately found to represent metastatic lesions, and 30 cases of extrahepatic HCC found to be primary, ectopic HCC.

CONCLUSION

Hepatocellular carcinoma can seldomly present with extrahepatic metastasis in the setting of occult primary. In patients with risk factors for HCC and lesions suspicious for metastatic disease, MRI may be integral to identifying small hepatic lesions and differentiating from ectopic HCC. Tumor markers may also have utility in establishing the diagnosis.

T-Lymphocyte Gene-Regulated CCL5 and Its Association with Extrahepatic Metastasis in Hepatocellular Carcinoma

BACKGROUND

Extrahepatic metastasis in hepatocellular carcinoma (HCC) greatly limits the prognostic survival of HCC patients. Levels of preoperative peripheral lymphocyte subsets and cytokines in the serum for predicting extrahepatic spread of hepatocellular carcinoma are still not common in clinical practice. The aim of this study is to investigate the value and mechanisms of peripheral lymphocyte subsets and cytokines in predicting extrahepatic spread of HCC.

METHODS

We used a retrospective design to analyze data pertaining to a total of 380 patients with HCC who were examined for peripheral T-lymphocyte subsets before receiving microwave ablation. We performed Cox regression analysis to screen out independent risk factors and used pathology specimens from the patients and public databases of liver cancer to investigate the correlation between cytokines and intra-tumor immune cells.

RESULTS

The CD4low group had better metastasis-free 1-year, 3-year, and 5-year survival rates compared to the CD4high group (80% vs 69%, 67% vs 51%, and 57% vs 39%, respectively; HR 1.7 (1.2, 2.3), P = 0.0019). Similarly, the CD8high group had better metastasis-free 1-year, 3-year, and 5-year survival rates compared to the CD8low group (65% vs 78%, 46% vs 64%, and 34% vs 54%, respectively; HR 0.6 (0.4, 0.8), P < 0.001). Patients with the CD4high/CD8low phenotype had significantly worse metastasis-free survival times compared to other patients (HR 2.0 (1.5, 2.8), P < 0.001). Additionally, T lymphocyte-specific genes (CD4, CD8) were correlated with CCL5 expression, which was also positively correlated with the level of intra-tumoral infiltrating CD8 T cells and the prognosis of HCC patients.

CONCLUSION

Both CD4+ and CD8+ T lymphocyte subsets were independent risk factors for extrahepatic metastasis in HCC. Serum CCL5 levels could indicate the infiltration level of intra-tumoral CD8+ T cells and the risk of extrahepatic metastasis in HCC patients, aiding in patient risk stratification for metastasis.