Development and validation of MRI-based model for the preoperative prediction of macrotrabecular hepatocellular carcinoma subtype

Diagnostic accuracy of preoperative MRI in assessing macrotrabecular-massive subtype of hepatocellular carcinoma: a systematic review and meta-analysis

OBJECTIVES

To determine the value of preoperative magnetic resonance imaging (MRI) in predicting macrotrabecular-massive hepatocellular carcinoma (MTM-HCC).

MATERIALS AND METHODS

A search was conducted on PubMed, Web of Science, Cochrane Library databases, and Embase for studies evaluating the performance of MRI in assessing MTM-HCC. The quality assessment of diagnostic studies (QUADAS-2) tool was used to assess the risk of bias. Diagnostic accuracy measures, including sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic odds ratio (DOR), were pooled. Summary receiver operating characteristic (SROC) curves with the area under the curve (AUC) were generated. Meta-regression analysis was performed to explore potential sources of heterogeneity.

RESULTS

A total of ten eligible studies including 2074 lesions in 2053 patients were analyzed. The pooled sensitivity, specificity, PLR, NLR, DOR, and AUC were 0.65 (0.52, 0.76), 0.88 (0.80, 0.94), 5.6 (3.70, 8.60), 0.40 (0.30, 0.53), 14 (10, 20), and 0.84 (0.81, 0.87), respectively. High heterogeneity was observed (I2 was 78.61% and 90.95% for sensitivity and specificity, respectively) along with a threshold effect (Spearman's correlation coefficient = 0.927, p < 0.001). Meta-regression analysis demonstrated that the MRI method (radiomics or non-radiomics) affected the heterogeneity.

CONCLUSION

MRI has diagnostic value for MTM-HCC due to its higher specificity and moderate sensitivity, but its clinical application remains suboptimal due to significant heterogeneity. Thus, further prospective studies with large sample sizes are needed to confirm these results.

KEY POINTS

Question What is the value of MRI for preoperatively predicting MTM-HCC? Findings Meta-regression analyses revealed that the MRI method (radiomics or non-radiomics) is a significant factor contributing to heterogeneity. Clinical relevance This study demonstrates the high diagnostic accuracy of MRI for early detection of MTM-HCC, which can assist in guiding individualized management.

Diagnostic Values of Magnetic Resonance Imaging and Computed Tomography for Predicting Macrotrabecular-Massive Hepatocellular Carcinoma Subtype: A Meta-analysis

BACKGROUND

The diagnostic accuracy of magn\etic resonance imaging (MRI) vs. computed tomography (CT) for predicting macrotrabecular-massive hepatocellular carcinoma (MTM-HCC) is yet to be ascertained. Therefore, this meta-analysis aimed to summarise the diagnostic accuracies of MRI and CT for MTM-HCC.

METHODS

A comprehensive literature search of PubMed and Embase was conducted up to 20 August 2024, to evaluate the diagnostic performance of MRI and CT for the diagnosis of MTM-HCC. Pooled sensitivity and specificity were calculated for MRI and CT using a bivariate random-effects model. Subgroup analyses based on different covariates were conducted to compare the diagnostic performances of MRI and CT.

RESULTS

15 studies involving 2299 patients, including 706 with MTM-HCC and 1593 with non-MTM-HCC were analysed. Comparative analysis revealed no significant differences between MRI and CT in pooled sensitivity (66% vs. 82%, respectively) and specificity (88% vs. 79%, respectively) for the diagnosis of MTM-HCC (P=0.53), with comparable areas under the summary receiver operating characteristic curves of 0.87 and 0.86, respectively. In the subgroup analysis of imaging methods within radiomics, CT had significantly higher sensitivity and specificity than MRI (98% vs. 85% [sensitivity], 83% vs. 79% [specificity], P=0.01). In the other subgroups, including age, the most common aetiology of liver disease, the proportion of patients with cirrhosis, and tumour size, there were no significant differences (all P>0.05).

CONCLUSION

CT and MRI had comparable predictive performances for the non-invasive diagnosis of MTM-HCC. In the subgroup of radiomics-based imaging methods, CT outperformed MRI. Nevertheless, multicenter prospective studies with uniform design are needed to confirm these findings.

Transfer learning radiomic model predicts intratumoral tertiary lymphoid structures in hepatocellular carcinoma: a multicenter study

BACKGROUND

Intratumoral tertiary lymphoid structures (iTLS) in hepatocellular carcinoma (HCC) are associated with improved survival and may influence treatment decisions. However, their non-invasive detection remains challenging in HCC. We aim to develop a non-invasive model using baseline contrast-enhanced MRI to predict the iTLS status.

METHODS

A total of 660 patients with HCC who underwent surgery were retrospectively recruited from four centers between October 2015 and January 2023 and divided into training, internal test, and external validation sets. After features dimensionality and selection, corresponding features were used to construct transfer learning radiomic (TLR) models for diagnosing iTLS, and model interpretability was explored with pathway analysis in The Cancer Genome Atlas-Liver HCC. The performances of models were assessed using the area under the receiver operating characteristic curve (AUC). The log-rank test was used to evaluate the prognostic value of the TLR model. The combination therapy set of 101 patients with advanced HCC treated with first-line anti-programmed death 1 or ligand 1 plus antiangiogenic treatment between January 2021 and January 2024 was used to investigate the value of the TLR model for evaluating the treatment response.

RESULTS

The presence of iTLS was identified in 46.0% (n=308) patients. The TLR model demonstrated excellent performance in predicting the presence of iTLS in training (AUC=0.91, 95% CI: 0.87, 0.94), internal test (AUC=0.85, 95% CI: 0.77, 0.93) and external validation set (AUC=0.85, 95% CI: 0.81, 0.90). The TLR model-predicted iTLS group has favorable overall survival (HR=0.66; 95% CI: 0.48, 0.90; p=0.007) and relapse-free survival (HR=0.64; 95% CI: 0.48, 0.85; p=0.001) in the external validation set. The model-predicted iTLS status was associated with inflammatory response and specific tumor-associated signaling activation (all p<0.001). The proportion of treatment responders was significantly higher in the model-predicted group with iTLS than in the group without iTLS (36% vs 13.73%, p=0.009).

CONCLUSION

The TLR model has indicated accurate prediction of iTLS status, which may assist in the risk stratification for patients with HCC in clinical practice.

MRI imaging features for predicting macrotrabecular-massive subtype hepatocellular carcinoma: a systematic review and meta-analysis

PURPOSE

To identify significant MRI features associated with macrotrabecular-massive hepatocellular carcinoma (MTM-HCC), and to assess the distribution of Liver Imaging Radiology and Data System (LI-RADS, LR) category assignments.

METHODS

PubMed and EMBASE were searched up to March 28, 2023. Random-effects model was constructed to calculate pooled diagnostic odds ratios (DORs) and 95% confidence intervals (CIs) for each MRI feature for differentiating MTM-HCC from NMTM-HCC. The pooled proportions of LI-RADS category assignments in MTM-HCC and NMTM-HCC were compared using z-test.

RESULTS

Ten studies included 1978 patients with 2031 HCCs (426 (20.9%) MTM-HCC and 1605 (79.1%) NMTM-HCC). Six MRI features showed significant association with MTM-HCC: tumor in vein (TIV) (DOR = 2.4 [95% CI, 1.6-3.5]), rim arterial phase hyperenhancement (DOR =2.6 [95% CI, 1.4-5.0]), corona enhancement (DOR = 2.6 [95% CI, 1.4-4.5]), intratumoral arteries (DOR = 2.6 [95% CI, 1.1-6.3]), peritumoral hypointensity on hepatobiliary phase (DOR = 2.2 [95% CI, 1.5-3.3]), and necrosis (DOR = 4.2 [95% CI, 2.0-8.5]). The pooled proportions of LI-RADS categories in MTM-HCC were LR-3, 0% [95% CI, 0-2%]; LR-4, 11% [95% CI, 6-16%]; LR-5, 63% [95% CI, 55-71%]; LR-M, 12% [95% CI, 6-19%]; and LR-TIV, 13% [95% CI, 6-22%]. In NMTM-HCC, the pooled proportions of LI-RADS categories were LR-3, 1% [95% CI, 0-2%]; LR-4, 8% [95% CI, 3-15%]; LR-5, 77% [95% CI, 71-82%]; LR-M, 5% [95% CI, 3-7%]; and LR-TIV, 6% [95% CI, 2-11%]. MTM-HCC had significantly lower proportion of LR-5 and higher proportion of LR-M and LR-TIV categories.

CONCLUSIONS

Six MRI features showed significant association with MTM-HCC. Additionally, compared to NMTM-HCC, MTM-HCC are more likely to be categorized LR-M and LR-TIV and less likely to be categorized LR-5.

CLINICAL RELEVANCE STATEMENT

Several MR imaging features can suggest macrotrabecular-massive hepatocellular carcinoma subtype, which can assist in guiding treatment plans and identifying potential candidates for clinical trials of new treatment strategies.

KEY POINTS

• Macrotrabecular-massive hepatocellular carcinoma is a subtype of HCC characterized by its aggressive nature and unfavorable prognosis. • Tumor in vein, rim arterial phase hyperenhancement, corona enhancement, intratumoral arteries, peritumoral hypointensity on hepatobiliary phase, and necrosis on MRI are indicative of macrotrabecular-massive hepatocellular carcinoma. • Various MRI characteristics can be utilized for the diagnosis of the macrotrabecular-massive hepatocellular carcinoma subtype. This can prove beneficial in guiding treatment decisions and identifying potential candidates for clinical trials involving novel treatment approaches.

Prediction of macrotrabecular-massive hepatocellular carcinoma by using MR-based models and their prognostic implications

PURPOSE

To evaluate the efficacy of MRI-based radiomics and clinical models in predicting MTM-HCC. Additionally, to investigate the ability of the radiomics model designed for MTM-HCC identification in predicting disease-free survival (DFS) in patients with HCC.

METHODS

A total of 336 patients who underwent oncological resection for HCC between June 2007 and March 2021 were included. 127 patients in Cohort1 were used for MTM-HCC identification, and 209 patients in Cohort2 for prognostic analyses. Radiomics analysis was performed using volumes of interest of HCC delineated on pre-operative MRI images. Radiomics and clinical models were developed using Random Forest algorithm in Cohort1 and a radiomics probability (RP) of MTM-HCC was obtained from the radiomics model. Based on the RP, patients in Cohort2 were divided into a RAD-MTM-HCC (RAD-M) group and a RAD-non-MTM-HCC (RAD-nM) group. Univariate and multivariate Cox regression analyses were employed to identify the independent predictors for DFS of patients in Cohort2. Kaplan-Meier curves were used to compare the DFS between different groups pf patients based on the predictors.

RESULTS

The radiomics model for identifying MTM-HCC showed AUCs of 0.916 (95% CI: 0.858-0.960) and 0.833 (95% CI: 0.675-0.935), and the clinical model showed AUCs of 0.760 (95% CI: 0.669-0.836) and 0.704 (95% CI: 0.532-0.843) in the respective training and validation sets. Furthermore, the radiomics biomarker RP, portal or hepatic vein tumor thrombus, irregular rim-like arterial phase hyperenhancement (IRE) and AFP were independent predictors of DFS in patients with HCC. The DFS of RAD-nM group was significantly higher than that of the RAD-M group (p < .001).

CONCLUSION

MR-based clinical and radiomic models have the potential to accurately diagnose MTM-HCC. Moreover, the radiomics signature designed to identify MTM-HCC also can be used to predict prognosis in patients with HCC, realizing the diagnostic and prognostic aims at the same time.