What question did this study set out to answer?

To create a stacking model that combines intratumoral and peritumoral CT radiomics with serum biomarkers for predicting microvascular invasion in HCC.

March 28, 2026Open Access

Interpretable stacking model integrating intra-/peritumoral CT-radiomics and serum biomarkers for predicting microvascular invasion in HCC: a dual-center retrospective study

Key Points

To create a stacking model that combines intratumoral and peritumoral CT radiomics with serum biomarkers for predicting microvascular invasion in HCC.
Retrospective analysis of 219 HCC patients from two centers.
Radiomics features extracted from CT images of tumors and surrounding areas.
Development of models using four machine learning classifiers with a focus on stacking methods.
Model evaluation performed using AUC, CI, and DCA.
SLMXG model achieved an AUC of 0.9577 in the training set.
Validation sets showed AUCs of 0.8611 and 0.8629 respectively.
External validation indicated an accuracy of 0.8088 and precision of 0.8529.
Correlation analyses confirmed significant agreements among radiomics scores and serum biomarkers.

Abstract

To establish an interpretable stacking model integrating intratumoral and peritumoral multi-phase CT radiomics with serum biomarkers for predicting microvascular invasion (MVI) in hepatocellular carcinoma (HCC). We retrospectively analyzed 219 HCC patients. 151 HCC patients from Center 1 were randomly divided into a training set (N = 105) and a test set (N = 46). 68 HCC patients from Center 2 were classified as an external validation set. Radiomics features were extracted from primary lesion and its surrounding 5 mm region on enhanced CT, and the total Stacking radiomics score (TOTALSRads) was constructed. The nutritional immune inflammation score (NIIs) was derived from serum biomarkers. Four machine learning classifiers were employed to develop models, and the optimal model (SLMXG) was integrated using several different fusion strategies. The model’s evaluation used the area under the curve (AUC), confidence interval (CI), and decision curve analysis (DCA). Model interpretability was assessed using SHAP analysis and correlation analyses. SLMXG achieved the best AUC of 0. 9577 in the training set, and was well verified in test set (AUC: 0. 861195%CI 0. 7493–0. 9729) and external validation set (AUC: 0. 862995%CI 0. 7730–0. 9528) with good calibration. In external validation set, SLMXG exhibited an accuracy of 0. 8088, precision of 0. 8529, F1 score of 0. 8169, and Brier score of 0. 1545, showing favorable clinical net benefit with a threshold probability range of 20%‒85%. Correlation analyses indicated good agreement among intratumoral and peritumoral radiomics, TOTALSRads, and NIIs (P < 0. 001). SHAP analyses highlighted that peritumoral radiomics and serum biomarkers contributed powerful enhancing roles for SLMXG, with Venousₚhaseᵢntra-peritumoral 0. 5 cm radiomics and Xgboost contributing the most. The SLMXG, which integrates different learning fusion strategies with serum biomarkers and intratumoral and peritumoral multi-phase CT radiomics, highlights good discriminative performance for predicting MVI in HCC, and may promote individualized therapeutic planning.

AI से पूछें

Bookmark

View Full Paper