biostudies-literatureUnknown15Fu H<h4>Background</h4>Microvascular invasion (MVI) is a critical determinant of poor prognosis in hepatocellular carcinoma (HCC). Accurate preoperative prediction of MVI is essential for optimizing surgical and therapeutic strategies. This study aims to develop a combined model integrating intratumoral, peritumoral, and clinical features from ultrasound-based radiomics for MVI prediction.<h4>Methods</h4>Ultrasound images of 119 patients with pathologically confirmed HCC were analyzed. A total of 1,414 radiomics features were extracted from intratumoral and peritumoral regions. Feature selection was performed using intraclass correlation coefficient (ICC) analysis, t-tests, and least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, Random Forest, and other macFrontiers in oncology1566105https://www.ebi.ac.uk/biostudies/studies/S-EPMC12433787biostudies-literatureIntegrating intratumoral, peritumoral, and clinical features in an ultrasound-based radiomics model: contributions and synergies for predicting microvascular invasion in hepatocellular carcinoma.PMC12433787Xu LQian HHuang YFu HZhou DHou CYu JLu BfalseIntegrating intratumoral, peritumoral, and clinical features in an ultrasound-based radiomics model: contributions and synergies for predicting microvascular invasion in hepatocellular carcinoma.<h4>Background</h4>Microvascular invasion (MVI) is a critical determinant of poor prognosis in hepatocellular carcinoma (HCC). Accurate preoperative prediction of MVI is essential for optimizing surgical and therapeutic strategies. This study aims to develop a combined model integrating intratumoral, peritumoral, and clinical features from ultrasound-based radiomics for MVI prediction.<h4>Methods</h4>Ultrasound images of 119 patients with pathologically confirmed HCC were analyzed. A total of 1,414 radiomics features were extracted from intratumoral and peritumoral regions. Feature selection was performed using intraclass correlation coefficient (ICC) analysis, t-tests, and least absolute shrinkage and selection operator (LASSO) regression. Logistic regression, Random Forest, and other mac2025-01-01T00:00:00Z20252026-06-01T15:47:22.205Z2026-04-08T13:50:59.714ZS-EPMC124337874095885610.3389/fonc.2025.1566105