CT-Based Habitat Radiomics and Deep Learning for Predicting Early Response and Survival in Unresectable Hepatocellular Carcinoma Treated with Hepatic Arterial Infusion Chemotherapy plus Lenvatinib and Programmed Death Receptor-1 Inhibitors
This study developed and validated a noninvasive, multidimensional fusion model integrating CT-based habitat radiomics, 2.5D deep learning features, and clinical indicators to accurately predict early treatment response and progression-free survival in patients with unresectable hepatocellular carcinoma receiving HAIC-FOLFOX combined with lenvatinib and PD-1 inhibitors.