Hepatocellular carcinoma is the sixth most common malignancy worldwide and the third leading cause of cancer-related death. Conventional imaging is limited in tumor differentiation, microvascular invasion, molecular biomarkers, and therapeutic efficacy prediction. In recent years, radiomics and deep learning have been increasingly applied in the diagnosis and treatment of hepatocellular carcinoma, showing notable progress in multiple aspects. These approaches can provide valuable support for clinical decision-making and potentially improve patient prognosis. This review summarizes the current progress, challenges, and future directions of radiomics in hepatocellular carcinoma diagnosis and treatment.