Large Language Models for Preoperative Microvascular Invasion Prediction in Hepatocellular Carcinoma: A Multicenter Comparison with Radiologists and Treatment Outcomes

Background

Preoperative prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC) is critical for prognosis but challenging. This study evaluated the performance of large language models (LLMs) for MVI prediction compared with radiologists with varying levels of experience and explored the association of model-predicted MVI with recurrence and treatment outcomes.