Current Advances in Classification, Prediction and Management of Microvascular Invasion in Hepatocellular Carcinoma

ABSTRACT Liver resection remains the mainstay curative treatment for hepatocellular carcinoma (HCC); however, the recurrence rate is reported to exceed 70% within 5 years after surgery. Microvascular invasion (MVI) has attracted great research interest in the last decade and has been confirmed to be an independent risk factor for postoperative recurrence and survival. Presently, the diagnosis of MVI depends on pathological specimens, which are not helpful in guiding preoperative planning and intraoperative decision‐making. However, preoperative MVI prediction has developed rapidly with the widespread application of predictive models. Besides the well‐defined clinical predictive factors, radiomics and artificial intelligence (AI)‐based models can provide accurate predictions of MVI. In terms of the specific management of MVI, multiple pre‐ and intraoperative therapeutic choices have shown favourable effects in patients at high risk of MVI indicated by predictive models. Several postoperative adjuvant therapies were also demonstrated to be associated with improved surgical outcomes in patients diagnosed with MVI. Considering that the present perspectives concerning MVI‐related management are still controversial, based on the latest research, the present paper provides updated insights into the 1 ) diagnosis and classification of MVI, 2 ) the predictive factors and models of MVI and 3 ) effective therapeutic choices of MVI in pre‐, intra‐ and postoperative processes. The remaining challenges in the management of MVI are highlighted to stimulate further explorations of the precise and individualised management of MVI.