Liver cancer is one of the most threatening diseases to the human body, and most patients are already in the advanced stage at the time of diagnosis, resulting in an extremely high mortality rate. The diagnosis and treatment of early-stage liver cancer is the key to improving the prognosis of patients. Medical imaging is an important method that assists in the diagnosis of liver cancer, and currently, intelligent image recognition technology based on medical imaging data has been widely applied in the field of medical diagnosis and has good application prospects. This article reviews the current status of research on artificial intelligence (AI) methods for the diagnosis of focal liver lesions based on liver medical images and proposes the advantages and shortcomings of current AI diagnosis, so as to provide new research ideas for the intelligent diagnosis of liver cancer in the future.