Application of artificial intelligence in the diagnosis of hepatocellular carcinoma

Abstract

Hepatocellular carcinoma (HCC) is a major cause of cancer-related deaths worldwide. This review explores the recent progress in the application of artificial intelligence (AI) in radiological diagnosis of HCC. The Barcelona Classification of Liver Cancer criteria guides treatment decisions based on tumour characteristics and liver function indicators, but HCC often remains undetected until intermediate or advanced stages, limiting treatment options and patient outcomes. Timely and accurate diagnostic methods are crucial for enabling curative therapies and improving patient outcomes. AI, particularly deep learning and neural network models, has shown promise in the radiological detection of HCC. AI offers several advantages in HCC diagnosis, including reducing diagnostic variability, optimising data analysis and reallocating healthcare resources. By providing objective and consistent analysis of imaging data, AI can overcome the limitations of human interpretation and enhance the accuracy of HCC diagnosis. Furthermore, AI systems can assist healthcare professionals in managing the increasing workload by serving as a reliable diagnostic tool. Integration of AI with information systems enables comprehensive analysis of patient data, facilitating more informed and reliable diagnoses. The advancements in AI-based radiological diagnosis hold significant potential to improve early detection, treatment selection and patient outcomes in HCC. Further research and clinical implementation of AI models in routine practice are necessary to harness the full potential of this technology in HCC management.