Application of artificial intelligence-based computer vision methods in liver diseases: a bibliometric analysis

Abstract

Medical imaging is essential for the diagnosis and treatment of liver diseases, and the objective analysis of such images is vital for precision medicine. Integration of artificial intelligence (AI), particularly computer vision, into hepatology has seen considerable growth. This study conducts a bibliometric analysis to map the evolution, principal trends, and focal points of AI in liver disease imaging research. We conducted a comprehensive literature review using the Web of Science Core Collection and PubMed databases, spanning January 1990 to July 2023, with keywords related to liver diseases and AI in medical imaging. The search resulted in 3,629 documents, with a surge in publications after 2017. The United States and China led in terms of publication volume, with the former exhibiting higher H-index scores and citation counts. However, greater number of research institutions that contribute significantly to publications in the relevant fields are based in China. Keyword analysis revealed extensive research on liver fibrosis, hepatocellular carcinoma, cirrhosis, and fatty liver disease. Techniques such as image segmentation, classification, and registration are prevalent, meeting clinical needs like lesion detection and disease prognosis. Convolutional neural networks (CNNs), particularly U-Net models, are predominantly utilized. This review synthesizes the findings to guide future advancements in AI-assisted liver disease diagnosis and management.

Ähnliche Arbeiten