Artificial Intelligence and Radiomics in Primary Liver Cancer Imaging: A Bibliometric and Visualized Analysis.
Ruizhi Fu1,2, Chen Gao1,2, Xinjing Lou1,2
1Department of Radiology, The First Affiliated Hospital of Zhejiang Chinese Medical University (Zhejiang Provincial Hospital of Chinese Medicine), Hangzhou, People's Republic of China.
Journal of Hepatocellular Carcinoma
|April 8, 2026
Summary
Artificial intelligence (AI) and radiomics combined for primary liver cancer (PLC) show growing research interest. Bibliometric analysis reveals China as the leading contributor, with key research hotspots in image reconstruction and deep supervision.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiomics
Background:
- Combining artificial intelligence (AI) with radiomics for primary liver cancer (PLC) enhances diagnostic precision, risk stratification, and personalized treatment.
- This field integrates advanced computational techniques with medical imaging for improved liver cancer management.
- The synergy between AI and radiomics offers novel approaches to understanding and treating liver malignancies.
Purpose of the Study:
- To conduct a bibliometric analysis of research combining AI and radiomics for PLC.
- To explore the current research status, identify key contributors, and pinpoint emerging hotspots in this domain.
- To provide data-driven insights for future research directions in AI-driven liver cancer imaging.
Main Methods:
- Bibliometric analysis of 2890 publications (2008-2025) from Web of Science and Scopus.
- Data analysis and visualization using VOSviewer, CiteSpace, and R software.
- Examination of publication trends, geographic distribution, institutional contributions, journals, authors, and keywords.
Main Results:
- Rapid publication growth observed since 2018, with China as the leading contributor (55.47%).
- Sun Yat-sen University and author Song, Bin identified as most productive.
- Key journals include *Frontiers in Oncology* and *Radiology*; prominent keywords are 'hepatocellular carcinoma', 'deep learning', and 'magnetic resonance imaging'.
Conclusions:
- AI and radiomics applications in liver cancer imaging are gaining significant traction.
- Emerging research hotspots include 'image reconstruction', 'liver cancer classification', and 'deep supervision'.
- Future research will likely focus on improving algorithmic accuracy and predicting clinical outcomes, such as microvascular invasion and treatment response.
