Background: Radiogenomics has emerged as a field that links medical imaging (radiomics) with molecular pathology (genomics), including proteomics and metabolomics. It utilizes radiomics to improve disease diagnosis, predict prognosis, evaluate treatment efficacy, and analyze outcomes. This study aims to examine the current research status and highlight the dynamic changes in hotspots within radiogenomics research.Objective: Radiogenomics has emerged as a field that links medical imaging (radiomics) with molecular pathology (genomics), including proteomics and metabolomics. It utilizes radiomics to improve disease diagnosis, predict prognosis, evaluate treatment efficacy, and analyze outcomes. This study aims to examine the current research status and highlight the dynamic changes in hotspots within radiogenomics research.Methods: Visual software Vosviewer and Citespace were employed to analyze the data in this study. Vosviewer was used to assess the frequency of keywords, while Citespace was utilized to analyze countries, institutions, journals, co-citations, reference clusters, timeline views, and keyword bursts. The number of published documents was counted using Excel.
Results:The United States and China are the leading contributors to this field, with the largest number of co-citations and published articles, respectively. The co-occurrence map of keywords indicates a recent prevalence of machine learning, deep learning, and artificial intelligence. The reference co-citations resulted in 11 clusters, including radiomics, glioma, breast cancer, EGFR, radiotherapy, normal tissue toxicity, glioblastoma, rectal cancer, immunotherapy, oncologic imaging, and deep learning.
Conclusions:The United States and China are the leading contributors to this field, with the largest number of co-citations and published articles, respectively. The co-occurrence map of keywords indicates a recent prevalence of machine learning, deep learning, and artificial intelligence. The reference co-citations resulted in 11 clusters, including radiomics, glioma, breast cancer, EGFR, radiotherapy, normal tissue toxicity, glioblastoma, rectal cancer, immunotherapy, oncologic imaging, and deep learning.