Radiomics and ischemic stroke research: bibliometric insights and visual trends (2004-2024)

Area of Science:

• Medical Imaging Analysis
• Machine Learning in Medicine
• Neurology and Stroke Research

Background:

• Ischemic stroke poses significant global health challenges in diagnosis, treatment, and prognosis.
• Radiomics, using machine learning for high-dimensional imaging feature extraction, shows promise in ischemic stroke research.
• A systematic bibliometric analysis is needed to synthesize the rapidly growing body of literature on ischemic stroke radiomics.

Purpose of the Study:

• To conduct a visual bibliometric analysis of ischemic stroke radiomics research.
• To map the evolution of research trends and identify emerging hotspots in the field.
• To understand technological advancements and collaborations in ischemic stroke radiomics.

Main Methods:

• Bibliometric and visual analysis of publications from 2004 to 2024.
• Utilized analysis tools such as CiteSpace and VOSviewer.
• Explored publication trends, research hotspots, technological advancements, and collaborations.

Main Results:

• Exponential growth in ischemic stroke radiomics research since 2014, with major contributions from China and the United States.
• Focus on acute ischemic stroke (AIS) using CT and MRI, with widespread application of deep learning models for segmentation and prognosis.
• Identified persistent challenges in standardizing imaging protocols, fostering interdisciplinary collaboration, and clinical translation.

Conclusions:

• Radiomics is revolutionizing ischemic stroke research through detailed imaging analysis and data-driven decision-making.
• Future research should focus on standardization, multicenter collaborations, and integrating radiomics with clinical/molecular biomarkers.
• These efforts will accelerate clinical adoption and improve patient outcomes in ischemic stroke care.