@article{JMAI11467,
author = {Lian Peng and Xiangkai Zhong and Hui Zeng and Ruxian Zuo},
title = {Research trends and hotspots in the applications of artificial intelligence in CT based on Web of Science—bibliometric research (2015–2024)},
journal = {Journal of Medical Artificial Intelligence},
volume = {9},
number = {0},
year = {2026},
keywords = {},
abstract = {Background: Bibliometrics is a quantitative assessment that uses mathematical and statistical methods to evaluate the contribution of scientific literature. In recent years, the application of artificial intelligence (AI) in medical imaging has received extensive attention, while the research hotspots, patterns and trends have not yet been clarified. Multiple notable knowledge gaps persist within current domain research and existing bibliometric analyses of this field. Most prior bibliometric studies merely outline basic publication trends, national distributions and keyword clusters, without quantitatively dissecting the striking mismatch between massive algorithm outputs and low clinical translation efficiency or thoroughly unpacking its underlying multi-layered drivers. Therefore, we conducted a bibliometric analysis of the literature on the application of AI in computed tomography (CT) based on the Web of Science Core Collection (WoSCC) database over the past 10 years. The results systematically synthesize the comprehensive research landscape of AI-CT, providing clinicians with data-driven insights to prioritize technology adoption and may provide references for further in-depth studies in this field in the future.Methods: In this study, we searched papers related to AI and CT in the Web of Science database by constructing a professional search engine and screened the literature according to the inclusion and exclusion criteria. Then, we conducted bibliometric research and visual analysis from aspects such as the annual publication trend, author collaboration trend, country distribution, institutional collaboration trend, journal distribution, high-frequency keywords, and co-cited literature.Results: We retrieved a total of 6,097 publications from the Web of Science, but only 4,384 were included after screening. Among these 4,384 publications,the number of published papers has been increasing annually. At present, the top five countries by the number of articles published in this field are China, the United States, Italy, South Korea, and India. The institution with the highest number of published papers, total citation frequency, and average citation frequency was Harvard Medical School. The literature cooperation rate has remained above 90% since 2015. It reached as high as 100% in 2016 and 2017. The research involved a total of 1,128 journals. The research hotspots mainly focus on aspects such as “deep learning”, “machine learning”, “classification”, “COVID-19”, and “diagnosis”. The article with the highest citation rate was published by van Griethuysen’s team in Cancer Research (2017).Conclusions: Through bibliometric methods, we reviewed the research on AI in the field of CT over the past decade. The results revealed current hotspots and cutting-edge trends, and provided references for subsequent related research. The study identified gaps in several areas that have not been sufficiently investigated, including algorithm design, clinical translation, data infrastructure, and ethical research. Future research efforts should focus primarily on developing advanced intelligent algorithms, conducting multicenter clinical validation, and improving clinical translation rates.},
issn = {2617-2496}, url = {https://jmai.amegroups.org/article/view/11467}
}