Tumor Image Segmentation: A Bibliometric Analysis from 2003 to Now

Background: Bibliometrics has been applied to the study of tumor image segmentation, which can indicate the current research hotspots and trends. Method: In this study, bibliometric analyses were performed on data retrieved from the Web of Science database. A total of 3377 articles on the application of tumor image segmentation from January 1, 2003, to October 9, 2024, were analyzed for the characteristics of the articles, including the number of yearly publications, country/region, institution, journal, author, keywords, and references. Visualising co-authorship, co-citation, and co-occurrence analysis with VOSviewer. Results: The annual publication volume of tumor image segmentation literature shows that from the first time of more than 100 articles in 2016, the publication volume of literature in this field has surged, reaching 576 articles by 2023. Mainland China is ranked first in terms of publication volume (n=1356). Saudi Arabia ranks first in average publication year (n=2021.96). IEEE Transactions on Medical Imaging was the journal with the highest average number of citations. The Chinese Academy of Sciences (n=78) was the most prolific institution, while Harvard University was the most prestigious, with a total number of citations and an average number of citations of 3190 and 213, respectively. In terms of keywords, co-occurrence analysis of 107 keywords with a frequency of more than 30 times produced four clusters: (1) methods of image segmentation, (2) applications of image segmentation, (3) image segmentation modelled on CT, (4) image segmentation modelled on MRI. Transformer, Attention Mechanism, and U-Net are the latest keywords. The analysis of keywords helps scholars understand and identify the current research hotspots and research directions. Conclusion: Within the last 20 years, the number of articles on the application of tumor image segmentation has increased steadily. From U-Net to MAMBA, many methods for tumor image segmentation have been proposed, and the limitations of models and algorithms are becoming increasingly smaller, which demonstrates the importance of advances in tumor image segmentation technology for disease prevention and monitoring. It presents a strong connection between countries/regions and authors, which reflects the global interest and support for the development of this field. This study shows global trends, research hotspots, and emerging topics in this field and reviews some of the knowledge about tumor image segmentation applications from past studies. And it will provide good research guidelines for researchers in this field.