Emerging Trends and Research Foci of Deep Learning in Spine: Bibliometric and Visualization Study

Abstract

Abstract As the cognition of spine develops, deep learning (DL) presents a tremendous potential and function as an advantageous tool in this field. In this study, bibliometrics and visual methods were adopted with a retrieval of Web of Science to provide a comprehensive overview of DL-spine research. VOSviewer and Citespace were primarily used for literature measurement and knowledge graph analysis. A total of 273 studies was retrieved focusing on DL in spine with a sum of 2407 citations, and the global total number of articles published showed a continuous increasing trend. China was the country with the largest number of publications, while USA was the country with the most citation. The top 2 journals were “European spine journal” and “Medical image analysis”, and the most involved research area was Radiology Nuclear Medicine Medical Imaging. VOSviewer visually presented three clusters into “segmentation”, “area”, and “neural network”. And CiteSpace indicated the keywords with the longest use were “magnetic resonance image” and “lumbar”, while “agreement” and “automated detection” were the most popular keywords. The stage of DL-spine research is still in its infancy and its future is bright. Intercontinental cooperation, extensive application and more interpretable algorithms will exert more vitality in this field.