Related Experiment Video
Updated: Feb 21, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
The Current Research Landscape on Integrating Artificial Intelligence with Ultrasound Imaging for Cancer Diagnosis: A
Xiaolei Miao1, Jinxu Wang1, Halisa Paerhati2
1Department of Anesthesiology, Beijing Chao-Yang Hospital, Capital Medical University, Beijing 100020, China.
Introduction:
Early cancer detection is crucial for improving outcomes. Ultrasound (US) imaging is widely accessible and cost-effective but limited by operator dependency and modest tissue contrast. Over the past decade, Artificial Intelligence (AI) has been increasingly utilized to enhance ultrasound-based cancer diagnosis, yet a comprehensive overview of this research landscape remains lacking.
Methods:
We conducted a dual-database bibliometric analysis of literature from the Web of Science Core Collection and Scopus database covering 2015 to April 2025, using R software, VOSviewer, and CiteSpace.
Results:
The field has grown rapidly since 2020, with 1,848 publications identified in the Web of Science dataset. China led in publication volume (n = 869) and showed the broadest international collaboration network, followed by the USA (n = 187), India (n = 113), Korea (n = 97), and Japan (n = 64). Frontiers in Oncology, Diagnostics, and Cancers were the most productive journals, while Radiology achieved the highest citation impact. Keyword co-occurrence and citation burst analyses revealed three major research hotspots. Firstly, designing deep learning-based computer-aided diagnosis models for automated cancer detection, segmentation, and classification. Secondly, embedding AI into clinical workflows to improve diagnostic accuracy and efficiency. Thirdly, developing multimodal fusion strategies to enhance diagnosis and guide prognosis and therapy.
Discussion:
Integrating AI with US imaging shows strong potential to enhance cancer diagnosis. From algorithm refinement to clinical implementation and multimodal radiomics, AI-assisted US imaging may significantly impact cancer care.
Conclusion:
Future work should emphasize large, diverse datasets, multimodal integration, transparent algorithms, and prospective validation to ensure measurable patient benefits.
