摘要
目的:分析人工智能(AI)在辅助肺结节诊断方面的研究现状、热点及问题,以探究我国在该领域的优势与不足,厘清后续发展思路。方法:以Web of Science核心合集数据库作为数据来源,纳入2003年1月至2023年1月AI辅助肺结节诊断相关文献1 468篇,利用CiteSpace绘制可视化知识图谱,依次分析合作网络、共被引网络和关键词共现。结果:AI辅助肺结节诊断研究存在核心国家、机构;国内已经形成稳定的研究与合作团队,但跨国家的合作明显不足;美国在研究中处于领先、核心地位,中国是后起之秀,韩国是近年的先锋;AI算法导致研究热点的大幅度转移,目前研究重点是利用CT断层扫描和深度学习算法辅助判断肺结节和低密度磨玻璃结节,进行诊断和病因分析。结论:AI辅助肺结节诊断的研究近年飞速发展,需增强各国研究团队的合作。此领域受算法性能影响较大,后继应该继续关注AI等用于计算机辅助诊断的新算法性能的提升。
Purpose:To analyzes the research status,hot spots and problems of artificial intelligence(Al)in assisting the diagnosis of pulmonary nodules,aiming to explore the advantages and shortcomings in this field,and clarify the subsequent development ideas.Method:Based on the Web of Science core collection database,1468 AIassisted pulmonary nodule diagnosis related literature from January 2003 to January 2023 were included,visual knowledge maps was drawn using CiteSpace,and the cooperation network,co-cited network and keyword cooccurrence in turn were analyzed.Result:Core countries and institutions have been discovered.A stable research and cooperation team has been formed in China,but cross-country cooperation is obviously insufficient.In the feild of research on Al-assisted pulmonary nodule diagnosis,the United States is in a leading and core position,China is a rising star,and South Korea is a pioneer in recent years.The upgrading of AI algorithms has led to a large shift in research hotspots,and the current research focus is on the use of CT and deep learning algorithms to assist in the judgment of lung nodules and low-density ground-glass nodules,diagnosis and etiological analysis.Conclusion:The rapid development of Al-assisted lung nodule diagnosis research in recent years requires enhanced cooperation among research teams from various countries.This field is greatly affected by algorithm performance,and we should continue to pay attention to the improvement of the performance of new algorithms for computer-aided diagnosis such as Al.
作者
李艳红
任俊宇
孙希文
黄海量
LI Yanhong;REN Junyu;SUN Xiwen;HUANG Hailiang(Al Lab,School of Information Management and Engineering,Shanghai University of Finance and Economics,Shanghai 200433,China;Department of Radiology,Shanghai Pulmonary Hospital,Tongji University)
出处
《中国医学计算机成像杂志》
CSCD
北大核心
2023年第5期505-510,共6页
Chinese Computed Medical Imaging
基金
国家自然科学基金(72271151)
上海市2021年度“科技创新行动计划”医学创新研究专项项目(21Y11910400)
申康-联影联合科研发展计划(临床研究与转化方向)(SKLY2022CRT202)
上海市肺科医院临床研究重点项目(FK18007)。
