Current Issue Cover
  • 发布时间:
  • 摘要点击次数:
  • 全文下载次数:
  • DOI:
  • 2022 | Volume  | Number 3

()

摘 要
在过去20年里,医学影像技术、人工智能技术以及这两项技术相结合的临床应用都取得了长足发展。中国在该领域的研究也取得卓越成就,并且在全世界范围内的贡献比例仍在逐步提高。为了记录和总结国内同行的科研成果,本文对中国医学影像人工智能过去20年的发展历程进行回顾和展望。重点分析了国内同行在公认的医学影像人工智能领域的国际顶级刊物Medical Image Analysis(MedIA)和IEEE Transactions on Medical Imaging(TMI)以及顶级会议Medical Image Computing and Computer Assisted Intervention(MICCAI)发表的论文,定量统计了论文发表数量、作者身份、发表单位、作者合作链、关键词、被引次数等信息。同时总结了近20年中国医学影像人工智能发展进程中的重要事件,包括举办的医学影像人工智能知名国际和国内会议、《中国医学影像AI白皮书》的发布以及国内同行在COVID-19期间的贡献,最后展望了中国医学影像人工智能领域未来的发展趋势。上述统计结果系统性地反映了在过去20年里中国在医学影像人工智能领域所取得的突出成绩。许多研究论文的作者将数据和源代码公开给全世界共享,为全世界医学影像人工智能的科研和教学做出了杰出贡献。通过本文中国医学影像人工智能领域的发展历程,可为医学影像人工智能同行,尤其为新一代的学者和学生提供科研和教学参考,也为继续促进和加强国际合作交流,为全世界该领域进一步的蓬勃发展做出重要贡献。
关键词

()

Abstract
The past 20 years have witnessed incredibly rapid development of medical imaging, artificial intelligence, as well as clinical applications that combined medical imaging and artificial intelligence worldwide. With the increase of medical imaging data, the improvement and optimization of artificial intelligence models, and the upgrading of hardware and software equipment, more and more artificial intelligence techniques have been successfully applied to a variety of clinical scenarios in order to help improve the efficiency and accuracy of diagnosis and treatment, as well as to shorten the time and cost for patients. Notably, China has been continually playing a major role and making increasing contributions in the field of medical imaging artificial intelligence in the past 20 years. In terms of scientific research, it has attracted numerous prestigious researchers worldwide in the field of medical imaging artificial intelligence to join in the universities and institutions in China. The number of papers published by Chinese researchers in top international journals and conferences in medical imaging artificial intelligence has dramatically increased yearly. More and more prestigious international conferences in medical imaging artificial intelligence have been successfully held in China. In terms of industrial applications, there is an increasing number of traditional medical, internet technology and artificial intelligence companies devoting to the research and development of medical imaging artificial intelligence products. More and more hospitals have actively participated in collaborative research projects and provided a solid foundation for the implementation of medical imaging artificial intelligence. The Chinese government has also formulated relevant policies and issued strategic plans for the field of medical imaging artificial intelligence, and included the intelligent medical care as one of the key tasks for the development of new generation of artificial intelligence in China in 2030. In order to summarize the major achievements made by Chinese researchers in the field of medical imaging artificial intelligence, we hereby performed a 20-year retrospect and prospect of medical imaging artificial intelligence in China in this article. Specifically, we summarized all papers published by Chinese researchers in the representative prestigious medical imaging artificial intelligence journals and conferences including Medical Image Analysis (MedIA), IEEE Transactions on Medical Imaging (TMI), and Medical Image Computing and Computer Assisted Intervention (MICCAI) in the past 20 years. The detailed quantitative metrics including the number of published papers, authorship, affiliations, author’s cooperation network, keywords, and the number of citations were analyzed. In addition, we briefly summarized some milestone events of medical imaging artificial intelligence in China, including the prestigious international and domestic conferences in medical imaging artificial intelligence held in China, the release of the ‘The White Paper on Medical Imaging Artificial Intelligence in China’, as well as the contributions of Chinese researchers during the COVID-19 pandemic. The quantitative analysis and summary systematically demonstrated the outstanding achievements made by Chinese researchers in the field of medical imaging artificial intelligence in the past 20 years. For instance, the total number of published papers in the past 20 years and the proportion of published papers in 2021 by Chinese affiliations have reached to 333 and 37.29% in MedIA, 601 and 42.26% in TMI, and 985 and 44.26% in MICCAI. In those published papers by Chinese institutes, the proportion of the first and the corresponding Chinese authors is 71.97% in MedIA, 69.64% in TMI, and 77.4% in MICCAI in 2021. The average number of citations per paper by Chinese institutes is 22, 28, and 9 in MedIA, TMI, and MICCAI, respectively. In all published papers by Chinese institutes, the predominant research methods were transformed from conventional approaches to sparse representation in 2012, and to deep learning in 2017, which were closely in line with the latest developmental trend of artificial intelligence technologies. Besides conventional applications such as medical image registration, segmentation, reconstruction and computer-aided diagnosis, etc., the published papers also focused on urgent healthcare challenges such as COVID-19 pandemic. Many of those studies have shared the data and source codes with global researchers, making significant contributions to the research and education of medical imaging artificial intelligence field worldwide. This study could provide a reference for scientific research and education, as well as a clue for understanding the developmental history of the medical imaging artificial intelligence field in China and in the world for the new generation of Chinese scholars and students, who will continue to strengthen international cooperation and communication, as well as contributing to the development of this field in the future. Finally, we provided prospects for future investigations in the medical imaging artificial intelligence field. First, it is recommended to further improve the ability of deep learning for medical imaging artificial intelligence, including optimal and efficient deep learning, generalizable deep learning, explainable deep learning, fair deep learning, and responsible and trustworthy deep learning. Second, it is advocated to further improve the availability and sharing of high-quality and benchmarked medical imaging datasets in order to promote the development, validation, and dissemination of medical imaging artificial intelligence to address the key challenges in both basic scientific research and clinical applications. Third, it is necessary to strengthen the multi-center and multi-modal medical imaging data acquisition and fusion, as well as integration with natural language such as diagnosis report. Fourth, it is suggested to further strengthen the close cooperation with doctors in order to focus on real challenges in the clinical applications of medical imaging artificial intelligence. Finally, it is expected that researchers commit to those key scientific problems that require long-term research efforts. It is also expected that researchers continue to strengthen talent training, international collaboration, as well as sharing of open source data and codes for the vigorous development of medical imaging artificial intelligence worldwide.
Keywords
QQ在线


订阅号|日报