深度学习在放射学科和麻醉学交叉领域的应用进展  

The Progress of the Application of Deep Learning in the Interdisciplinary Fields of Radiology and Anesthesiology

作　　者：张振强 王远军[1] 王振猛 ZHANG Zhenqiang;WANG Yuanjun;WANG Zhenmeng(School of Health Science and Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China;Department of Anesthesia,Third Affiliated Hospital of Naval Military Medical University,Shanghai 200438,China)

机构地区：[1]上海理工大学健康科学与工程学院,上海200093 [2]海军军医大学第三附属医院麻醉科,上海200438

出　　处：《生物医学工程学进展》2024年第1期42-47,共6页Progress in Biomedical Engineering

摘　　要：随着互联网和人工智能的应用,很多医疗领域变得更加高效和可靠。现代麻醉学的范畴已经不再局限于手术室内,还包括门诊、内镜科等,这就使麻醉医生的负担进一步加重。放射学科与麻醉学的结合为麻醉手术提供了更精确、更安全和更高效的方法,而深度学习技术的快速发展为该领域带来了许多前沿创新。该文综合归纳了近年来深度学习在该交叉领域的相关研究成果,并对相关应用进行了分类和总结。通过对文献的分析,该文重点讨论了医学影像领域的图像识别和目标定位等具体应用,并探讨了深度学习在麻醉学领域的局限性和未来发展方向。With the access to the Internet and artificial intelligence,many medical fields have become more efficient and reliable.Modern anesthesiology extends beyond the operating room to include outpatient settings,endoscopy units,and more,placing an additional burden on anesthesiologists.The integration of radiology and anesthesiology provides more accurate,safe,and efficient methods for anesthesia procedures.The rapid development of deep learning technology brings cutting-edge innovations to this field.This paper summarizes the recent research findings related to deep learning in this interdisciplinary field,and categorizes and summarizes the relevant applications.Through literature analysis,we will focus on discussing specific applications such as image recognition and object positioning in the field of medical imaging.Finally,we explore the limitations and future directions of deep learning methods in the field of anesthesiology.

关 键 词：深度学习 麻醉学 人工智能 图像识别 目标定位 

分 类 号：R614[医药卫生—麻醉学]