人工智能在放射性核素心肌灌注显像中的研究进展  

Research Advances of Artificial Intelligence in Radionuclide Myocardial Perfusion Imaging

作　　者：赵福锴 李剑明[1] ZHAO Fukai;LI Jianming(Department of Nuclear Medicine,Tianjin Medical University Cardiovascular Clinical Institute,TEDA International Cardiovascular Hospital,Tianjin 300457,China)

机构地区：[1]天津医科大学心血管病临床学院、泰达国际心血管病医院核医学科,天津300457

出　　处：《中国医学影像学杂志》2023年第12期1316-1322,1341,共8页Chinese Journal of Medical Imaging

基　　金：天津市自然科学基金项目(21JCYBJC00580)。

摘　　要：随着科技的不断发展进步,人工智能在医学成像中的应用逐渐广泛,推动了核心脏病学中放射性核素心肌灌注显像的智能化和精准化发展。人工智能,尤其是机器学习和深度学习,在处理心肌灌注显像中的大量复杂数据、减少图像采集时间和辐射剂量、提高图像质量、优化诊断准确性、自动化处理和预后评估等方面展现出巨大潜力。本文将从人工智能在心肌灌注显像的数据采集处理、衰减校正、图像后处理、诊断报告及患者预后评估等方面进行总结,为科研工作提供新的思路与方法,促进核心脏病学的工作朝着智能化、精准化方向发展。With the continuous advancement of technology,the application of artificial intelligence in medical imaging has become increasingly widespread,notably revolutionizing the field of nuclear cardiology through the intelligent and precise development of radionuclide myocardial perfusion imaging.Artificial intelligence,particularly machine learning and deep learning,has shown immense potential in handling the voluminous and complex data associated with myocardial perfusion imaging.It plays a pivotal role in reducing image acquisition time and radiation dosage,enhancing image quality,optimizing diagnostic accuracy and automating processing and prognostic assessments.This paper summarizes the applications of artificial intelligence in various aspects of myocardial perfusion imaging,including data collection and processing,attenuation correction,image post-processing,diagnostic reporting and patient prognostic evaluation.The aim is to provide new insights and methodologies for research work,thereby promoting the intelligent and precise advancement of nuclear cardiology.

关 键 词：核心脏病学 放射性核素 心肌灌注显像 人工智能 综述 

分 类 号：R445.5[医药卫生—影像医学与核医学] R541[医药卫生—诊断学]