摘要
金属伪影是影响临床CT图像质量与诊断准确性的主要干扰因素,去除CT图像中的金属伪影一直是业界研究的重要方向。近年来,深度学习技术的发展与应用,为CT图像金属伪影去除算法研究开辟了新途径,涌现出大量优秀成果。本文首先阐述CT图像中金属伪影产生的原因及表现形式,其次从图像域、投影域及双域3个方向,综述近年来深度学习在CT图像金属伪影去除领域中的研究进展,最后对现有方法进行概括总结,并对金属伪影去除的研究前景进行展望。
Metal artifacts adversely affect computed tomography(CT)image quality and diagnostic accuracy.Metal-artifact reduction(MAR)in CT images has long been a major focus of research.In recent years,with the advancement and application of deep-learning technologies,new approaches have emerged for research on MAR algorithms,leading to a wealth of outstanding achievements.In this paper,we first introduce the causes and manifestations of metal artifacts in CT images.We then review recent progress in deeplearning-based MAR methods,categorizing them into three approaches:image,projection,and dual domains.Finally,we summarize these methods and discuss future research prospects for MAR technology.
作者
叶子豪
金潼
车子刚
王士森
刘进
陈阳
YE Zihao;JIN Tong;CHE Zigang;WANG Shisen;LIU Jin;CHEN Yang(School of Computer and Information,Anhui Polylechnic University,Wuhu 241000,China;Department of Radiology,Nanjing Tongren Hospital,Southeast University,Nanjing 211102,China;School of Computer Science and Engineering,Southeast University,Nanjing 210096,China)
出处
《CT理论与应用研究(中英文)》
2026年第1期15-27,共13页
Computerized Tomography Theory and Applications
基金
国家自然科学基金(CT成像理论、关键技术及应用(T2225025))
安徽省中青年教师培养行动项目重点项目(任务驱动的深度能谱CT成像算法研究(YQZD2023041))。
关键词
CT图像
金属伪影去除
深度学习
双域
无监督学习
CT image
metal artifact reduction
deep learning
dual domain
unsupervised learning
