CT理论与应用研究2026，Vol.35Issue(1)：15-27,13.DOI:10.15953/j.ctta.2025.264
基于深度学习的CT图像金属伪影去除研究进展
CT Image Metal Artifact Reduction Based on Deep Learning
摘要
Abstract
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 deep-learning-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.关键词
CT图像/金属伪影去除/深度学习/双域/无监督学习Key words
CT image/metal artifact reduction/deep learning/dual domain/unsupervised learning分类
信息技术与安全科学引用本文复制引用
叶子豪,金潼,车子刚,王士森,刘进,陈阳..基于深度学习的CT图像金属伪影去除研究进展[J].CT理论与应用研究,2026,35(1):15-27,13.基金项目
国家自然科学基金(CT成像理论、关键技术及应用(T2225025)) （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)). （任务驱动的深度能谱CT成像算法研究(YQZD2023041）
