基于联合投影数据的动态锥束CT伪影消除算法  

View aliasing artifacts reduction method for 4D cone-beam CT based on joint projection data

作　　者：职少华 蔡剑梅 段嘉毓 牟轩沁[1] 

机构地区：[1]西安交通大学电信学院图像处理与识别研究所,西安710049

出　　处：《中国体视学与图像分析》2017年第3期293-298,共6页Chinese Journal of Stereology and Image Analysis

基　　金：国家重点研发计划(No.2016YFA0202003);国家自然科学基金(No.61571359)

摘　　要：动态锥束CT重建技术被广泛应用于人体呼吸运动状态成像目标的放疗锥束CT中。该技术在一定程度上可以削减由于运动引起的运动伪影,但每一个相位投影数据引入稀疏角问题并导致重建图像有严重的条形伪影。本文利用不同相位重建图像之间具有很强相关性这一特点,提出了一种简单并有效的方法来估计某一相位重建图像的全角度投影数据并应用于三维迭代重建框架中,从而有效消除了条形伪影。Four-dimensional Cone-Beam Computed Tomography（4D-CBCT） reconstruction could be widely used in motion targeted CBCT in image-guided radiation therapy. Although it could reduce motion blurring artifacts,the image quality may still be degraded by severe view-aliasing artifacts because of highly under-sampled projections at each phase. Inspired by the strong correlation between different phase-resolved reconstructed images,we present a simple and effective approach to estimate a set of full-sampled projections for every individual respiratory phase and incorporate them into the 4D-CBCT iterative reconstruction scheme. The streaking artifacts could be eliminated at each phases by this method.

关 键 词：计算机断层成像 动态锥束CT 基于图像引导的放疗技术 迭代重建 联合投影数据 

分 类 号：R814.42[医药卫生—影像医学与核医学] TP391.41[医药卫生—放射医学]