基于多相位图像相似性的肺4D-CT超分辨率重建  

Multi-phase similarity based super-resolution reconstruction for lung 4D-CT

作　　者：陈瑾[1,2] 张煜[1,2] CHEN Jin;ZHANG Yu(School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China;Guangdong Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou 510515, China)

机构地区：[1]南方医科大学生物医学工程学院,广州510515 [2]南方医科大学广东省医学图像处理重点实验室,广州510515

出　　处：《计算机工程与应用》2017年第15期191-195,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.31271067);广东省自然科学基金(No.S2013010014049)

摘　　要：肺4D-CT为放射治疗提供全面的图像引导,在当今肺癌治疗中起着重要的作用。然而,由于采集时间和人体所能承受辐射剂量的限制,无法得到高分辨率(Z轴方向)CT图像,因此,通常采集到的肺4D-CT图像Z轴方向细节部分往往不够清晰。针对这一问题,提出了一个基于多相位相似性的非局部均值超分辨率重建方法,来提升肺4D-CT图像的质量。该方法利用多相位图像之间的互补信息,以非局部均值滤波为基础,来恢复图像的高分辨率细节结构;另外,由于呼吸运动,肺4D-CT图像中不同相位图像肺区域的灰度会有所差异,为保证重建高分辨率图像的灰度不变性,引入全局约束以修正重建图像的整体灰度。采用一套公共肺4D-CT数据集评估提出的方法,该数据集由10组肺4D-CT数据组成,每组数据包含10个相位。实验表明,在恢复图像的细节和增强分辨率方面,该方法要优于传统的线性插值和凸集投影(Projection Onto Convex Set,POCS)超分辨率重建算法。Lung4D-CT is of great value in the application of cancer treatment,because it provides comprehensive imageguidance for radiation therapy.However,the high resolution lung4D-CT data along the Z axis can’t be obtained due tothe dose limitation.Concern this problem,a multi-phase similarity based non-local means super-resolution reconstructionfor lung4D-CT is proposed in this paper.The redundant information from multi-phases of4D-CT data are used to recoversome of this high frequency information by using a patch-based reconstruction in combination with a global constraint.Apublic dataset provided by DIR-lab is used to evaluate the proposed method.The dataset consists of10groups of lung4DCTdata and each group contains10phases.All the evaluation results show that the approach outperforms traditional linear-interpolation and the convex set projection approach(POCS)in terms of quantitative measures and visual observation.

关 键 词：肺4D-CT 非局部均值 超分辨率重建 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]