乳腺DCE-MRI增强场时间序列和组织形变场的联合估计  

Joint Estimation of Enhancement Field Sequence and Deformation Field of Breast DCE-MRI

作　　者：余丽玲[1] 阳维[1] 卢振泰[1] 冯前进[1] 陈武凡[1] 

机构地区：[1]南方医科大学生物医学工程学院,广东广州510515

出　　处：《电子学报》2014年第8期1509-1514,共6页Acta Electronica Sinica

基　　金：国家自然科学青年基金(No.81101109);国家973重点基础研究发展计划(No.2010CB732505)

摘　　要：乳腺DCE-MRI扫描过程中,病人运动等会使图像序列产生运动伪影,需要对DCE-MRI时间序列图像进行运动补偿,消除运动伪影的影响.为充分利用数据信息和增强在空间和时间上的先验信息,本文提出了联合估计增强场时间序列和组织形变场的贝叶斯框架.采用离散马尔科夫随机场模型分别对增强场时间序列和组织形变场进行建模和添加平滑约束,并通过分步迭代方式进行估计.利用估计的增强场对DCE-MRI时间序列图像进行"去增强"处理后,可将增强时间序列图像视为同一模态图像进行配准.实验结果表明,本文方法可准确估计增强场时间序列,并可达到较高的配准精度.Dynamic contrast-enhanced magnetic resonance imaging （DCE-MRI） suffer artifact by patient motion during the imaging procedure. It is necessary to correct patient motion by deformation registration for DCE-MRI. We present a MAP framework of joint estimation of the enhancement field sequence and the deformation field, which can make use of the prior knowledge of en- hancement in space-time. The enhancement field sequence and the deformation field are modeled by the MRF models with the smoothness constraints, and are estimated by a two-step alternate optimization algorithm. In the altemate optimization procedure, the estimated enhancement field sequence is used to de-enhance the post-contrast images. Thus, the pre-contrast and post-contrast images can be considered as the same modal image for registration and it make the estimation of deformation field easier. The experimental results show that the proposed method can estimate the enhancement field sequence accurately axld provides high registration accuracy.

关 键 词：乳腺肿瘤 动态增强磁共振 图像配准 马尔科夫随机场 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]