基于局部保留投影的荧光分子断层成像快速重建  

Fast Reconstruction in Fluorescence Molecular Tomography Based on Locality Preserving Projections

作　　者：张旭[1] 易黄建[1] 侯榆青[1] 张海波[1] 贺小伟[1] 

机构地区：[1]西北大学信息科学与技术学院,陕西西安710127

出　　处：《光学学报》2016年第7期213-222,共10页Acta Optica Sinica

基　　金：国家自然科学基金(61372046;11571012);陕西省科技计划项目(2013K12-20-12;2015KW-002)

摘　　要：采用大规模荧光分子断层成像(FMT)投影数据进行重建需要消耗大量的计算内存,花费较长的计算时间.为降低FMT重建的病态性以及加快重建速度,基于流形学习和压缩感知理论,提出了结合局部保留投影(LPP)和稀疏正则化的重建方法,并对原始的多投影荧光数据进行重建.为评估该方法的重建效果和时间,分别设计了非匀质圆柱单、双目标仿真实验和真实小鼠实验.实验结果表明,在保证FMT重建图像精度和分辨率的同时将重建时间大幅度减少.Image reconstruction with large scale of fluorescence molecular tomography（FMT）data needs a large amount of computational memory and time.In order to reduce the ill-posedness of FMT and speed up the reconstruction,an accelerated reconstruction method for FMT based on locality preserving projections（LPP）and sparse regularization algorithm is presented,combining with the manifold learning and compressive sensing theory.The original fluorescent multi-projection data is reconstructed.Simulation experiment of non-homogeneous cylinder single and double goal and real experiment are performed to evaluate the reconstruction effect and time of the proposed method respectively.Experimental results demonstrate that the proposed method can ensure the accuracy and resolution of the FMT reconstruction image and reduce the reconstruction time greatly.

关 键 词：生物光学 荧光分子断层成像 数据降维 局部保留投影 图像重建 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] Q632[自动化与计算机技术—计算机科学与技术]