基于张量分解的电阻抗三维成像方法  

Three-dimensional imaging method based on tensor decomposition for electrical impedance tomography

作　　者：李秀艳[1,2] 尉蕾 王琦[1,2,3] 段晓杰[1,2] 马会梅[1,2] 陆纪璇 LI Xiu-yan;YU Lei;WANG Qi;DUAN Xiao-jie;MA Hui-mei;LU Ji-xuan(School of Electronics and Information Engineering,Tiangong University,Tianjin 300387,China;Tianjin Key Laboratory of Optoelectronic Detection Technology and Systems,Tiangong University,Tianjin 300387,China;School of Life Sciences,Tiangong University,Tianjin 300387,China)

机构地区：[1]天津工业大学电子与信息工程学院,天津300387 [2]天津工业大学天津市光电检测技术与系统重点实验室,天津300387 [3]天津工业大学生命科学学院,天津300387

出　　处：《天津工业大学学报》2022年第1期73-80,共8页Journal of Tiangong University

基　　金：国家自然科学基金资助项目(61872269,61601324,61903273);天津市自然科学基金资助项目(18JCYBJC85300);天津市企业科级特派员项目(18JCTPJC61600)。

摘　　要：针对现有的三维电阻抗成像只是对图像横截面的单独重建,然后罗列为三维进行显示,没有考虑到不同图层间的关联性,致使图像信息利用不充分的问题,提出一种基于张量分解的电阻抗三维成像方法。该方法将实验中测得的数据建立张量模型,使用张量分解可以对胸腔进行直接三维重建,能够充分利用图层间的关联性;并将该方法与总变差正则化(Total Variation,TV)成像算法、Tikhonov正则化重建算法进行实验对比。实验结果表明:基于张量分解的电阻抗三维成像方法,可以充分利用图像的空间结构信息,考虑图像层与层之间的关联特性,能够更加接近肺部的真实情况,准确地反映肺的状态,进而提高图像重建质量;基于张量分解的电阻抗三维成像方法相比于二维张量重建方法,将图像的峰值信噪比(PSNR)提高了13.8%。由此可得,与Tikhonov正则化以及TV成像算法相比,基于张量分解的电阻抗三维成像方法更适合电阻抗的图像重建工作。Aiming at the problem that the current three-dimensional electrical impedance imaging is only a separate recon-struction of the image cross-section,and then listed as three-dimensional display,which is not considered the correlation between different layers,so the image information is not fully utilized.A three-dimensional imaging method based on tensor decomposition for electrical impedance tomography is proposed.In the experiment,the measured data is built into a tensor model by this method.By tensor decomposition,the thorax can be reconstr-ucted directly.The correlation between layers can be fully exploited.Meanwhile,experimental comparison is made with Tikhonov regularized reconstruction algorithm and Total Variation regularization(TV)imaging algori-thm.The reconstruction results are closer to real condition of lung.As a result,it can make full use of the spatial structure information of the image and consider the correlation between the image layers to improve the quality of image reconstruction.Compared with the two-dimensional tensor reconstruction method,the peak signal-to-noise ratio(PSNR)of the three-dimensional impedance imaging method based on tensor decomposition is impr-oved by 13.8%.Therefore,it can be concluded that compared with Tikhonov regularized reconstruction algorithm and TV imaging algorithm,the three-dimensional imaging method of electrical impedance based on tensor decomposition is more suitable for electrical impedance image reconstruction.

关 键 词：电阻抗三维成像 张量分解 空间结构信息 图像质量 图像重建 

分 类 号：TN911.73[电子电信—通信与信息系统]