北京生物医学工程

非局部相似性压缩感知下的医学设备三维成像方法

Three-dimensional imaging of medical equipment based on non local similarity compressed sensing

作者：沈海荣张力杰

单位：云南省滇南中心医院(红河州第一人民医院)医学装备 部(云南红河州 661199) 通信作者:沈海宗。E-mail： ennaqq@163.com

分类号：R318.04；TN911.73

出版年·卷·期（页码）：2021·40·6（564-569）

摘要：

目的针对像素间的领域结构信息难以获取，无法分析医学设备图像子块相似性的问题，本文提出了一种新的非局部相似性压缩感知下的医学设备三维成像方法。方法首先获取医学设备三维图像并对其分块处理，通过冗余字典完成稀疏图像表示，利用自回归模型模拟医学设备三维成像的非局部状态，分析三维成像的非局部相似特性，得到医学设备三维图像的局部相关性和非局部相似性，以此为限定条件，实现医学设备三维成像的相似性压缩感知。最后以某三甲医院肿瘤科的3台医疗器械为实验对象，以不同时间段产生的三维图像为实验样本,与其他两种文献方法进行了对比。结果本文提出了非局部相似性压缩感知下的医学设备三维成像方法，相比于其他两种文献方法，其压缩感知峰值信噪比与标准值的匹配度最高可达99%。结论在稳定的采样频率下获取领域结构信息,可达到最佳的图像重构效果，解决了医学设备图像子块相似性的问题,保证医学设备三维成像质量。

Objective To solve the problem that it is difficult to obtain the domain structure information between pixels and analyze the similarity of medical device image sub blocks, a new 3D imaging method of medical device based on non local similarity compressed sensing is proposed. Methods Firstly, the 3D images of medical equipment are obtained and processed in blocks. The sparse images are represented by redundant dictionaries. The non local state of 3D imaging of medical equipment is simulated by autoregressive model. The non local similarity characteristics of 3D imaging are analyzed, and the local correlation and non local similarity of 3D images of medical equipment are obtained to realize the similarity compressed sensing of 3D imaging of medical equipment. Finally, three medical devices in the Oncology Department of a 3A hospital are taken as the experimental objects, and the three -dimensional images generated in different time periods are taken as the experimental samples, which are compared with the other two literature methods, the peak signal-to-noise ratio of compressed sensing can match the standard value up to 99%. Conclusions Obtaining domain structure information at a stable sampling frequency can achieve the best effect of image reconstruction, solve the problem of image sub block similarity of medical equipment, and ensure the quality of 3D imaging of medical equipment.

参考文献：

[1 ]杜秀丽，胡兴，陈波，等.基于加权非局部相似性的视频压缩感知多假设重构算法[J].计算机科学,2019,46 ( 1)： 291-296.

Du XL, Hu X, Chen B, et al. Multi-hypothesis reconstruction algorithm of DCVS based on weighted non-local similarity [ J]. Computer Science ,2019,46( 1) ： 291-296.

[2 ]刘歌，芮国胜，田文飕.基于结构特征约束两阶段重构的视频压缩感知[J].系统工程与电子技术,2020,42 ( 11 )： 2441-2449.

Liu G, Rui GS, Tian WB. Video compressed sensing based on two-phase reconstruction of structural feature prior constraints [J ]. Systems Engineering and Electronics, 2020 , 42 ( 11 )： 2441-2449.

[3 ]赵辉,杨晓军，张静，等.基于结构组全变分模型的图像压缩感知重建[J].电子与信息学报,2020,42(11) =2773-2780.

Zhao H, Yang XJ, Zhang J, et al. Image compressed sensing reconstruction based on structural group total variation [ J ].

Journal of Electronics & Information Technology, 2020,42(11): 2773-2780.

[4 ]吴科永，陈东，辛宁，等.压缩感知和相似性约束的图像超分辨率重构算法[J].计算机应用研究,2019,36 ( 5)： 1555-1559.

Wu KY, Chen D, Xin N, et al. Compressed sensing and similarity constraint image super-resolution [ J]. Application Research of

Computers,2019,36(5) ： 1555-1559.

[5 ]赵辉，方禄发,张天骐，等.基于组稀疏表示和加权全变分的图像压缩感知重构[J].系统工程与电子技术,2020,42 (10) ：2172-2180.

Zhao H, Fang LF, Zhang TQ, et al. Image compressive sensing reconstruction via group sparse representation and weighted total variation [ J ] . Systems Engineering and Electronics, 2020 , 42 (10) ：2172-2180.

[6 ]马培旗，袁玉山,张宗夕，等.基于压缩感知技术三维MRI用于半月板损伤[J].中国医学影像技术,2020,36( 10)： 1533-1536.

Ma PQ, Yuan YS,Zhang ZX,et al. Three dimensional MRI based on compressed sensing technology in d這gnosis of meniscal injuries [ J ]. Chinese Journal of Medical Imaging Technology, 2020,36(10) ： 1533-1536.

[7]魏敏，王松，吴亚东.医学图像可视化的视觉优化方法[J].计算机辅助设计与图形学学报,2019,31(4):659-667.

Wei M,Wang S, Wu YD. Research on visual optimization method of medical image visualization [ J ]. Journal of Computer-Aided Design & Computer Graphics,2019,31(4) ：659-667.

[8 ]李碧草，李润川,刘洲峰，等.基于非扩展嫡相似度的三维医学图像配准[J].计算机应用与软件,2020,37(11) =95-100.

Li BC, Li RC, Liu ZF, et al. Three-dimensional medical image registration based on nonextensive entropic similarity measure [J ]. Computer Applications and Software, 2020, 37 ( 11 )： 95-100.

[9 ] 丁金立，王志平,卓芝政，等.2D-SSh-MRCP序列与基于压缩感知技术的CS-3D-MRCP序列在胰胆管成像中的对比研究 [J].北京生物医学工程,2020,39(3) ：290-295.

Ding JL, Wang ZP, Zhuo ZZ, et al. Comparison of 2D — SSh — MRCP and compressed sensing sensitivity encoding based CS— 3D—MRCP in cholangiopancreatography [ J ]. Beijing Biomedical Engineering, 2020,39(3) ： 290—295.

[10]?李青,鲁珊珊，孙涛，等.压缩感知技术在头颅磁共振血管成像中的应用研究[J].中国医学装备,2020,17(2) ：66-70.

Li Q, Lu SS, Sun T, et al. The applied research on the CS technique in intracranial MRA [ J]. China Medical Equipment, 2020,17(2) ：66-70.

[11]?孔欢，束月霞,刘欣.基于光学波动和压缩感知的超分辨超声成像研究[J].医疗卫生装备,2019,40(9) ：8-11.

Kong H, Shu YX, Liu X, Super-resolution ultrasound imaging based on optical fluctuation and compressed sensingf J]. Chinese Medical Equipment Journal,2019,40(9) ：8—11.

[12]?董昕，陈思佳,李军.基于压缩感知和散斑相关法的散射介质成像方法研究[J].激光生物学报,2019,28(1) =64-71.

Dong X, Chen SJ, Li J. Research on scattering medium imaging method based on compressive sensing and speckle correlation [J]. Acta Laser Biology Sinica,2019,28(1) ： 64-71.

[13]?郭庆,滕月阳，仝灿，等.基于压缩感知与快速迭代阈值收缩算法的脑功能网络重建[J].生物医学工程学杂志,2020,37 (5) ：855-862.

Guo Q, Teng YY, Tong C, et al. Brain functional network reconstruction based on compressed sensing and fast iterative shrinkage-thresholding algorithm [ J ]. Journal of Biomedical Engineering,2020,37(5) ：855-862.

[14]?魏强，王家正,伊东娜，等.结合压缩感知技术与敏感度编码的 3D mDixon序列以及3D Vane序列对肝脏成像的影响的对比研究[J].磁共振成像,2020,11(9) ：781-785.

Wei Q,Wang JZ,Yi DN,et al. A comparative study on the effects of 3D mDixon sequence and 3D Vane sequence on liver imaging by combining the Compressed SENSE technology and SENSE] J]. Chinese Journal of Magnetic Resonance Imaging, 2020,11 (9)： 781-785.

[15]?向逾，黄飞，何清.基于三维决策空间的医疗设备维修策略研究[J].医疗卫生装备,2019,40(12) ：61-64.

Xiang Y, Huang F, He Q. Research on medical equipment maintenance strategies based on 3D decision space [ J]. Chinese Medical Equipment Journal,2019,40( 12) ：61—64

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录