ICP优化下的B样条四维CT图像弹性配准方法

doi:10.16182/j.issn1004731x.joss.19-VR0436

系统仿真学报 ›› 2020, Vol. 32 ›› Issue (7): 1301-1311.doi: 10.16182/j.issn1004731x.joss.19-VR0436

ICP优化下的B样条四维CT图像弹性配准方法

汤雯洁^{1, 2}, 李若桐², 邓雪松³, 司伟鑫², 王琼²

1. 武汉理工大学,湖北武汉 430070;
2. 中国科学院深圳先进技术研究院,广东深圳 518500;
3. 深圳市第二人民医院,广东深圳 100730

收稿日期:2019-08-23 修回日期:2019-11-07 出版日期:2020-07-25 发布日期:2020-07-15
通讯作者: 汤雯洁(1995-),女,湖北黄冈,硕士生,研究方向为医学图像处理。
作者简介:汤雯洁(1995-),女,湖北黄冈,硕士生,研究方向为医学图像处理。

ICP Optimized B-Spline Non-Rigid Registration for 4D-CT Images

Tang Wenjie^{1, 2}, Li Ruotong², Deng Xuesong³, Si Weixin², Wang Qiong²

1. Wu Han University of Technology, Wuhan 430070, China;
2. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences, Shenzhen 518500, China;
3. Shenzhen second people's hospital, Shenzhen 100730, China;

Received:2019-08-23 Revised:2019-11-07 Online:2020-07-25 Published:2020-07-15

摘要/Abstract

摘要： 为提高不同生理状态下两组四维CT图像之间配准的精度和速度,基于多分辨率B样条的自由形变模型(Free Form Deformation, FFD),提出一种使用迭代最近点(Iterative Closest Point,ICP)优化该模型的配准算法。在传统B样条之前加入ICP算法实现两组四维CT图像间的点云配准：根据分割完的两组四维CT图像生成点云数据和灰度数据,使用ICP对模型中的两组点云配准。level 1,level 2,level 3相似性测度提高率分别为：8.68%,10.46%,2.39%,速度提高率分别为：-51.89%,41.71%,81.09%,结果证明新模型在不同控制网格大小配准上精度和速度都有提高。

关键词: ICP, B样条, 非刚性配准, CT图像

Abstract: In order to improve the accuracy and speed of registration between two groups of 4D-CT images under different physiological activities, based on FFD model of multi-resolution B-spline, a registration algorithm using ICP to optimize the model is proposed. The ICP algorithm is added before the traditional b-spline to realize the point cloud registration between two groups of 4D-CT images: the appropriate model is generated from the two segmented groups of 4D-CT images, then the two groups of point clouds in the model are registered with ICP. The improvement rates of similarity measurement at level 1, level 2 and level 3 are 8.68%, 10.46% and 2.39% respectively, and the speed improvement rates are -51.89%, 41.71%, 81.09% respectively.

Key words: ICP, B-spline, Non-rigid registration, CT images

中图分类号:

TP391.41

汤雯洁, 李若桐, 邓雪松, 司伟鑫, 王琼. ICP优化下的B样条四维CT图像弹性配准方法[J]. 系统仿真学报, 2020, 32(7): 1301-1311.

Tang Wenjie, Li Ruotong, Deng Xuesong, Si Weixin, Wang Qiong. ICP Optimized B-Spline Non-Rigid Registration for 4D-CT Images[J]. Journal of System Simulation, 2020, 32(7): 1301-1311.

参考文献 16

[1]	Mitrović U, Likar B, Pernuš F, et al.3D-2D registration in endovascular image-guided surgery: Evaluation of state-of-the-art methods on cerebral angiograms[J]. International journal of computer assisted radiology and surgery (S1861-6410), 2018, 13(2): 193-202.
[2]	李明晏. 基于B样条的图像弹性配准算法研究[D]. 济南: 山东大学, 2011.Li Mingyan.The Research on Non-rigid Registration Based on B-Spline[D]. Ji’nan: Shandong university, 2011.
[3]	冯兆美, 党军, 崔崤峣, 等. 基于B样条自由形变三维医学图像非刚性配准研究[J]. 影像科学与光化学, 2014, 32(2): 200-208.Feng Zhaomei, Dang Jun, Cui Xiaoyao, et al.B-spline Free-form Deformation Based 3-D Non-rigid Registration of Medical Images[J]. Photographic Science and Photochemistry, 2014, 32(2): 200-208.
[4]	汪友生, 李冠宇. 基于平滑样条函数的血管图像弹性配准算法[J]. 电子测量与仪器学报, 2015, 29(9): 1334-1339.Wang Yousheng, Li Guanyu.Vascular image elastic registration algorithm based on smoothing spline function[J]. Journal of electronic measurement and instrumentation, 2015, 29(9): 1334-1339.
[5]	Wodzinski M, Skalski A, Ciepiela I, et al.Application of demons image registration algorithms in resected breast cancer lodge localization[C]// 2017 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA): IEEE, 2017: 400-405.
[6]	庞皓文, 孙小杨, 杨波. 五种弹性配准方法在放射治疗CT图像配准中的应用比较[J]. 中国医学装备, 2018, 15(3): 26-29.Pang Haowen, Sun Xiaoyang,Yang Bo.Comparison on application of five kinds of elastic registration methods in the CT image registration of radiotherapy[J]. Chinese Medical Equipment, 2018, 15(3): 26-29.
[7]	宋湘芬, 林仕令, 宋磊, 等. 基于B样条的医学图像弹性配准[J]. 生物医学工程研究, 2017, 36(3): 213-217.Song Xiangfen, Lin Shiling, Song Lei, et al.Elastic Registration of Medical Image Using B-Spline[J]. Biomedical Engineering Research, 2017, 36(3): 213-217.
[8]	Liu Y, Zhu B.Deformable image registration with geometric changes[J]. Frontiers of Information Technology & Electronic Engineering (S2095-9230), 2015, 16(10): 829-837.
[9]	李宇森. 基于多层B样条和L2正则化的图像配准方法研究[D]. 济南: 山东大学, 2017.Li Yusen.Research on Non-rigid Image Registration Based on Multi-level B-spline and L2-Regularization[D]. Jinan: Shandong University, 2017.
[10]	Chan C L, Anitescu C, Zhang Y J, et al.Two and Three Dimensional Image Registration Based on B-Spline Composition and Level Sets[J]. Communications in Computational Physics (S1815-2406), 2017, 21(2): 600-622.
[11]	Pawar A, Zhang Y J, Anitescu C, et al.Joint image segmentation and registration based on a dynamic level set approach using truncated hierarchical B-splines[J]. Computers & Mathematics with Applications (S0898-1221), 2019, 78(10): 3250-3267.
[12]	Wu Z Z, Chen H C, Du S Y, et al.Correntropy based scale ICP algorithm for robust point set registration[J]. Pattern Recognition (S0031-3203), 2019, 93: 14-24.
[13]	Albarqouni S, Konrad U, Wang L, et al.Single-view X-ray depth recovery: toward a novel concept for image-guided interventions[J]. International journal of computer assisted radiology and surgery (S1861-6410), 2016, 11(6): 873-880.
[14]	Kang X, Armand M, Otake Y, et al.Robustness and accuracy of feature-based single image 2-D-3-D registration without correspondences for image-guided intervention[J]. IEEE Transactions on Biomedical Engineering (S0018-9294), 2013, 61(1): 149-161.
[15]	Shi S, Yuan R, Sun Z, et al.A liver registration method for segmented multi-phase CT images[C]// Medical Imaging 2015: Image Processing. International Society for Optics and Photonics, 2015: 941331.
[16]	顾菊平, 程天宇, 华亮, 等. 面向脊柱生物建模的图像分割与配准研究综述[J]. 系统仿真学报, 2019, 31(2): 167-173.Gu Juping, Cheng Tianyu, Hua Liang, et al.Overview of Image Segmentation and Registration for Spine Biological Modeling[J]. Journal of System Simulation, 2019, 31(2): 167-173.

ICP优化下的B样条四维CT图像弹性配准方法

ICP Optimized B-Spline Non-Rigid Registration for 4D-CT Images

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 16

相关文章 3

编辑推荐

Metrics

本文评价

[1]	李琳, 陈维杰, 邹焱飚. 基于条纹式激光传感器的焊缝测量系统研究[J]. 系统仿真学报, 2017, 29(7): 1588-1595.
[2]	方志力, 温维亮, 郭新宇, 吴建伟. 基于Kinect的三维玉米植株骨架提取[J]. 系统仿真学报, 2017, 29(3): 524-530.
[3]	余文利, 周明全, 税午阳, 武仲科. 基于曲率的点云自动配准方法[J]. 系统仿真学报, 2015, 27(10): 2374-2379.