基于空间对齐和轮廓匹配的颈动脉多对比MRI三维配准方法

doi:10.11896/j.issn.1002-137X.2019.05.037

计算机科学 ›› 2019, Vol. 46 ›› Issue (5): 241-246.doi: 10.11896/j.issn.1002-137X.2019.05.037

所属专题：医学图像

基于空间对齐和轮廓匹配的颈动脉多对比MRI三维配准方法

汪晓妍¹, 刘琪琪¹, 黄晓洁², 姜娓娓¹, 夏明¹

(浙江工业大学计算机科学与技术学院杭州310023)¹
(浙江大学医院院杭州310058)²

发布日期:2019-05-15
作者简介:汪晓妍(1982-),女,博士,副教授,CCF会员,主要研究方向为计算机视觉与图像,E-mail:xiaoyanwang@zjut.edu.cn(通信作者);刘琪琪(1993-),女,硕士生,主要研究方向为医学图像处理;黄晓洁(1984-),女,硕士,主要研究方向为临床医学;姜娓娓(1984-),女,博士,讲师,主要研究方向为医学图像处理;夏明(1981-),男,博士,副教授,硕士生导师,主要研究方向为智能计算。
基金资助:
浙江省自然科学基金(LY18F030019,LY18F020030),国家自然科学基金(11302195,61401397,61701442)资助。

Multi-contrast Carotid MRI 3D Registration Method Based on Spatial Alignment and Contour Matching

WANG Xiao-yan¹, LIU Qi-qi¹, HUANG Xiao-jie², JIANG Wei-wei¹, XIA Ming¹

(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China)¹
(School of Medicine,Zhejiang University,Hangzhou 310058,China)²

Published:2019-05-15

摘要/Abstract

摘要： 多对比高分辨率磁共振成像(Magnetic Resonance Imaging,MRI)技术可以无创显示管壁结构和斑块成分,为分析颈动脉粥样硬化斑块提供了一种有效手段。多对比图像中的血管配准是斑块成分识别的关键任务,由此提出一种基于空间位置对齐和内腔轮廓匹配的颈动脉多对比磁共振图像三维配准算法。基于多对比序列图像,采用由粗到细的策略:首先利用图像的物理坐标进行空间位置的层间对齐;然后运用最大类间方差法和活动轮廓模型实现各序列血管内腔的半自动连续分割;最后以内腔轮廓组成的三维点云进行基于改进迭代最近点算法的三维配准。实验结果表明,配准后TOF序列和T₁Gd序列的三维内腔包含率达到92.79%,T₁WI序列和T₁Gd序列的三维内腔包含率达到94.66%,实现了多对比磁共振图像血管的三维精确配准,为后续易损斑块的成分分析奠定了基础。

关键词: 磁共振图像, 多对比, 颈动脉粥样硬化, 三维配准, 易损斑块

Abstract: Multi-contrast high-resolution magnetic resonance imaging(MRI) technology can non-invasively display the wall structure and plaque composition,providing an effective method for diagnosis and analysis of carotid atherosclerotic plaque.The registration of vessels in multi-contrast images becomes a critical task for plaque identification.This paper proposed a three-dimensional registration algorithm based on spatial position alignment and lumen contour matching.With multi-contrast carotid MRI,a coarse-to-fine strategy was adopted.Firstly,the physical coordinates are found to perform the spatial alignment.Then,the ostu algorithm and active contour model are used to complete the semi-automatic continuous segmentation of the blood vessel lumens.Finally,the lumen contour point clouds are utilized to perform three-dimensional rigid registration based on an improved iterative closest point algorithm.The results indicate that the three-dimensional average lumen inclusion rate between TOF and T₁Gd sequence reaches 92.79%,and the average lumen inclusion rate between T₁WI and T₁Gd sequence reaches 94.66%.The proposed algorithm achieves three-dimensional accurate registration of multi-contrast MRI,which lays the foundation for the subsequent analysis of vulnerable atherosclerotic plaque.

Key words: Carotid atherosclerosis, Magnetic resonance image, Multi-contrast, Three-dimensional registration, Vulnerable plaque

中图分类号:

TP391

汪晓妍, 刘琪琪, 黄晓洁, 姜娓娓, 夏明. 基于空间对齐和轮廓匹配的颈动脉多对比MRI三维配准方法[J]. 计算机科学, 2019, 46(5): 241-246. https://doi.org/10.11896/j.issn.1002-137X.2019.05.037

WANG Xiao-yan, LIU Qi-qi, HUANG Xiao-jie, JIANG Wei-wei, XIA Ming. Multi-contrast Carotid MRI 3D Registration Method Based on Spatial Alignment and Contour Matching[J]. Computer Science, 2019, 46(5): 241-246. https://doi.org/10.11896/j.issn.1002-137X.2019.05.037

参考文献

[1]AMMIRATI E,FOGACCI F.Clinical relevance of biomarkers for the identification of patients with carotid atherosclerotic plaque:Potential role and limitations of cysteine protease legumain[J].Atherosclerosis,2017,257:248-249.
[2]KUROSAKI Y,YOSHIDA K,FUKUMITSU R,et al.Carotid artery plaque assessment using quantitative expansive remodeling evaluation and MRI plaque signal intensity[J].Journal of Neurosurgery,2015,124(3):1-7.
[3]COOLEN B F,POOT D H,LIEM M I,et al.Three-dimensional quantitative T1 and T2 mapping of the carotid artery:Sequence design and in vivo feasibility[J].Magnetic Resonance in Medicine,2016,75(3):1008-1017.
[4]BRINJIKJI W,LEHMAN V T,HUSTON J,et al.The association between carotid intraplaque hemorrhage and outcomes of carotid stenting:a systematic review and meta-analysis[J].Journal of NeuroInterventional Surgery,2017,9(9):837-842.
[5]SILVA T D,UNERI A,KETCHA M,et al.WE-AB-BRA-09:Registration of Preoperative MRI to Intraoperative Radiographs for Automatic Vertebral Target Localization[J].Medical Physi-cs,2016,43(6):3793.
[6]GUO H,WANG G,HUANG L,et al.A Robust and Accurate Two-Step Auto-Labeling Conditional Iterative Closest Points (TACICP) Algorithm for Three-Dimensional Multi-Modal Carotid Image Registration[J].Plos One,2016,11(2):1-22.
[7]LIU Y H,YAN D Q,LIU C F.Research on Medical Image Regi-stration Classification[J].Computer Science,2015,42(11):22-27.(in Chinese) 刘益含,闫德勤,刘彩凤.医学图像配准分类研究[J].计算机科学,2015,42(11):22-27.
[8]SLOMKA P J,MANDEL J,DOWNEY D,et al.Evaluation of voxel-based registration of 3-D power Doppler ultrasound and 3-D magnetic resonance angiographic images of carotid arteries.Ultrasound in medicine & biology,2001,27(7):945-955.
[9]LIU Z,SONG Y Q,WANG D D.Medical Image RegistrationBased on Self-adaptive DE Algorithm and Powell Algorithm[J].Computer Science,2017,44(11):297-300.(in Chinese)刘哲,宋余庆,王栋栋.自适应变异差分算法与Powell算法相结合的医学图像配准[J].计算机科学,2017,44(11):297-300.
[10]MATL S,BROSIG R,BAUST M,et al.Vascular image registration techniques:A living review[J].Medical Image Analysis,2017,35:1-17.
[11]LI J W,WANG X Y,ZHANG J H,et al.Multi-sequence MR Ima-ge Denoising and Registration Based on Carotid Atherosclerosis Plaque[J].Journal of Image and Graphics,2015,20(7):871-881.(in Chinese) 李军伟,汪晓妍,张剑华,等.基于颈动脉粥样硬化斑块的多序列MR图像去噪与配准[J].中国图象图形学报,2015,20(7):871-881.
[12]WU Y X,XU X P,ZHANG X,et al.Registration AlgorithmBased on Multi-Contrast Magnetic Resonance Carotid Artery Images[J].Chinese Journal of Biomedical Engineering,2017,36(2):129-135.(in Chinese) 吴玉霞,徐肖攀,张曦,等.基于多对比度磁共振颈动脉图像的配准算法研究[J].中国生物医学工程学报,2017,36(2):129-135.
[13]BESL P J,MCKAY N D.Method for registration of 3-D shapes[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,14(2):239-256.
[14]BOOKSTEIN F L.Principal Warps:Thin-Plate Splines and the Decomposition of Deformations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,16(6):567-585.
[15]CHIU B,SHAMDASANI V,ENTREKIN R,et al.Characteri-zation of carotid plaques on 3-dimensional ultrasound imaging by registration with multicontrast magnetic resonance imaging.[J].Journal of Ul-trasound in Medicine Official Journal of the American Institute of Ultrasound in Medicine,2012,31(10):1567-1580.
[16]KANANENKA A A,WELDEN A R,LAN T N,et al.Efficient tempera-ture-dependent Green’s function methods for realistic systems:using cubic spline interpolation to approximate Matsubara Green’s functions[J].Journal of Chemical Theory & Computation,2016,12(5):2250-2259.
[17]BIZOPOULOS P A,SAKELLARIOS A,MICHALIS L K,et al.3-D Registration on Carotid Artery imaging data:MRI for different timesteps∥2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC).IEEE,2016:1159-1162.
[18]OSTU N,NOBUYUKI O,OTSU N.A threshold selectionmethod from gray-level histogram IEEE transactions on systems[J].IEEE Transactions on Systems Man & Cybernetics,1979,9(1):62-66.
[19]CHAN T,VESE L.An Active Contour Model without Edges[C]∥International Conference on Scale-Space Theories in Computer Vision.Springer-Verlag,1999:141-151.
[20]LIU J,ZHANG X,ZHU J W.An ICP three-dimensional point cloud registration method based on K-D tree optimization[J].Engineering of Surveying and Mapping,2016,25(6):15-18.(in Chinese) 刘江,张旭,朱继文.一种基于K-D树优化的ICP三维点云配准方法[J].测绘工程,2016,25(6):15-18.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于空间对齐和轮廓匹配的颈动脉多对比MRI三维配准方法

Multi-contrast Carotid MRI 3D Registration Method Based on Spatial Alignment and Contour Matching

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

Metrics

本文评价

推荐阅读 0

[1]	戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[2]	黄雪冰, 魏佳艺, 沈文宇, 凌力. 基于自适应加权重复值滤波和同态滤波的MR图像增强 MR Image Enhancement Based on Adaptive Weighted Duplicate Filtering and Homomorphic Filtering 计算机科学, 2021, 48(6A): 21-27. https://doi.org/10.11896/jsjkx.200800183
[3]	张文华, 刘晓鸽, 王沛沛, 刘静静, 程敬亮. 肝脏多b值扩散加权图像的三维配准 3D Registration for Multi-b-value Diffusion Weighted Images of Liver 计算机科学, 2020, 47(11A): 241-243. https://doi.org/10.11896/jsjkx.200400060
[4]	吕鸿蒙,赵地,迟学斌. 基于增强AlexNet的深度学习的阿尔茨海默病的早期诊断 Deep Learning for Early Diagnosis of Alzheimer’s Disease Based on Intensive AlexNet 计算机科学, 2017, 44(Z6): 50-60. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.011
[5]	李勇明,周顺,王洪辉,高乙文. 基于脑磁共振图像配准的动态联合角点检测算法 Dynamic Combinational Corner Detection Algorithm Based on Brain Magnetic Resonance Image Registration 计算机科学, 2012, 39(6): 278-282.
[6]	. 基于动态自适应蚁群算法的MRI图像分割计算机科学, 2008, 35(2): 226-229.