Abstract Recently multi-contrast magnetic resonance imaging (MRI) has become a powerful tool for plaque analyzing due to its strong potential in enhanced demonstration of carotid wall, but its performance is hampered by the misalignment of difference imaging sequences. To achieve accurate vessel registration of multi-sequence images, a two-step coarse-to-fine registration strategy was proposed in this study. First, the iterative closest point was applied to realize the rigid registration of the centerlines of the multi-contrast images, and then the thin plate spline was used to realize the non-rigid registration based on the boundaries of carotid artery. In the second step, to find the corresponding points of the boundaries in different sequences, a shape context descriptor was innovatively introduced to screen the boundary points. In addition, the deterministic annealing technique was employed to find a globally optimized solution. The effectiveness of the proposed algorithm was quantitatively evaluated by novel three-dimensional (3D) multi-contrast vessel wall MRI sequences. The results indicated that after registration, the overlap of two boundaries from different sequences was more than 95%, and their mean surface distance was 0.12 mm, which improved the accuracy of registration effectively and laid the foundation for further component analysis.
Wu Yuxia,Xu Xiaopan,Zhang Xi, et al. Multi-Contrast Magnetic Resonance Imaging Registration of Carotid Arteries[J]. Chinese Journal of Biomedical Engineering, 2017, 36(2): 129-135.
[1] Naghavi M, Libby P, Falk E, et al. From vulnerable plaque to vulnerable patient: a call for new definitions and risk assessment strategies: part I [J]. Circulation, 2003, 108(14):1664-1672.
[2] CaiJianming, Hatsukami TS, Ferguson MS, et al. Classification of human carotid atherosclerotic lesions with in vivo multicontrast magnetic resonance imaging [J]. Circulation, 2002, 106(11):1368-1373.
[3] 李睿,陈慧军,苑纯. 磁共振颈动脉斑块成像技术的现状与进展[J]. 中国卒中杂志, 2014, 9(2):129-134.
[4] Viola P, Wells III WM. Alignment by maximization of mutual information [J]. International Journal of Computer Vision, 1995, 24(2):16-23.
[5] Studholme C, Hill D, Hawkes DJ. An overlap invariant entropy measure of 3D medical image alignment [J]. Pattern Recognition. 1999, 32(1):71-86.
[6] Can A, Stewart CV, Roysam B, et al. A feature-based, robust, hierarchical algorithm for registering pairs of images of the curved human retina [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3):347-364.
[7] Stewart CV, Tsai CL, Roysam B. The dual-bootstrap iterative closest point algorithm with application to retinal image registration [J]. IEEE Transactions on Medical Imaging, 2003, 22(11):1379-1394.
[8] GuoHengkai, Wang Guilin, Huang Lingyun, et al. A robust and accurate two-step auto-labeling conditional iterative closest points (TACIP) algorithm for three-dimensional multi-modal carotid image registration [J]. PLoS ONE, 2016, 11(2):1-22.
[9] Balu N, Yarnykh VL, Chu B, et al. Carotid plaque assessment using fast 3D isotropic resolution black-blood MRI [J]. Magnetic Resonance in Medicine, 2011, 65(3):627-637.
[10] Wang Jinnan, B rnert P, Zhao Huilin, et al. Simultaneous noncontrast angiography and intraplaque hemorrhage (SNAP) imaging for carotid atherosclerotic disease evaluation [J]. Magnetic Resonance in Medicine, 2013, 69(2):337-345.
[11] Mihai G, Chung Y, Merchant A, et al. T1-weighted-SPACE dark blood whole body magnetic resonance angiography (DB-WBMRA): Initial experience [J]. Journal of Magnetic Resonance Imaging, 2010, 31(2):502-509.
[12] Zhao Huilin, Wang Jinnan, Liu Xiaosheng, et al. Assessment of carotid artery atherosclerotic disease by using three-dimensional fast black-blood MR imaging: comparison with DSA [J]. Radiology, 2015, 274(2): 508-516.
[13] Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11):1222-1239.
[14] 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.
[15] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 4(24):509-522.
[16] Papadimitriou CH. Combinatorial optimization: algorithms and complexity [M]//New York: Docer Pub, 1982: 248-254.
[17] Bookstein FL. Principal warps: thin-plate splines and the decomposition of deformations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(6):567-585.
[18] Rose K, Gurewitz E, Fox CG. Statistical mechanics and phase transitions in clustering [J]. Physical Review Letters, 1990, 65 (8):945-948.
[19] Belongie S, Malik J, and Puzicha J. Shape context: A new descriptor for shape matching and object recognition [C] // Advaces in Neural Information Processing Systems13. Barcelona: MIT Press, 2001: 831-837.
[20] Chui H, Rangarajan A. A new point matching algorithm for non-rigid registration [J]. Computer Vision and Image Understanding, 2003, 89(2-3):114-141.
[21] van’tKlooster R, Staring M, Klein S, et al. Automated registration of multispectral MR vessel wall images of the carotid artery [J]. Medical Physics, 2013, 40(12): 1-12.
