Multi-modal MRI Image Registration Based on Adaptive Diffeomorphic Multi-Resolution Demons Algorithm
Wang Chang1,2, Ren Qiongqiong1,2, Qin Xin1,2, Liu Yan1, Li Zhenxin1, Yu Yi1,2*
1School of Biomedical Engineering, Xinxiang Medical University, Xinxiang 453003, Henan,China 2Key Lab of Neurosense and Control, Xinxiang Medical University, Xinxiang 453003, Henan,China
Abstract：Diffeomorphic Demons can guarantee the deformation smooth and reversible and avoid producing unreasonable deformation simultaneously. But its iterations need to be set manually and have great impact on registration results. In order to solve this problem, the adaptive diffeomorphic multi-resolution demons was proposed in this paper. Firstly optimization theory framework of non-rigid registration and multi-resolution strategy were used, then similarity energy function based on gray level was designed, and termination condition was set, finally the iteration number was realized adaptively. Check board image, same modality and different modality MRI were tested, quantitative analysis was made using registration evaluation index, and the influence of different driving forces and parameters on registration result were analyzed. Experimental results indicated that, for the same modality of MRI, the mean square error was 514.7965, normalized cross correlation was 0.9993, structural similarity was 0.9948 by this method. For the different modality of MRI, the mean square error was 1354.1, normalized cross correlation was 0.5935, structural similarity was 0.5116. The Mean square error ws the lowest, normalized cross correlation and structural similarity was the highest. In conclusion, this method is effective and robust, showing the application potential in the non-rigid registration of MRI images.
[1] Svarm L, Enqvist O, Kahl F, et al. Improving robustness for inter-subject medical image registration using a feature-based approach [C] //IEEE International Symposium on Biomedical Imaging. New York: IEEE, 2015,824-828. [2] Wang H,Dong L, O’Daniel J, et al. Validation of an accelerated ‘demons’ algorithm for deformable image registration in radiation therapy [J]. Physics in Medicine and Biology, 2005. 50(12): 2887-2905. [3] Pennec X, Cachier P, Ayache N. Understanding the demons algorithm: 3D non-rigid registration by gradient descent [C] //Taylor C, Colchester A, eds. Processings of 2nd International Conference on Medical Image Computing and Computer -Assisted Intervention. Berlin: Springer-Verlag, 1999, 597-605. [4] Hellier P,Barillot C,Corouge I,et al. Retrospective evaluation of inter-subject brain registration [J]. IEEE Transactions on Medical Imaging,2003, 22(9): 1120-1130. [5] 杨佩. 基于Active Demons算法的非刚性图像配准方法研究[D]. 济南:山东大学, 2015. [6] 薛鹏, 杨佩, 曹祝楼, 等. 基于平衡系数的Active Demons非刚性配准算法[J]. 自动化学报, 2016, 42(9):1389-1440. [7] Cazoulat G, Simon A, Dumenil A, et al. Surface-constrained nonrigid registration for dose monitoring in prostate cancer radiotherapy [J]. IEEE Transactions on Medical Imaging, 2014, 33(7):1464:1474. [8] Cao Zhoulou, Dong Enqing, Zheng Qiang, et al. Accurate inverse-consistent symmetric optical flow for 4D CT lung registration [J]. Biomedical Signal Processing and Control, 2016, 24(9): 25-33. [9] David M, David RH, Hubert V, et al. PET-CT Image Registration in the Chest Using Free-form Deformations[J]. IEEE Transactions on Image Processing, 2003, 22(1):120-128. [10] 雷文娟,祝轩,贾义亭,等. 梯度与曲率变形力相结合的图像配准方法[J],计算机工程与应用, 2012,48(5):204-206. [11] 林相波, 邱天爽, 阮素, 等. Demons 非刚性配准算法拓扑保持性的研究[J].自动化学报, 2010, 36(1):179-183. [12] Vercauteren T,Pennec X,Perchant A,et al. Non-parametric diffeomorphic image registration with the demons algorithm [C] // Ayache N, Ourselin S, Maeder A, eds. Proceedings of 10th International Conference on Medical Image Computing and Computer Assisted Intervention. Berlin: Springer-Verlag, 2007:319-326. [13] Vercauteren T,Pennec X, Perchant A, et al. Diffeomorphic demons: efficient non-parametric image registration[J]. Neuroimage, 2009, 45(1):61-72. [14] 徐峰, 刘伟, 李传富, 等. 具有大形变特征的颅脑CT图像的非刚性配准[J]. 中国生物医学工程学报, 2010, 29(2):172-177. [15] 张娟.医学图像配准中相似性测度的研究[D].广州:南方医科大学, 2014. [16] Wang Z, Bovik AC, Sheikh HR, et al. Image quality assessment: From error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
