摘要
在图像引导的脊柱手术中,实时高效的2D/3D配准是一项重要且具有挑战性的任务.通常的2D/3D配准一般是将三维图像投影到二维平面,然后进行2D/2D的配准.由于投影空间涉及到3个平移以及3个旋转参数,其投影空间的复杂度为O(n6),使得配准很难兼具高准确性和高实时性.本文提出了一个结合机器学习与几何变换的2D/3D配准方法,首先,使用统计形状模型对目标脊椎进行建模,并构建了一种新的投影方式,使得6个投影参数中的4个可以使用几何的方法计算出来;接下来利用回归学习的方法学习目标脊椎的形状与投影参数之间的关系;最终,结合学到的关系和几何变换完成配准.本方法的两个姿态参数的平均预测误差为0.84?和0.81?,平均目标配准误差(Mean target registration error,m TRE)为0.87 mm,平均配准时间为0.9 s.实验结果表明本方法具有很好的实时性和准确性.
In spine operations, an effective 2 D/3 D registration is of great importance yet a challenging task. Traditional2 D/3 D registration approach projects 3 D data to a 2 D plan then conducts a 2 D/2 D registration. It is difficult to obtain both high accuracy and good real-time performance, because the projection space has 3 translation and 3 rotation degrees of freedom and its complexity O(n6). In this paper we propose a method which combines machine learning strategy with geometric transformation. We build a shape model using statistical shape model and construct a new projection method,which makes it possible to calculate that 4 of the 6 projection parameters with the geometric method. Then we use regression learning method to learn a pose model between shape of vertebra and projection parameters. Finally we fulfill the registration by using the learned pose model and geometric transformation. Using the proposed method, the mean predicted errors of two pose parameters are 0.84?and 0.81?, respectively. The mean target registration error(m TRE) is0.87 mm. And the mean time of registration is 0.9 s. These results show that our method owns both high accuracy and good real-time performance.
引文
1 Wu J,Kim M,Peters J,Chung H,Samant S S.Evaluation of similarity measures for use in the intensity-based rigid2D-3D registration for patient positioning in radiotherapy.Medical Physics,2009,36(12):5391-5403
2 Russakoff D B,Rohlfing T,Adler J R,Maurer C R.Intensity-based 2D-3D spine image registration incorporating a single fiducial marker.Academic Radiology,2005,12(1):37-50
3 Otake Y,Wang A S,Webster S J,Uneri A,Kleinszig G,Vogt S,Khanna A J,Gokaslan Z L,Siewerdsen J H.Robust 3D-2D image registration:application to spine interventions and vertebral labeling in the presence of anatomical deformation.Physics in Medicine and Biology,2013,58(23):8535-8553
4 Russakoff D B,Rohlfing T,Ho A,Kim D H,Shahidi R,Adler J R,Maurer C R.Evaluation of intensity-based 2D-3D spine image registration using clinical gold-standard data.In:Proceedings of the 2nd International Workshop on Biomedical Image Registration(WBIR 2003).Philadelphia,PA,USA:Springer-Verlag,2003.151-160
5 Zollei L,Grimson E,Norbash A,Wells W.2D-3D rigid registration of X-ray fluoroscopy and CT images using mutual information and sparsely sampled histogram estimators.In:Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR2001).Kauai,HI,USA:IEEE,2001.II-696-II-703
6 Kim J,Yin F F,Zhao Y,Kim H J.Effects of X-ray and CT image enhancements on the robustness and accuracy of a rigid 3D/2D image registration.Medical Physics,2005,32(4):866-873
7 Chen H M,Goela A,Garvin G J,Li S.A parameterization of deformation fields for diffeomorphic image registration and its application to myocardial delineation.In:Proceedings of the 13th international conference on Medical Image Computing and Computer-Assisted Intervention-(MIC-CAI 2010).Beijing,China:Springer-Verlag,2010.340-348
8 Pohl K M,Wells W M,Guimond A,Kasai K,Shenton M E,Kikinis R,et al.Incorporating non-rigid registration into expectation maximization algorithm to segment MR images.In:Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention-(MICCAI 2002).Tokyo,Japan:Springer-Verlag,2002.564-571
9 Chou C R,Frederick B,Mageras G,Chang S,Pizer S.2D/3D Image Registration using Regression Learning.Computer Vision and Image Understanding,2013,117(9):1095-1106
10 Cyr C M,Kamal A F,Sebastian T B,Kimia B B.2D-3D registration based on shape matching.In:Proceedings of the 2000 IEEE Workshop on Mathematical Methods in Biomedical Image Analysis.Washington,D.C.,USA:IEEEComputer Society,2000.198
11 Philipp S,Markus N,Karl F,Felix S,Deutschmann H.A novel class of machine-learning-driven real-time 2D/3Dtracking methods:texture model registration(TMR).Proceedings of the SPIE,2011,DOI:10.1117/12.878147
12 Gouveia A R,Metz C,Freire L,Klein S.3D-2D image registration by nonlinear regression.In:Proceedings of the9th IEEE International Symposium on Biomedical Imaging.Barcelona,Spain:IEEE,2012.1343-1346
13 Cootes T F,Taylor C J,Cooper D H,Graham J.Active shape models-their training and application.Computer Vision and Image Understanding,1995,61(1):38-59
14 Cootes T F,Edwards G J,Taylor C J.Active appearance models.IEEE Transactions on Pattern Analysis and Machine Intelligence,2001,23(6):681-685
15 van Ginneken B,Frangi A F,Staal J J,Ter Haar Romeny BM,Viergever M A.Active shape model segmentation with optimal features.IEEE Transactions on Medical Imaging,2002,21(8):924-933
16 Cootes T F,Hill A,Taylor C J,Haslam J.The use of active shape models for locating structures in medical images.In:Proceedings of the 13th International Conference on Information Processing in Medical Imaging.London,UK:Springer-Verlag,1993.33-47
17 Gower J G.Procrustes Analysis.International Encyclopedia of the Social and Behavioral Sciences,2001,39(4):12141-12143
18 Lee D T,Schachter B J.Two algorithms for constructing a Delaunay triangulation.International Journal of Parallel Programming,1980,9(3):219-242